Artificial Intelligence-Based Optical Imaging Data Analysis Method and System

Abstract

Embodiments of the present application relate to the technical field of image data processing, specifically to an optical imaging data analysis method and system based on artificial intelligence. An image analysis idea based on a liquid crystal imaging wavelet descriptor is proposed. By constructing a professional liquid crystal imaging pattern example set and using the wavelet descriptor for refined feature extraction, the embodiments of the present application aim to improve the accuracy and efficiency of liquid crystal visual acuity chart quality inspection. At the same time, through an innovative algorithm debugging strategy, the embodiments of the present application further improve the intelligent level of the automated quality inspection system, providing strong technical support for the technological progress and industrial upgrading of the liquid crystal display industry.

Description

Technical Field

[0001] This application relates to the technical field of image data processing, and more specifically, to an optical imaging data analysis method and system based on artificial intelligence. Background Art

[0002] Today, with the rapid development of liquid crystal display technology, the quality inspection of liquid crystal eye charts has become a key link to ensure product performance and user experience. However, traditional quality inspection methods often rely on manual visual inspection, which is not only inefficient but also easily affected by human factors, making it difficult to ensure the accuracy and consistency of inspections. With the rise of artificial intelligence technology, using algorithms to perform automated quality inspection on liquid crystal eye charts has become an inevitable trend in the industry's development.

[0003] However, existing automated quality inspection technologies often have problems such as low recognition accuracy and slow processing speed when faced with complex and variable liquid crystal image features. Especially when identifying subtle defects and classifying similar features, the limitations of existing technologies are more obvious. In addition, due to the imaging characteristics of liquid crystal eye charts, their image data contains a large amount of detailed information, which requires quality inspection algorithms to not only have efficient processing capabilities but also accurate feature extraction and classification capabilities. Summary of the Invention

[0004] In view of this, this application provides an optical imaging data analysis method and system based on artificial intelligence.

[0005] An embodiment of this application provides an optical imaging data analysis method applied to an optical imaging data analysis system. The method includes:

[0006] Obtain a liquid crystal imaging pattern example set corresponding to an optical image learning data set; the liquid crystal imaging pattern example set includes a first liquid crystal imaging pattern example and a second liquid crystal imaging pattern example; the first liquid crystal imaging pattern example carries quality inspection standard annotations, and the second liquid crystal imaging pattern example carries quality inspection defect annotations;

[0007] Determine the liquid crystal imaging wavelet descriptors corresponding to each liquid crystal imaging pattern example in the liquid crystal imaging pattern example set;

[0008] Perform clustering based on a number of the liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern example set to obtain a number of wavelet descriptor cluster sets;

[0009] Determine a target wavelet descriptor cluster set according to the liquid crystal imaging wavelet descriptors corresponding to each of the number of wavelet descriptor cluster sets;

[0010] Adjust the annotations of the first liquid crystal imaging pattern examples corresponding to the target wavelet descriptor cluster set to the quality inspection defect annotations to obtain an adjusted liquid crystal imaging pattern example set;

[0011] Adjust the initial image analysis algorithm according to the liquid crystal imaging map example set to obtain the target image analysis algorithm.

[0012] In some technical solutions, clustering is performed based on several liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern example set to obtain several wavelet description cluster sets, including: determining the wavelet description common value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the liquid crystal imaging wavelet descriptors corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively; clustering several wavelet description common values corresponding to the liquid crystal imaging pattern example set to obtain the several wavelet description cluster sets;

[0013] Determining the target wavelet description cluster set according to the liquid crystal imaging wavelet descriptors corresponding to the several wavelet description cluster sets respectively includes: determining the target wavelet description cluster set according to the wavelet description common values corresponding to the several wavelet description cluster sets respectively.

[0014] In some technical solutions, determining the target wavelet description cluster set according to the liquid crystal imaging wavelet descriptors corresponding to the several wavelet description cluster sets respectively includes: determining the wavelet description cluster set including the imaging defect wavelet descriptor in the several wavelet description cluster sets as the target wavelet description cluster set;

[0015] Among them, the determination method of the imaging defect wavelet descriptor includes:

[0016] Obtain the past liquid crystal imaging atlas corresponding to the past optical image data set; the past liquid crystal imaging atlas includes the first past liquid crystal imaging map and the second past liquid crystal imaging map;

[0017] Determine the liquid crystal imaging wavelet descriptors corresponding to each past liquid crystal imaging map in the past liquid crystal imaging atlas;

[0018] Cluster according to several past liquid crystal imaging wavelet descriptors corresponding to the past liquid crystal imaging atlas to obtain several past wavelet description cluster sets;

[0019] Determine the proportion of the second imaging map corresponding to each past wavelet description cluster set;

[0020] Determine the past wavelet description cluster set with the proportion of the second imaging map greater than the first set threshold as the defect description cluster set;

[0021] Determine the past liquid crystal imaging wavelet descriptors in the defect description cluster set as the imaging defect wavelet descriptors.

[0022] In some technical solutions, clustering is performed on the several past liquid crystal imaging wavelet descriptors corresponding to the past liquid crystal imaging atlas to obtain several past wavelet description cluster sets, including: determining a past wavelet description common value between the first past liquid crystal imaging map and the second past liquid crystal imaging map according to the past liquid crystal imaging wavelet descriptors corresponding to the first past liquid crystal imaging map and the second past liquid crystal imaging map respectively; performing clustering according to the several past wavelet description common values corresponding to the past liquid crystal imaging atlas to obtain the several past wavelet description cluster sets;

[0023] The method further includes: determining the sampling description common value in the defect description cluster set as the commonality measurement threshold; the sampling description common value in the defect description cluster set is less than the first wavelet description common value; the first wavelet description common value is the wavelet description common value in the defect description cluster set except the sampling description common value;

[0024] Determining the target wavelet description cluster set according to the wavelet description common values corresponding to the several wavelet description cluster sets respectively includes: determining the target wavelet description common value in each wavelet description cluster set; the target wavelet description common value in any wavelet description cluster set is less than the second wavelet description common value in the any wavelet description cluster set; the second wavelet description common value in any wavelet description cluster set is the wavelet description common value in the any wavelet description cluster set except the target wavelet description common value; determining the wavelet description cluster set whose target wavelet description common value is not less than the commonality measurement threshold as the target wavelet description cluster set.

[0025] In some technical solutions, the method further includes: determining the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively; determining the pixel description common value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively;

[0026] Performing clustering on the several wavelet description common values corresponding to the liquid crystal imaging pattern example set to obtain the several wavelet description cluster sets includes: performing clustering on the several wavelet description common values and the several pixel description common values corresponding to the liquid crystal imaging pattern example set to obtain the several wavelet description cluster sets.

[0027] In some technical solutions, the method further includes: constructing a first mapping rule corresponding to the image semantic block in the liquid crystal imaging pattern example; the first mapping rule includes adjusting the pixel features of the object label into a first linear vector, adjusting the pixel features of the table label into a second linear vector, and adjusting the pixel features of the curve label into a third linear vector;

[0028] Determining the liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern examples in the liquid crystal imaging pattern example set includes: mapping each liquid crystal imaging pattern example in the liquid crystal imaging pattern example set into a first liquid crystal imaging wavelet descriptor according to the first mapping rule; and determining the liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern examples according to the first liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern examples.

[0029] In some technical solutions, the method further includes: constructing a second mapping rule corresponding to the image semantic block; the second mapping rule is to construct a semantic feature relationship network of a target scale; wherein, the target scale corresponds to a set number of vertically distributed labels, and the set number of vertically distributed labels includes a plurality of first vertically distributed labels and a plurality of second vertically distributed labels; each first vertically distributed label corresponds to an imaging object, and the linear vector in each first vertically distributed label represents whether the imaging object corresponding to each first vertically distributed label exists in the image semantic block; each second vertically distributed label corresponds to a non-imaging object pixel feature; the non-imaging object pixel feature includes a linear vector and a curve feature; the linear vector in each second vertically distributed label represents whether the non-imaging object pixel feature corresponding to each second vertically distributed label exists in the image semantic block.

[0030] Determining the liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern examples according to the first liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern examples includes: mapping each liquid crystal imaging pattern example into a second liquid crystal imaging wavelet descriptor according to the second mapping rule; and determining the liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern examples according to the first liquid crystal imaging wavelet descriptors and the second liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern examples.

[0031] In some technical solutions, the method further includes: constructing a third mapping rule corresponding to the image semantic block; the third mapping rule includes dividing the image semantic block into two local image semantic blocks according to the target pixel features in the image semantic block; mapping the two local image semantic blocks into local liquid crystal imaging wavelet descriptors respectively according to the first mapping rule; and determining the mean calculation result of the two local liquid crystal imaging wavelet descriptors to obtain the liquid crystal imaging wavelet descriptor.

[0032] Determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptor and the second liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example includes: mapping each liquid crystal imaging pattern example into a third liquid crystal imaging wavelet descriptor according to the third mapping rule; determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptor, the second liquid crystal imaging wavelet descriptor, and the third liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example.

[0033] In some technical solutions, the method further includes: constructing a fourth mapping rule corresponding to the image semantic block; the fourth mapping rule includes dividing the image semantic block into two local image semantic blocks according to the target pixel features in the image semantic block; mapping the two local image semantic blocks into local liquid crystal imaging wavelet descriptors respectively according to the second mapping rule; determining the averaging calculation result of the two local liquid crystal imaging wavelet descriptors to obtain the liquid crystal imaging wavelet descriptor;

[0034] Determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptor, the second liquid crystal imaging wavelet descriptor, and the third liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example includes: mapping each liquid crystal imaging pattern example into a fourth liquid crystal imaging wavelet descriptor according to the fourth mapping rule; determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptor, the second liquid crystal imaging wavelet descriptor, the third liquid crystal imaging wavelet descriptor, and the fourth liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example.

[0035] In some independent technical solutions, determining the pixel description common value of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively includes:

[0036] Determining the target linked imaging atlas of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively;

[0037] Determining the image semantic block dimensions corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively;

[0038] Determine the first pixel description commonality value of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the respective image semantic block dimensions of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example and the target linked imaging atlas;

[0039] Determine the pixel description commonality value of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the first pixel description commonality value.

[0040] In some independent technical solutions, the determining the pixel description commonality value of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the first pixel description commonality value includes:

[0041] Determine the linked pixel features of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the respective image semantic blocks of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example;

[0042] Determine the second pixel description commonality value of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the respective image semantic block dimensions of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example and the linked pixel features;

[0043] Determine the pixel description commonality value of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the first pixel description commonality value and the second pixel description commonality value.

[0044] In some independent technical solutions, the determining the pixel description commonality value of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the first pixel description commonality value and the second pixel description commonality value includes:

[0045] Determine the respective linear vector ratios of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the respective image semantic blocks of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example;

[0046] Determine the third pixel description commonality value of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the respective linear vector ratios of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example;

[0047] Determine the pixel description commonality value of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the first pixel description commonality value, the second pixel description commonality value, and the third pixel description commonality value.

[0048] In some technical solutions, adjusting the initial image analysis algorithm according to the liquid crystal imaging map adjustment sample set to obtain a target image analysis algorithm includes: inputting each liquid crystal imaging map adjustment sample in the liquid crystal imaging map adjustment sample set into the initial image analysis algorithm to obtain a semantic quantization vector corresponding to each liquid crystal imaging map adjustment sample; determining a quality inspection status prediction result corresponding to each liquid crystal imaging map adjustment sample according to the semantic quantization vectors corresponding to each liquid crystal imaging map adjustment sample; and adjusting the algorithm weight of the initial image analysis algorithm according to the difference between the quality inspection status prediction result corresponding to each liquid crystal imaging map adjustment sample and the quality inspection status certification result corresponding to each liquid crystal imaging map adjustment sample to obtain the target image analysis algorithm.

[0049] The method further includes: obtaining a liquid crystal imaging map to be analyzed for the optical image data to be analyzed; inputting the liquid crystal imaging map to be analyzed into the target image analysis algorithm to obtain an imaging quality inspection view; and if the imaging quality inspection view indicates that the liquid crystal imaging map to be analyzed is a quality inspection defect view, determining the optical image data to be analyzed as non-compliant optical image data.

[0050] This application also provides an optical imaging data analysis system, including: a memory for storing program instructions and data; and a processor coupled to the memory to execute the instructions in the memory to implement the method as described above.

[0051] This application also provides a computer storage medium containing instructions that, when executed on a processor, implement the method as described above.

[0052] The embodiment of this application proposes an image analysis idea based on liquid crystal imaging wavelet descriptors. By constructing a professional liquid crystal imaging pattern sample set and using wavelet descriptors for refined feature extraction, the embodiment of this application aims to improve the accuracy and efficiency of liquid crystal vision chart quality inspection. At the same time, through an innovative algorithm debugging strategy, the embodiment of this application further enhances the intelligent level of the automated quality inspection system, providing strong technical support for the technological progress and industrial upgrading of the liquid crystal display industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0054] Figure 1 It is a schematic flowchart of the steps of an optical imaging data analysis method based on artificial intelligence provided by an embodiment of this application.

[0055] Figure 2 It is a structural block diagram of an optical imaging data analysis system provided by an embodiment of this application. Detailed implementation manners

[0056] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0057] When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application. It should be noted that the terms "first", "second", etc. in the specification of the present application and the above accompanying drawings are used to distinguish similar objects and do not necessarily need to be used to describe a specific order or sequence.

[0058] The method embodiments provided by the embodiments of the present application can be executed in an optical imaging data analysis system, a computer device, or a similar computing device. Taking running on an optical imaging data analysis system as an example, the optical imaging data analysis system may include one or more processors (the processors may include, but are not limited to, processing devices such as a microprocessor MCU or a field programmable gate array FPGA), and a memory for storing data. Optionally, the above optical imaging data analysis system may further include a transmission device for communication functions. Those of ordinary skill in the art can understand that the above structure is only illustrative and does not limit the structure of the above optical imaging data analysis system. For example, the optical imaging data analysis system may further include more or fewer components than those shown above, or have a different configuration from those shown above.

[0059] The memory can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to an optical imaging data analysis method based on artificial intelligence in the embodiments of the present application. The processor executes various functional applications and data processing by running the computer program stored in the memory, that is, the above method is implemented. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, the memory may further include a memory remotely disposed relative to the processor, and these remote memories can be connected to the optical imaging data analysis system through a network. Examples of the above network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0060] The transmission device is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of an optical imaging data analysis system. In one example, the transmission device includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device may be a Radio Frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0061] Referring to the above content, please refer to Figure 1 , Figure 1 FIG. is a schematic flowchart of an optical imaging data analysis method based on artificial intelligence provided by an embodiment of the present application. This method is applied to an optical imaging data analysis system and may further include steps 110-step 160.

[0062] In an exemplary application scenario of liquid crystal visual acuity chart quality inspection, the optical imaging data analysis system plays a crucial role. The following are the detailed steps for the optical imaging data analysis system to execute the technical solution.

[0063] Step 110: Obtain a liquid crystal imaging pattern example set corresponding to the optical image learning data set; the liquid crystal imaging pattern example set includes a first liquid crystal imaging pattern example and a second liquid crystal imaging pattern example; the first liquid crystal imaging pattern example carries a quality inspection passing annotation, and the second liquid crystal imaging pattern example carries a quality inspection defect annotation.

[0064] First, in step 110, the optical imaging data analysis system obtains an optical image learning data set from a database or an external storage device. This data set is specifically for the imaging of the liquid crystal visual acuity chart. The data set contains two types of liquid crystal imaging pattern examples: the first liquid crystal imaging pattern example is a display screen image that passes the quality inspection, while the second liquid crystal imaging pattern example shows various quality inspection defects. These pattern examples are attached with corresponding annotations indicating whether they pass the inspection or the specific defects present.

[0065] Based on the above content, the optical image learning data set is a data set specifically used for learning and training an optical image processing and analysis model. In this application scenario of liquid crystal visual acuity chart quality inspection, this data set contains a large number of optical images of liquid crystal visual acuity charts, which capture the visual performance of the display screen under various conditions. These data are carefully selected and annotated so that machine learning algorithms can extract useful features from them, thereby improving the ability to judge the quality of liquid crystal visual acuity charts.

[0066] The liquid crystal imaging pattern example set is a part of specific pattern examples extracted from the optical image learning dataset, focusing on the imaging characteristics of the liquid crystal visual acuity chart. This pattern example set includes different types of liquid crystal visual acuity chart images, both images of normally working displays and images of displays with various quality problems, which are used to help the algorithm learn and identify the quality status of the liquid crystal visual acuity chart.

[0067] The first liquid crystal imaging pattern example refers to the display screen images marked as passing quality inspection in the liquid crystal imaging pattern example set. These images show the visual effects that the liquid crystal visual acuity chart should present under normal circumstances, without any obvious quality defects. They are important references for training the algorithm to identify the normal display screen state. In contrast to the first liquid crystal imaging pattern example, these pattern examples show the display screen images with quality inspection defects. These defects may include various problems such as bright spots, dark spots, color distortion, and insufficient contrast. The existence of the second liquid crystal imaging pattern example enables the algorithm to learn how to identify and classify these quality problems.

[0068] The quality inspection passed annotation is the annotation information for the first liquid crystal imaging pattern example, clearly indicating that the display screens represented by these images are qualified in quality inspection. These annotations are important guidance in the training process of the machine learning algorithm, helping the algorithm understand which image features are the signs of passing quality inspection.

[0069] Corresponding to the quality inspection passed annotation, these annotations mark the specific quality inspection defects existing in the second liquid crystal imaging pattern example. These annotations describe in detail the type, location, and severity of the defects, providing rich learning materials for the algorithm to accurately identify and classify various quality inspection defects.

[0070] Specifically, in step 110, the primary task of the optical imaging data analysis system is to obtain an optical image learning dataset specifically for the liquid crystal eye chart. This dataset has been previously collected and organized, containing a large amount of liquid crystal eye chart image data. The system needs to extract a set of liquid crystal imaging pattern examples from the dataset, which will serve as the basis for subsequent analysis and learning. The set of liquid crystal imaging pattern examples consists of two types of pattern examples: the first liquid crystal imaging pattern examples and the second liquid crystal imaging pattern examples. The first liquid crystal imaging pattern examples are the display screen images marked as passing quality inspection, which represent the visual effects of the liquid crystal eye chart under normal working conditions. These images can have clear display effects without obvious quality defects. In contrast, the second liquid crystal imaging pattern examples show the display screen images with various quality inspection defects. These defects may include uneven display, color deviation, dead pixels, etc. The existence of these pattern examples is crucial for training the system to identify and classify the quality problems of the liquid crystal eye chart. To ensure the accuracy of subsequent analysis, each liquid crystal imaging pattern example is accompanied by corresponding annotation information. For the first liquid crystal imaging pattern examples, these annotations clearly indicate that the display screen represented by the image passes quality inspection; for the second liquid crystal imaging pattern examples, the annotations detail the existing quality inspection defects and their specific situations. These annotation information will provide important reference bases for subsequent wavelet descriptor extraction, clustering, and algorithm debugging.

[0071] Step 120: Determine the liquid crystal imaging wavelet descriptors corresponding to each liquid crystal imaging pattern example in the set of liquid crystal imaging pattern examples.

[0072] Next, in step 120, the optical imaging data analysis system processes each pattern example in the set of liquid crystal imaging pattern examples to extract their respective liquid crystal imaging wavelet descriptors. The wavelet descriptor is an important tool for capturing the multi-scale features of an image, which helps the system to more accurately understand and analyze the image content.

[0073] Based on the above content, the liquid crystal imaging wavelet descriptor is a feature vector extracted from the liquid crystal eye chart image through wavelet transform technology. This descriptor can capture the detailed changes of the image at different scales and directions, thus effectively representing the key information such as the texture, edges, and shape of the liquid crystal eye chart image. Specifically, the liquid crystal imaging wavelet descriptor can be composed of a multi-dimensional feature vector, where each dimension represents the response intensity of the image under a specific wavelet basis function.

[0074] For example, a typical liquid crystal imaging wavelet descriptor may contain multiple levels of wavelet coefficients, and each level is further subdivided into different directions and frequency bands. These coefficients reflect the energy distribution of the image at different frequencies and directions and are important quantitative indicators of image features. In practical applications, the liquid crystal imaging wavelet descriptor can be represented as a high-dimensional numerical vector, such as [0.12, -0.05, 0.34, ..., -0.18], where each numerical value represents the coefficient value after a specific wavelet transform.

[0075] The liquid crystal imaging wavelet descriptor plays a key role in the quality inspection of liquid crystal vision charts because it can help algorithms accurately identify and classify various subtle defects on liquid crystal vision charts, such as bright spots, dark spots, line defects, etc. By comparing the wavelet descriptors of normal displays and defective displays, an efficient classification model can be trained, thereby improving the automation and accuracy of quality inspection.

[0076] Specifically, in step 120, the core task of the optical imaging data analysis system is to determine the wavelet descriptor corresponding to each pattern example in the liquid crystal imaging pattern example set. This process is the basis for subsequent image analysis and defect detection and is therefore crucial. First, the system traverses each pattern example in the liquid crystal imaging pattern example set. For each pattern example, the system applies the wavelet transform algorithm, which is a widely used mathematical tool in signal processing and can effectively extract the multi-scale features of the image. When performing the wavelet transform, the system selects appropriate wavelet basis functions, such as Haar wavelets, Daubechies wavelets, etc. These functions have good time-frequency localization characteristics and can capture the detailed changes in the image. Through multi-level wavelet decomposition, the image is decomposed into sub-images at different scales and directions, and each sub-image contains the information of the original image in a specific frequency band and direction. Subsequently, the system calculates the wavelet coefficients of each sub-image, and these coefficients reflect the energy distribution of the image at different frequencies and directions. To form a unified and representative feature vector, the system selects key wavelet coefficients and combines them into a high-dimensional numerical vector, that is, the liquid crystal imaging wavelet descriptor. This process is repeated for each pattern example in the liquid crystal imaging pattern example set until each pattern example corresponds to a unique wavelet descriptor. These descriptors not only capture the detailed features of the image but also provide strong data support for subsequent image classification and defect detection. Through the processing of step 120, the optical imaging data analysis system successfully converts the original liquid crystal vision chart image into a series of representative numerical feature vectors, laying a solid foundation for subsequent clustering, classification, and algorithm debugging.

[0077] Step 130: Cluster according to a plurality of the liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern example set to obtain a plurality of wavelet descriptor cluster sets.

[0078] Enter step 130, where the system performs clustering analysis on the pattern examples using the extracted wavelet descriptors, i.e., "grouping". Through a certain algorithm, the system can cluster images with similar features together to form several wavelet description group sets. The images within each group set are highly similar in terms of features.

[0079] Based on the above, the wavelet description group set is a data set obtained during the quality inspection of liquid crystal vision charts by using wavelet transform technology to extract image features and perform clustering analysis. Wavelet transform is a method that can analyze the local features of an image at different scales and directions. Through wavelet transform, the detailed information and structural features of the image can be extracted, and these features are called wavelet descriptors. In quality inspection applications, wavelet descriptors are used to characterize various attributes of liquid crystal vision chart images, such as brightness, contrast, texture, etc. After the wavelet descriptors are extracted, the system uses a clustering algorithm to divide them into different groups (or clusters) according to the similarity and difference of these descriptors. The images within each group have high similarity in terms of features, while the images between different groups have significant differences. The data set formed in this way is called the wavelet description group set. Each group set can be regarded as a collection of liquid crystal vision chart images with similar features, which is crucial for subsequent defect detection and classification. The wavelet description group set can not only help quality inspectors more quickly identify and locate potential defects of liquid crystal vision charts, but also provide strong data support for the debugging and optimization of image analysis algorithms.

[0080] Specifically, step 130 is a key link in the optical imaging data analysis system. It involves performing clustering analysis on liquid crystal imaging pattern examples to form a wavelet description group set. The following is a detailed introduction to this step.

[0081] (1) Data preparation: Before entering step 130, the system has completed the extraction of wavelet descriptors for liquid crystal imaging pattern examples. These descriptors capture the multi-scale features of the image and provide rich information for subsequent clustering analysis.

[0082] (2) Select a clustering algorithm: The system selects a suitable clustering algorithm for grouping according to actual requirements and data characteristics. Commonly used clustering algorithms include K-means, hierarchical clustering, DBSCAN, etc. When selecting an algorithm, it is necessary to consider the efficiency, accuracy of the algorithm, and its adaptability to data distribution.

[0083] (3) Perform clustering: Using the selected clustering algorithm, the system clusters the liquid crystal imaging wavelet descriptors. During this process, the algorithm groups them according to the similarity between the descriptors to form different clusters (i.e., groups). The descriptors within each cluster have high similarity, while the descriptors between clusters have significant differences.

[0084] (4) Form wavelet description clusters: After clustering, the system classifies the liquid crystal imaging pattern examples in each cluster into the corresponding wavelet description clusters. In this way, each wavelet description cluster represents a set of images with certain common characteristics or attributes.

[0085] (5) Verification and optimization: To ensure the accuracy and effectiveness of clustering, the system can use some evaluation metrics (such as silhouette coefficient, Davies-Bouldin index, etc.) to evaluate the clustering results. If it is found that the clustering effect is not good, the system can adjust the parameters of the clustering algorithm or try other algorithms for optimization.

[0086] (6) Output and storage: Finally, the system outputs the formed wavelet description clusters and stores them in a database or external storage device for use in subsequent steps.

[0087] Through the clustering analysis in step 130, the optical imaging data analysis system can organize and utilize the liquid crystal imaging pattern example data more effectively, providing strong support for subsequent quality inspection and defect identification.

[0088] Step 140: Determine the target wavelet description cluster according to the liquid crystal imaging wavelet descriptors corresponding to the several wavelet description clusters.

[0089] In step 140, the optical imaging data analysis system further analyzes these wavelet description clusters and determines a target wavelet description cluster according to the liquid crystal imaging wavelet descriptors therein. This target cluster may contain images of a certain specific defect or feature that quality inspectors are particularly concerned about.

[0090] Based on the above content, the target wavelet description cluster is a specific set selected from multiple wavelet description clusters through the processing and analysis of the optical imaging data analysis system during the quality inspection of the liquid crystal eye chart. The images in this set have similar wavelet descriptor characteristics, and these characteristics may point to a certain defect or specific attribute that quality inspectors are particularly concerned about. The wavelet descriptor is a feature descriptor extracted from an image through wavelet transform, which can capture the detailed information of the image at different scales and directions. The determination of the target wavelet description cluster helps the quality inspection system to more accurately identify and classify various defects on the liquid crystal eye chart, improving the efficiency and accuracy of quality inspection.

[0091] Specifically, step 140 is one of the key steps in the optical imaging data analysis system, which involves determining a target wavelet description cluster from multiple wavelet description clusters. The following is a detailed introduction to the expansion of this step.

[0092] (1) Analyze the wavelet description cluster sets: After completing step 130, the system has obtained several wavelet description cluster sets, and the images in each set have similar wavelet descriptor features. The primary task of step 140 is to conduct an in-depth analysis of these wavelet description cluster sets.

[0093] (2) Feature comparison and screening: The system compares the wavelet descriptors in each wavelet description cluster set to find those features that are highly correlated with quality inspection defects or specific attributes. This may involve comparing with pre-set standards or historical data to identify the cluster sets that may contain important information.

[0094] (3) Determine the target cluster sets: Based on the results of the feature comparison, the system selects one or several wavelet description cluster sets that are most relevant to the quality inspection target as the target wavelet description cluster sets. This set may contain images of a certain defect or specific image attributes that quality inspectors are particularly concerned about and is the key object for subsequent quality inspection analysis.

[0095] (4) Verification and adjustment: After determining the target wavelet description cluster sets, the system can perform a further verification process to ensure that the selected cluster sets indeed meet the quality inspection requirements. If it is found that the selected cluster sets do not match the expectations, the system makes corresponding adjustments to re-select or optimize the target wavelet description cluster sets.

[0096] (5) Output and recording: Finally, the system outputs the determined target wavelet description cluster sets and records the relevant information for use in subsequent steps. This target cluster set will become an important reference in the subsequent quality inspection process, helping the quality inspection system to more accurately identify and classify the defects on the liquid crystal vision chart.

[0097] Through the precise screening and determination of the target wavelet description cluster sets in step 140, the optical imaging data analysis system can conduct subsequent quality inspection analysis more pertinently, improving the efficiency and accuracy of quality inspection. This is a crucial step for liquid crystal vision chart manufacturers to ensure product quality and improve production efficiency.

[0098] Step 150: Adjust the annotations of the first liquid crystal imaging pattern examples corresponding to the target wavelet description cluster sets into the quality inspection defect annotations to obtain an adjusted set of liquid crystal imaging pattern examples.

[0099] After determining the target wavelet description cluster sets, step 150 requires the system to adjust the annotations of the first liquid crystal imaging pattern examples (originally marked as quality inspection compliant images) in this specific cluster set. This is because in the actual quality inspection process, it can be found that some images originally considered compliant actually have subtle defects. By adjusting the annotations of these images to quality inspection defect annotations, the system can create a more accurate adjusted set of liquid crystal imaging pattern examples.

[0100] Based on the above, the liquid crystal imaging map adjustment sample set refers to a set of images formed after specific processing and analysis during the quality inspection of a liquid crystal visual acuity chart. The images in this set originally belonged to the first liquid crystal imaging pattern sample, that is, the images originally marked as passing the quality inspection. However, through further detailed analysis and comparison, it can be found that there are subtle defects in these images that were not detected during the initial quality inspection. Therefore, the annotation of these images needs to be adjusted from the original "quality inspection passed" to "quality inspection defect". Such an adjustment sample set is of great significance for optimizing and improving the quality inspection accuracy of the liquid crystal visual acuity chart. It can help the quality inspection system better learn and identify various potential and hard-to-detect display defects, thereby improving the product quality control level.

[0101] Specifically, in the quality inspection process of the liquid crystal visual acuity chart, step 150 is a key link, which involves the annotation adjustment of the images in a specific image set - the target wavelet description cluster set. The purpose of this step is to more accurately reflect the actual situation in the images and further optimize the accuracy of the quality inspection system. Specifically, when the optical imaging data analysis system determines the target wavelet description cluster set through the previous steps, it will conduct a detailed review and analysis of the first liquid crystal imaging pattern samples in this set. These first liquid crystal imaging pattern samples were originally considered to have passed the quality inspection, but through in-depth data analysis and comparison, the system can discover hidden subtle defects. These defects may not have been noticed during the initial quality inspection, but for manufacturers pursuing high-quality products, they are issues that cannot be ignored. Therefore, in step 150, the system adjusts the annotation of these newly discovered defective images from the original "quality inspection passed" to "quality inspection defect". This adjustment process is not only a correction of the initial quality inspection results but also an improvement of the self-learning ability of the quality inspection system. Through this annotation adjustment, the system can "remember" the characteristics of these subtle defects, so as to more accurately identify similar problems during future quality inspection processes. Finally, after the processing of step 150, a liquid crystal imaging map adjustment sample set will be obtained. The images in this set have all been carefully reviewed and had their annotations adjusted, and they reflect various subtle defects that may exist in the liquid crystal visual acuity chart. This adjustment sample set will become an important reference for subsequent quality inspection work, helping manufacturers continuously improve product quality and customer satisfaction.

[0102] Step 160: Debug the initial image analysis algorithm according to the liquid crystal imaging map adjustment sample set to obtain the target image analysis algorithm.

[0103] Finally, in step 160, the optical imaging data analysis system uses this adjusted sample set to debug and optimize the initial image analysis algorithm. Through continuous iteration and adjustment, the system can finally obtain a more accurate and efficient target image analysis algorithm, which will be used in the future to automatically detect the quality of the liquid crystal eye chart and accurately identify various potential defects.

[0104] Based on the above, the initial image analysis algorithm refers to the image recognition and processing algorithm initially adopted during the quality inspection of the liquid crystal eye chart. This algorithm may be based on some general image processing techniques, such as edge detection, color analysis, shape recognition, etc., and is used to automatically or semi-automatically detect possible defects on the liquid crystal eye chart. However, due to its generality, this initial algorithm may not be able to accurately identify certain specific types of defects, or may not perform well when processing images with special textures and lighting conditions. Therefore, it needs to be debugged and optimized through actual application scenarios and data.

[0105] The target image analysis algorithm is an image analysis algorithm that is more adapted to the specific quality inspection requirements of the liquid crystal eye chart after debugging and optimization. Based on the initial image analysis algorithm, this algorithm makes targeted improvements to the initial algorithm by analyzing and learning a large amount of actual image data (such as the adjusted sample set of liquid crystal imaging diagrams). These improvements may include adjusting parameters, adding specific feature extraction methods, optimizing classifiers, etc., to improve the recognition accuracy and efficiency of specific defects. The target image analysis algorithm is the core algorithm that the optical imaging data analysis system finally uses for automated quality inspection, and its performance directly affects the accuracy and efficiency of quality inspection.

[0106] In detail, in the final stage of the quality inspection of the LCD eye chart, the optical imaging data analysis system ushered in the critical step 160. The core task of this step is to debug and optimize the initial image analysis algorithm using the LCD imaging image adjustment sample set carefully constructed in the previous step to obtain a more accurate and efficient target image analysis algorithm. The system first loads the initial image analysis algorithm, which is a basic algorithm that already has certain image processing capabilities. However, this algorithm may not be fully adapted to the various complex situations and specific defects in the quality inspection of the LCD eye chart. Therefore, the system needs to fine-tune it through the LCD imaging image adjustment sample set. The LCD imaging image adjustment sample set contains various carefully annotated images that reflect various actual situations in the quality inspection process, including common and special defect types. The system inputs these images into the initial image analysis algorithm and observes the output results of the algorithm. By comparing with the annotated information in the sample set, the system can accurately evaluate the performance of the algorithm and find out its shortcomings. Next, the system gradually debugs and optimizes the initial image analysis algorithm based on the evaluation results. This may include adjusting the algorithm's parameter settings, adding new feature extraction methods to increase sensitivity to specific defects, or optimizing the performance of the classifier to reduce misjudgments and missed detections. This process may need to be repeated many times, and the sample set must be re-verified after each adjustment to ensure that the algorithm's performance is continuously improved. In the end, after a series of debugging and optimization work, the system obtained a target image analysis algorithm with significantly improved performance. This algorithm can not only more accurately identify various defects on LCD eye charts, but also achieve higher standards in processing speed and stability. In the future, this target image analysis algorithm will become a core component of the optical imaging data analysis system, providing strong support for the quality inspection of LCD eye charts.

[0107] It can be seen that in the whole process, the optical imaging data analysis system not only improves the efficiency and accuracy of quality inspection by automatically processing and analyzing a large amount of LCD eye chart image data, but also greatly reduces labor costs and misjudgment rate. This is undoubtedly a huge technological advancement for LCD eye chart manufacturers.

[0108] In the embodiments of the present application, by obtaining a specific liquid crystal imaging pattern example set and using liquid crystal imaging wavelet descriptors for image feature extraction and classification, not only the refined detection of the quality of the liquid crystal vision chart is realized, but also the intelligent level of quality inspection is further improved. The specific beneficial effects are manifested in the following aspects: First, by constructing a liquid crystal imaging pattern example set containing quality inspection compliance and quality inspection defect annotations, the embodiments of the present application provide a rich and accurate data basis for subsequent image analysis, ensuring the reliability of the analysis results. Second, the embodiments of the present application use liquid crystal imaging wavelet descriptors to describe image features, and this method can deeply capture the detailed information of the image, providing strong support for subsequent image classification and recognition. Furthermore, through the clustering process of the wavelet descriptors, the embodiments of the present application can quickly locate the image sets with similar features, which not only improves the efficiency of image processing, but also makes it possible to accurately identify specific defects. In addition, the embodiments of the present application also innovatively propose a strategy of adjusting the compliance image annotations in a specific cluster set to defect annotations, and this step effectively corrects the possible errors in the initial annotation, further enhancing the accuracy and practicality of the data set. Finally, by using the adjusted example set to debug the initial image analysis algorithm, the embodiments of the present application successfully obtain a more accurate and efficient target image analysis algorithm. This algorithm can quickly identify and classify objects, features and anomalies in the image in practical applications, providing users with higher-quality decision-making support and significantly improving the automation and intelligent level of the quality inspection of the liquid crystal vision chart.

[0109] In some alternative embodiments, the step of clustering according to a plurality of the liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern example set to obtain a plurality of wavelet description cluster sets includes: determining a wavelet description common value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the liquid crystal imaging wavelet descriptors corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively; clustering a plurality of wavelet description common values corresponding to the liquid crystal imaging pattern example set to obtain the plurality of wavelet description cluster sets. Then the step of determining a target wavelet description cluster set according to the liquid crystal imaging wavelet descriptors corresponding to the plurality of wavelet description cluster sets respectively includes: determining a target wavelet description cluster set according to the wavelet description common values corresponding to the plurality of wavelet description cluster sets respectively.

[0110] In this embodiment, when the optical imaging data analysis system executes the technical solution, a series of refined operations will be carried out. When the system clusters according to the liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern examples, the specific steps are as follows: First, the optical imaging data analysis system extracts the liquid crystal imaging wavelet descriptors corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively. As a mathematical tool, the wavelet descriptor can accurately capture the characteristic changes of the image at different scales and directions, providing rich information for subsequent image analysis.

[0111] Next, based on these wavelet descriptors, the system calculates the wavelet description commonality value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example. This commonality value is actually a quantization index, which reflects the similarity degree of different images in terms of characteristics. The higher the commonality value, the closer these images are in terms of characteristics.

[0112] Subsequently, the optical imaging data analysis system performs clustering analysis on all the calculated wavelet description commonality values, that is, the so-called "clustering". In this process, the system aggregates the images with similar commonality values together to form several wavelet description cluster sets. Each cluster set represents a set of images with similar characteristics.

[0113] After determining these wavelet description cluster sets, the system further analyzes the corresponding wavelet description commonality values of each of them to find the target wavelet description cluster set that best meets the quality inspection requirements. This target cluster set may contain images of a certain characteristic or defect that quality inspectors are particularly concerned about, and it has important guiding significance for subsequent quality inspection work.

[0114] Through the above steps, the optical imaging data analysis system can achieve refined classification and processing of the liquid crystal imaging pattern example set, providing strong support for subsequent image analysis and quality inspection work.

[0115] In this way, by extracting the liquid crystal imaging wavelet descriptors and performing refined clustering processing based on these descriptors, not only the efficiency of image processing is improved, but also the accuracy of classification is ensured. At the same time, by determining the target wavelet description cluster set, the system can quickly locate the images of specific characteristics or defects that quality inspectors are concerned about, providing strong data support for subsequent quality inspection decisions. The implementation of this technical solution greatly improves the intelligent level of liquid crystal visual acuity chart quality inspection, reduces labor costs and misjudgment rates, and brings significant technological progress and industrial upgrading to the liquid crystal display industry.

[0116] In some other alternative technical solutions, determining the target wavelet description cluster set according to the respective corresponding liquid crystal imaging wavelet descriptors of the several wavelet description cluster sets includes: determining the wavelet description cluster set including the imaging defect wavelet descriptor in the several wavelet description cluster sets as the target wavelet description cluster set; wherein, the determining method of the imaging defect wavelet descriptor includes: obtaining a past liquid crystal imaging atlas corresponding to a past optical image data set; the past liquid crystal imaging atlas includes a first past liquid crystal imaging map and a second past liquid crystal imaging map; determining the liquid crystal imaging wavelet descriptors corresponding to each past liquid crystal imaging map in the past liquid crystal imaging atlas; clustering according to the several past liquid crystal imaging wavelet descriptors corresponding to the past liquid crystal imaging atlas to obtain several past wavelet description cluster sets; determining the proportion of the second imaging map corresponding to each past wavelet description cluster set; determining the past wavelet description cluster set with the proportion of the second imaging map greater than a first set threshold as the defect description cluster set; and determining the past liquid crystal imaging wavelet descriptors in the defect description cluster set as the imaging defect wavelet descriptor.

[0117] In this technical solution, when the optical imaging data analysis system determines the target wavelet description cluster set, it will adopt a specific method. This method first focuses on those wavelet description cluster sets that contain the imaging defect wavelet descriptor, and these particularly concerned wavelet description cluster sets are determined as the target wavelet description cluster set.

[0118] To clarify what the imaging defect wavelet descriptor is, its determination process needs to be elaborated in detail. First, the system obtains a past liquid crystal imaging atlas corresponding to a past optical image data set, and this atlas includes at least two types of past liquid crystal imaging maps: the first past liquid crystal imaging map and the second past liquid crystal imaging map. These two imaging maps may represent different imaging conditions or qualities.

[0119] Next, the system determines the corresponding liquid crystal imaging wavelet descriptors for each image in the past liquid crystal imaging atlas. The wavelet descriptor is a mathematical tool that can capture the details and features in the image and is crucial for image recognition and analysis.

[0120] Subsequently, based on these past liquid crystal imaging wavelet descriptors, the system clusters them to form several past wavelet description cluster sets. Each cluster set represents a group of images with similar characteristics.

[0121] To identify which sub-cluster sets may contain imaging defects, the system further analyzes the proportion of the second past liquid crystal imaging map in each past wavelet description sub-cluster set. If the proportion of the second imaging map in a sub-cluster set exceeds a preset first set threshold, then this sub-cluster set is identified as a defect description sub-cluster set. The first set threshold in the embodiment of the present application is a key parameter, which is used to define when a sub-cluster set is considered to contain sufficient imaging defects to be of particular concern.

[0122] Finally, the system determines the past liquid crystal imaging wavelet descriptors in the defect description sub-cluster sets as imaging defect wavelet descriptors. These descriptors represent the image features with significant imaging defects and are crucial for subsequent analysis and processing.

[0123] In this way, the optical imaging data analysis system can accurately identify and focus on those image sets containing imaging defects, providing strong data support for subsequent optimization and correction work. The implementation of this method not only improves the accuracy of image analysis but also provides a scientific basis for improving the quality of liquid crystal displays.

[0124] In an alternative embodiment, the clustering based on the several past liquid crystal imaging wavelet descriptors corresponding to the past liquid crystal imaging atlas to obtain several past wavelet description sub-cluster sets includes: determining the past wavelet description commonality value between the first past liquid crystal imaging map and the second past liquid crystal imaging map according to the past liquid crystal imaging wavelet descriptors corresponding to the first past liquid crystal imaging map and the second past liquid crystal imaging map respectively; clustering according to the several past wavelet description commonality values corresponding to the past liquid crystal imaging atlas to obtain the several past wavelet description sub-cluster sets.

[0125] Then the method further includes: determining the sampled description commonality value in the defect description sub-cluster set as the commonality measurement threshold; the sampled description commonality value in the defect description sub-cluster set is less than the first wavelet description commonality value; the first wavelet description commonality value is the wavelet description commonality value in the defect description sub-cluster set except for the sampled description commonality value.

[0126] Furthermore, the determining of the target wavelet description sub-cluster set according to the wavelet description commonality values corresponding to the several wavelet description sub-cluster sets respectively includes: determining the target wavelet description commonality value in each wavelet description sub-cluster set; the target wavelet description commonality value in any wavelet description sub-cluster set is less than the second wavelet description commonality value in the any wavelet description sub-cluster set; the second wavelet description commonality value in any wavelet description sub-cluster set is the wavelet description commonality value in the any wavelet description sub-cluster set except for the target wavelet description commonality value; determining the wavelet description sub-cluster set with the target wavelet description commonality value not less than the commonality measurement threshold as the target wavelet description sub-cluster set.

[0127] In the application scenario of a liquid crystal visual acuity chart, the optical imaging data analysis system plays a crucial role. In an alternative embodiment, the system deeply analyzes past liquid crystal imaging atlases to identify and classify features in the images.

[0128] First, the system determines the wavelet description commonality value between these two types of imaging charts based on the wavelet descriptors corresponding to the first past liquid crystal imaging chart and the second past liquid crystal imaging chart respectively. This commonality value is actually a quantization index used to measure the similarity or consistency of the wavelet features between the two types of images. By calculating these commonality values, the system can gain insights into the internal connections and differences between the images.

[0129] Next, the system performs a clustering operation based on the calculated multiple past wavelet description commonality values. The "clustering" in the embodiments of this application refers to classifying the image sets with similar commonality values together to form several past wavelet description cluster sets. Each cluster set represents a group of images with a certain specific wavelet feature commonality.

[0130] During this process, the system also particularly focuses on those cluster sets that may contain imaging defects. To accurately identify these defects, the system determines the sampling description commonality value in the defect description cluster set as the commonality measurement threshold. This threshold value acts as a benchmark for subsequent screening and classification of the wavelet description cluster sets. It should be noted that the sampling description commonality value in the defect description cluster set is less than the other wavelet description commonality values (i.e., the first wavelet description commonality value) in this cluster set, which reflects an anomaly or deviation in the imaging characteristics of this cluster set.

[0131] Furthermore, when the system needs to determine the target wavelet description cluster set, it first determines the target wavelet description commonality value in each wavelet description cluster set. This value is a specific value among all the wavelet description commonality values in this cluster set, and it is less than the other wavelet description commonality values (i.e., the second wavelet description commonality value) in this cluster set. Subsequently, the system determines the wavelet description cluster sets whose target wavelet description commonality values are not less than the previously determined commonality measurement threshold as the target wavelet description cluster sets.

[0132] The implementation of this technical solution enables the optical imaging data analysis system to accurately identify and classify groups of images with specific wavelet feature commonalities, especially those groups that may contain imaging defects. In this way, the system not only improves the accuracy of image analysis but also provides strong data support for subsequent image processing and optimization. Specifically, through refined image feature analysis and classification, the effectiveness of the optical imaging data analysis system in the application scenario of the liquid crystal visual acuity chart is significantly improved. It can accurately identify and focus on those image sets with specific imaging characteristics, laying a solid foundation for improving liquid crystal display quality and enhancing user experience.

[0133] In some other preferred embodiments, the method further includes: determining the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively; and determining the pixel description commonality values of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively.

[0134] Then, performing clustering on the several wavelet description commonality values corresponding to the liquid crystal imaging pattern example set to obtain the several wavelet description cluster sets includes: performing clustering on the several wavelet description commonality values and the several pixel description commonality values corresponding to the liquid crystal imaging pattern example set to obtain the several wavelet description cluster sets.

[0135] In the application scenario of the liquid crystal visual acuity chart, the optical imaging data analysis system further demonstrates its advanced functions. In some other preferred embodiments, the system not only focuses on wavelet descriptors, but also deeply explores the information of image semantic blocks, so as to more comprehensively analyze liquid crystal imaging pattern examples.

[0136] First, the system determines the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively. An image semantic block refers to a region in an image with specific semantics or meaning, such as a specific object, background, or texture, etc. By identifying these semantic blocks, the system can more deeply understand the content and structure of the image.

[0137] Next, the system determines the pixel description commonality values of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to these image semantic blocks. The pixel description commonality value is a quantization index used to measure the similarity or consistency between two images at the pixel level. By calculating this value, the system can more precisely compare and analyze the subtle differences between different images.

[0138] Importantly, when performing the clustering operation, the system not only considers the wavelet description commonality values, but also takes the pixel description commonality values into account. This means that the system performs joint clustering on the several wavelet description commonality values and the several pixel description commonality values corresponding to the liquid crystal imaging pattern example set, so as to obtain a more accurate and detailed wavelet description cluster set.

[0139] This clustering method that combines wavelet descriptors and pixel description commonality values enables the system to comprehensively analyze liquid crystal imaging pattern examples from multiple dimensions, improving the accuracy and effectiveness of clustering. In this way, the system can more precisely identify and classify image groups with similar features, providing more powerful support for subsequent image processing, analysis, and optimization.

[0140] Thus, by integrating wavelet descriptors and pixel description common values for cluster analysis, the optical imaging data analysis system demonstrates higher efficiency and accuracy in the application scenario of liquid crystal eye charts. This technical solution not only enhances the depth of image analysis but also provides a more solid technical foundation for improving liquid crystal display quality and user experience.

[0141] In some preferred embodiments, the method further includes: constructing a first mapping rule corresponding to the image semantic blocks in the liquid crystal imaging pattern examples; the first mapping rule includes adjusting the pixel features of the object label into a first linear vector, adjusting the pixel features of the table label into a second linear vector, and adjusting the pixel features of the curve label into a third linear vector.

[0142] Then, determining the liquid crystal imaging wavelet descriptors corresponding to each liquid crystal imaging pattern example in the liquid crystal imaging pattern example set includes: mapping each liquid crystal imaging pattern example in the liquid crystal imaging pattern example set into a first liquid crystal imaging wavelet descriptor according to the first mapping rule; determining the liquid crystal imaging wavelet descriptors corresponding to each liquid crystal imaging pattern example based on the first liquid crystal imaging wavelet descriptors corresponding to each liquid crystal imaging pattern example.

[0143] In some preferred embodiments, the optical imaging data analysis system further introduces a mapping rule to improve the analysis accuracy and efficiency of liquid crystal imaging pattern examples. In this process, the system first constructs a first mapping rule corresponding to the image semantic blocks in the liquid crystal imaging pattern examples.

[0144] This first mapping rule specifically defines how to convert different types of image semantic blocks into corresponding linear vectors. According to the rule, the pixel features of the object label are adjusted into a first linear vector, the pixel features of the table label are adjusted into a second linear vector, and the pixel features of the curve label are adjusted into a third linear vector. Here, the "object", "table", and "curve" labels may be automatically recognized based on the image content or predefined to describe different types of elements or features in the image.

[0145] After determining this mapping rule, the system can then map each liquid crystal imaging pattern example in the liquid crystal imaging pattern example set into a first liquid crystal imaging wavelet descriptor according to it. This step actually converts the semantic information of the image into a form that is more convenient for mathematical processing and comparison, namely, the wavelet descriptor.

[0146] Specifically, the system traverses each pattern example in the liquid crystal imaging pattern example set, identifies the image semantic blocks therein, and converts these semantic blocks into corresponding linear vectors according to the first mapping rule. Subsequently, these linear vectors will be further processed to generate the first liquid crystal imaging wavelet descriptor corresponding to each pattern example.

[0147] Finally, the system determines the liquid crystal imaging wavelet descriptors corresponding to each liquid crystal imaging pattern example based on these first liquid crystal imaging wavelet descriptors. This step may further optimize or standardize the first liquid crystal imaging wavelet descriptors to ensure that they can accurately reflect the characteristics of the image and facilitate subsequent analysis and comparison.

[0148] By introducing this mapping rule, the optical imaging data analysis system can more accurately capture and describe the features in the liquid crystal imaging pattern example, thereby improving the accuracy and efficiency of image analysis. The implementation of this technical solution not only helps the system to better understand the image content, but also provides strong support for subsequent image processing, recognition, and optimization. In other words, by constructing and applying the first mapping rule, the optical imaging data analysis system realizes the accurate analysis and description of the liquid crystal imaging pattern example in the application scenario of the liquid crystal vision chart. This technical solution significantly improves the intelligence and automation level of image analysis, laying a solid foundation for improving the liquid crystal display quality and enhancing the user experience.

[0149] In other possible technical solutions, the method further includes: constructing a second mapping rule corresponding to the image semantic block; the second mapping rule is to construct a semantic feature relationship network of a target scale; wherein, the target scale corresponds to a set number of vertically distributed labels, and the set number of vertically distributed labels includes several first vertically distributed labels and several second vertically distributed labels; each first vertically distributed label corresponds to an imaging object, and the linear vector in each first vertically distributed label represents whether the imaging object corresponding to each first vertically distributed label exists in the image semantic block; each second vertically distributed label corresponds to a non-imaging object pixel feature; the non-imaging object pixel feature includes a linear vector and a curve feature; the linear vector in each second vertically distributed label represents whether the non-imaging object pixel feature corresponding to each second vertically distributed label exists in the image semantic block; the step of determining the liquid crystal imaging wavelet descriptors corresponding to each liquid crystal imaging pattern example based on the first liquid crystal imaging wavelet descriptors corresponding to each liquid crystal imaging pattern example includes: mapping each liquid crystal imaging pattern example into a second liquid crystal imaging wavelet descriptor according to the second mapping rule; determining the liquid crystal imaging wavelet descriptors corresponding to each liquid crystal imaging pattern example based on the first liquid crystal imaging wavelet descriptors and the second liquid crystal imaging wavelet descriptors corresponding to each liquid crystal imaging pattern example.

[0150] In this technical solution, the optical imaging data analysis system further introduces a second mapping rule to deepen the analysis of the liquid crystal imaging pattern example. This rule not only helps the system to more comprehensively understand the image content, but also improves the recognition accuracy of image features.

[0151] Specifically, the second mapping rule is to construct a semantic feature relationship network at the target scale. The target scale of this relationship network corresponds to a set number of vertically distributed labels, which are divided into two categories: the first vertically distributed labels and the second vertically distributed labels.

[0152] The first vertically distributed labels correspond to imaging objects. Each first vertically distributed label represents a specific imaging object, such as characters, graphics, etc. Among these labels, linear vectors are used to characterize whether there is an imaging object corresponding to the label in the image semantic block. In other words, the system determines whether it conforms to a certain first vertically distributed label by examining the pixel features in the image semantic block and represents the result in the form of a linear vector.

[0153] The second vertically distributed labels, on the other hand, correspond to the pixel features of non-imaging objects. These features include linear vectors and curve features, which are used to describe the parts of the image that do not belong to specific imaging objects. Similar to the first vertically distributed labels, the linear vectors in the second vertically distributed labels are also used to characterize whether there are pixel features of non-imaging objects corresponding to the label in the image semantic block.

[0154] After constructing the second mapping rule, the system can map each liquid crystal imaging pattern example into a second liquid crystal imaging wavelet descriptor according to this rule. This process involves in-depth analysis and feature extraction of the image semantic block to ensure that the generated second liquid crystal imaging wavelet descriptor can accurately reflect various features in the image.

[0155] Subsequently, the system combines the first liquid crystal imaging wavelet descriptor and the second liquid crystal imaging wavelet descriptor to determine the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example. This step may involve fusing or weighted averaging the two types of descriptors to obtain a more comprehensive and accurate description of the image features.

[0156] By introducing the second mapping rule and constructing the semantic feature relationship network, the optical imaging data analysis system can analyze various features in the liquid crystal imaging pattern example more meticulously, including the pixel features of imaging objects and non-imaging objects. This not only improves the accuracy and depth of image analysis but also provides a richer information basis for subsequent image processing, recognition, and optimization. In this way, the optical imaging data analysis system realizes in-depth analysis and accurate description of the liquid crystal imaging pattern example in the liquid crystal vision chart application scenario. This technical solution significantly enhances the image analysis ability of the system and provides strong support for improving liquid crystal display quality and user experience.

[0157] In the following steps, the method further includes: constructing a third mapping rule corresponding to the image semantic block; the third mapping rule includes dividing the image semantic block into two local image semantic blocks according to the target pixel features in the image semantic block; mapping the two local image semantic blocks into local liquid crystal imaging wavelet descriptors respectively according to the first mapping rule; and determining the averaging calculation result of the two local liquid crystal imaging wavelet descriptors to obtain a liquid crystal imaging wavelet descriptor; determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptor and the second liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example includes: mapping each liquid crystal imaging pattern example into a third liquid crystal imaging wavelet descriptor according to the third mapping rule; determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptor, the second liquid crystal imaging wavelet descriptor and the third liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example.

[0158] Based on this embodiment, the optical imaging data analysis system further introduces a third mapping rule to optimize the processing and analysis of liquid crystal imaging pattern examples. The design of this rule aims to improve the accuracy and representativeness of liquid crystal imaging wavelet descriptors by refining the processing of image semantic blocks.

[0159] The implementation process of the third mapping rule is as follows: First, the system divides the image semantic block into two local image semantic blocks according to the target pixel features in the image semantic block. The purpose of this step is to divide the image more carefully to better capture and describe the local features therein. The target pixel features may include color, brightness, texture, etc., and these features help the system determine how to effectively segment the image semantic block.

[0160] Next, the system maps the two local image semantic blocks into local liquid crystal imaging wavelet descriptors respectively according to the first mapping rule. This step utilizes the multi-scale characteristics of wavelet transform and can capture the local detail information of the image. By mapping the local image semantic blocks into wavelet descriptors, the system can more accurately represent the features of these regions.

[0161] Then, the system calculates the average of the two local liquid crystal imaging wavelet descriptors to obtain a new liquid crystal imaging wavelet descriptor. The averaging calculation helps to reduce the influence of noise and outliers, making the finally obtained liquid crystal imaging wavelet descriptor more stable and reliable.

[0162] After applying the third mapping rule, the system can map each liquid crystal imaging pattern example into a third liquid crystal imaging wavelet descriptor according to this rule. These third liquid crystal imaging wavelet descriptors capture more local detail information in the image and provide richer data for subsequent image analysis and comparison.

[0163] Finally, the system combines the first liquid crystal imaging wavelet descriptor, the second liquid crystal imaging wavelet descriptor, and the third liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example to determine the final liquid crystal imaging wavelet descriptor for each liquid crystal imaging pattern example. This process may involve weighted averaging or other forms of fusion of the three types of descriptors to ensure that the finally obtained liquid crystal imaging wavelet descriptor can comprehensively and accurately reflect the overall characteristics and local details of the image.

[0164] By introducing the third mapping rule, the optical imaging data analysis system can process and analyze liquid crystal imaging pattern examples more precisely, thereby improving the accuracy and integrity of image feature description. The implementation of this technical solution not only helps the system to understand the image content more deeply, but also provides a more accurate data basis for subsequent image processing, recognition, and optimization.

[0165] In some alternative embodiments, the method further includes: constructing a fourth mapping rule corresponding to the image semantic block; the fourth mapping rule includes dividing the image semantic block into two local image semantic blocks according to the target pixel features in the image semantic block; mapping the two local image semantic blocks into local liquid crystal imaging wavelet descriptors respectively according to the second mapping rule; determining the mean calculation result of the two local liquid crystal imaging wavelet descriptors to obtain the liquid crystal imaging wavelet descriptor; the determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptor, the second liquid crystal imaging wavelet descriptor, and the third liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example includes: mapping each liquid crystal imaging pattern example into a fourth liquid crystal imaging wavelet descriptor according to the fourth mapping rule; determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptor, the second liquid crystal imaging wavelet descriptor, the third liquid crystal imaging wavelet descriptor, and the fourth liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example.

[0166] Based on this embodiment, the optical imaging data analysis system adopts another strategy to further enhance its analysis ability for liquid crystal imaging pattern examples, that is, by constructing and applying the fourth mapping rule. This rule is different from the previous mapping rules. It combines some characteristics of the second mapping rule and processes the image semantic block more carefully.

[0167] Specifically, the fourth mapping rule first divides the image semantic block into two local image semantic blocks according to the target pixel features in the image semantic block. The purpose of this step is to analyze the local features of the image more deeply. The target pixel features may involve color distribution, brightness change, or specific texture patterns, which provide a basis for the reasonable segmentation of the image.

[0168] Next, the system uses the second mapping rule to map these two segmented local image semantic blocks into local liquid crystal imaging wavelet descriptors respectively. Similar to the second mapping rule, this step also involves constructing a semantic feature relationship network, but this time it is applied to smaller image regions, so as to capture more refined feature information.

[0169] Subsequently, the system calculates the mean values of these two local liquid crystal imaging wavelet descriptors to obtain a unified liquid crystal imaging wavelet descriptor. Through the averaging process, the system can reduce the noise and anomalies in the local features and obtain a more stable and representative descriptor.

[0170] After applying the fourth mapping rule, the optical imaging data analysis system can map each liquid crystal imaging pattern example into a fourth liquid crystal imaging wavelet descriptor. These descriptors not only contain the overall features of the image, but also highlight the key local details, providing more abundant information for image analysis and comparison.

[0171] Finally, the system synthesizes the first liquid crystal imaging wavelet descriptor, the second liquid crystal imaging wavelet descriptor, the third liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example, and the newly generated fourth liquid crystal imaging wavelet descriptor to determine the final liquid crystal imaging wavelet descriptor of each liquid crystal imaging pattern example. This process may be achieved through weighted averaging, feature fusion or other advanced algorithms to ensure that the finally obtained descriptor can comprehensively and accurately reflect all the important features of the image.

[0172] By introducing the fourth mapping rule, the optical imaging data analysis system realizes multi-level and multi-angle analysis of liquid crystal imaging pattern examples in the application scenario of the liquid crystal vision chart. The implementation of the embodiments of this application not only improves the accuracy of image feature extraction, but also provides more detailed and accurate data support for subsequent image processing, recognition and optimization.

[0173] In summary, by combining the fourth mapping rule and the previous technical means, the optical imaging data analysis system significantly enhances its image analysis ability in the application scenario of the liquid crystal vision chart. This comprehensive solution can more comprehensively capture and describe the features of liquid crystal imaging pattern examples, laying a more solid foundation for improving liquid crystal display quality and enhancing user experience.

[0174] In some independent embodiments, determining the pixel description commonality value of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example based on the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively includes: determining the target linked imaging atlas of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example based on the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively; determining the dimensions of the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively; determining the first pixel description commonality value of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the dimensions of the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively and the target linked imaging atlas; and determining the pixel description commonality value of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the first pixel description commonality value.

[0175] Based on this embodiment, the optical imaging data analysis system adopts a unique method to determine the pixel description commonality value between two liquid crystal imaging pattern examples (i.e., the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example). This method not only considers the overall characteristics of the images, but also deeply analyzes the similarity and relevance between the images.

[0176] First, the system determines the target linked imaging atlas between the two based on the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively. The target linked imaging atlas can be understood as the set of similar or related parts in the two pattern examples, which reflects the commonality between the two pattern examples at the pixel level.

[0177] Next, the system determines the dimensions of the image semantic blocks corresponding to the two liquid crystal imaging pattern examples respectively. The dimension here refers to the number of features or parameters required to describe the image semantic block, which represents the complexity and information volume of the image. By comparing the dimensions of the two image semantic blocks, the system can initially evaluate the similarity degree between them.

[0178] Then, according to the dimensions of the image semantic blocks of the two pattern examples and the target linked imaging atlas determined previously, the system calculates the first pixel description commonality value. This value is a quantitative index used to measure the similarity or relevance between the two pattern examples at the pixel level. The calculation process may involve complex mathematical operations and image processing techniques to ensure the accuracy and reliability of the results.

[0179] Finally, based on the first pixel description commonality value, the system determines the pixel description commonality value of the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example. This final value is a comprehensive evaluation of the overall similarity between the two pattern examples. It considers multiple aspects and features of the images, so it has high reference value.

[0180] Through this method, the optical imaging data analysis system can accurately evaluate the pixel description commonality value between two liquid crystal imaging pattern examples. This not only helps the system to understand the image content more accurately, but also provides strong support for subsequent image processing, analysis, and comparison. It can be seen that through steps such as determining the target linkage imaging atlas, comparing the dimensions of image semantic blocks, and calculating the pixel description commonality value, this embodiment realizes a comprehensive and quantitative evaluation of the similarity between two liquid crystal imaging pattern examples. The embodiment of the present application significantly improves the accuracy and objectivity of image analysis, and provides strong technical support for image processing in the application scenario of the liquid crystal vision chart.

[0181] In some other independent embodiments, determining the pixel description commonality value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the first pixel description commonality value includes: determining the linkage pixel features between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example based on the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively; determining the second pixel description commonality value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the dimensions of the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively and the linkage pixel features; and determining the pixel description commonality value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the first pixel description commonality value and the second pixel description commonality value.

[0182] In this embodiment, the optical imaging data analysis system further refines the method for determining the pixel description commonality value between two liquid crystal imaging pattern examples (i.e., the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example). This method obtains a more comprehensive and accurate commonality value by deeply analyzing the pixel features and dimensions of the pattern examples.

[0183] First, the system identifies and extracts the linkage pixel features between the two pattern examples based on the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively. The linkage pixel features refer to the pixel features that appear simultaneously, have similarity or relevance in the two pattern examples, such as the same color, texture, or shape, etc. The existence of these features indicates that the two pattern examples have certain commonalities at the pixel level.

[0184] Next, the system calculates the second pixel description commonality value according to the dimensions of the image semantic blocks of the two pattern examples and the extracted linkage pixel features. This value takes into account the dimension information and pixel features of the image, and can more comprehensively reflect the similarity or relevance between the two pattern examples. The calculation process may involve weighted processing of dimensions and features or other complex mathematical operations to ensure the accuracy of the result.

[0185] Finally, the system combines the previously calculated first pixel description commonality value and the second pixel description commonality value to comprehensively determine the pixel description commonality value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example. This comprehensive commonality value is a comprehensive evaluation of the similarity between the two pattern examples at the pixel level. It takes into account multiple aspects and features of the images simultaneously, so it has higher accuracy and reliability.

[0186] Through this method, the optical imaging data analysis system can more deeply analyze and compare the similarity and relevance between the two liquid crystal imaging pattern examples. This not only helps the system to more accurately understand the image content, but also provides a more accurate data basis for subsequent image processing, recognition, and optimization. It can be seen that through steps such as identifying linked pixel features, calculating the second pixel description commonality value, and comprehensively determining the pixel description commonality value, this embodiment realizes in-depth analysis and quantitative evaluation of the similarity between the two liquid crystal imaging pattern examples. The embodiment of the present application further improves the accuracy and comprehensiveness of image analysis, and provides more powerful technical support for image processing in the application scenario of the liquid crystal visual acuity chart.

[0187] In some other independent embodiments, determining the pixel description commonality value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the first pixel description commonality value and the second pixel description commonality value includes: determining the respective linear vector ratios corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example based on the respective image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example; determining the third pixel description commonality value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example based on the respective linear vector ratios corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example; and determining the pixel description commonality value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the first pixel description commonality value, the second pixel description commonality value, and the third pixel description commonality value.

[0188] Based on this embodiment, the optical imaging data analysis system adopts a comprehensive method to determine the pixel description commonality value between two liquid crystal imaging pattern examples (i.e., the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example). This method combines multiple features of the images, thus obtaining a more accurate and comprehensive commonality value.

[0189] First, based on the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively, the system determines the proportion of the linear vectors corresponding to each of these two pattern examples. The proportion of the linear vectors can be understood as the weight or ratio of each feature vector in the image, which reflects the importance of different features in the image. By calculating the proportion of the linear vectors, the system can more accurately grasp the key features of the image.

[0190] Next, based on the proportion of the linear vectors of these two pattern examples, the system determines the third pixel description common value. This value takes into account the weights and ratios of the image feature vectors and can reflect the similarity or difference between the two pattern examples in terms of key features. The calculation process may involve complex mathematical operations and feature comparisons to ensure the accuracy of the results.

[0191] Finally, the system combines the first pixel description common value, the second pixel description common value calculated previously, and the newly obtained third pixel description common value to determine the pixel description common value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example. This comprehensive common value is a comprehensive assessment of the similarity between the two pattern examples at multiple levels. It takes into account multiple factors such as the dimensions, features, and proportion of feature vectors of the image, so it has higher accuracy and credibility.

[0192] Through this method, the optical imaging data analysis system can more accurately evaluate the similarity between two liquid crystal imaging pattern examples. This not only helps the system better understand the image content but also provides more accurate data support for subsequent image processing, comparison, and optimization. It can be seen that through steps such as calculating the proportion of the linear vectors, determining the third pixel description common value, and combining multiple common values, this embodiment realizes a comprehensive and accurate assessment of the similarity between two liquid crystal imaging pattern examples. The embodiment of the present application further improves the accuracy and credibility of image analysis and provides a more reliable technical guarantee for image processing in the application scenario of the liquid crystal vision chart.

[0193] In some preferred embodiments, the adjusting the initial image analysis algorithm according to the liquid crystal imaging map adjustment sample set to obtain the target image analysis algorithm includes: inputting each liquid crystal imaging map adjustment sample in the liquid crystal imaging map adjustment sample set into the initial image analysis algorithm to obtain the semantic quantization vector corresponding to each liquid crystal imaging map adjustment sample; determining the quality inspection status prediction result corresponding to each liquid crystal imaging map adjustment sample according to the semantic quantization vector corresponding to each liquid crystal imaging map adjustment sample; and adjusting the algorithm weight of the initial image analysis algorithm according to the difference between the quality inspection status prediction result corresponding to each liquid crystal imaging map adjustment sample and the quality inspection status certification result corresponding to each liquid crystal imaging map adjustment sample to obtain the target image analysis algorithm.

[0194] Further, the method further includes: obtaining a liquid crystal imaging map to be analyzed from the optical image data to be analyzed; inputting the liquid crystal imaging map to be analyzed into the target image analysis algorithm to obtain an imaging quality inspection view; if the imaging quality inspection view indicates that the liquid crystal imaging map to be analyzed is a quality inspection defect view, determining the optical image data to be analyzed as non-compliant optical image data.

[0195] Based on this embodiment, the optical imaging data analysis system adopts a refined method to optimize and adjust the image analysis algorithm, so as to more accurately identify and analyze the quality of the liquid crystal imaging map. In this process, the system first uses the liquid crystal imaging map adjustment sample set to debug the initial image analysis algorithm, and then obtains a more accurate target image analysis algorithm.

[0196] Specifically, the system inputs each liquid crystal imaging map adjustment sample in the liquid crystal imaging map adjustment sample set into the initial image analysis algorithm. The purpose of this step is to enable the algorithm to initially understand and identify the image features of these samples. Through the processing of the algorithm, the system obtains the semantic quantization vectors corresponding to each liquid crystal imaging map adjustment sample. These vectors are numerical representations of image features, which help the system more accurately analyze and compare the similarities and differences between different images.

[0197] Next, based on these semantic quantization vectors, the system determines the quality inspection status prediction results corresponding to each liquid crystal imaging map adjustment sample. This prediction result is a preliminary evaluation of the current image quality by the algorithm. However, this prediction result may not be completely accurate, so it needs to be compared with the actual quality inspection status.

[0198] To improve the accuracy of the algorithm, the system compares the quality inspection status prediction results corresponding to each liquid crystal imaging map adjustment sample with the actual quality inspection status certification results. By comparing the differences between the two, the system can discover where the algorithm's judgment is biased and accordingly adjust the algorithm weights of the initial image analysis algorithm. This adjustment process is to make the algorithm better adapt to the characteristics of the liquid crystal imaging map, thereby improving the accuracy of quality inspection.

[0199] After the above steps, the system finally obtains the optimized target image analysis algorithm. This algorithm has higher accuracy and reliability in identifying and analyzing liquid crystal imaging maps.

[0200] Further, after obtaining the target image analysis algorithm, the system also applies it to actual image processing tasks. Specifically, the system first obtains the liquid crystal imaging map to be analyzed from the optical image data to be analyzed. Then, these liquid crystal imaging maps to be analyzed are input into the target image analysis algorithm to obtain the corresponding imaging quality inspection views.

[0201] If the imaging quality inspection view represents that the liquid crystal imaging diagram to be analyzed is a quality inspection defect view, that is, the algorithm determines that there are quality problems in the image, the system will determine the corresponding optical image data to be analyzed as unqualified optical image data. This determination result provides an important basis for subsequent image screening, correction or re-acquisition, ensuring the controllability and consistency of image quality.

[0202] In summary, by using the liquid crystal imaging diagram to adjust the sample set to debug and optimize the initial image analysis algorithm, and applying the optimized algorithm to the actual image processing task, the optical imaging data analysis system realizes the precise control of the quality of the liquid crystal imaging diagram. This not only improves the accuracy of image analysis, but also provides a more reliable and efficient image processing solution for application scenarios such as liquid crystal vision charts.

[0203] Furthermore, Figure 2 FIG. shows a structural block diagram of the optical imaging data analysis system 300, including: a memory 310 for storing program instructions and data; a processor 320 for coupling with the memory 310 and executing the instructions in the memory 310 to implement the above method.

[0204] Furthermore, a computer storage medium is also provided, including instructions that, when executed on a processor, implement the above method.

[0205] In several embodiments provided in the embodiments of the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the drawings show the possible architectures, functions and operations of devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment or a part of code, and the module, program segment or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0206] In addition, in each embodiment of the present application, the various functional modules may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0207] When the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes. It should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or device. Without further limitations, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

[0208] The foregoing is only the preferred embodiment of this application and is not used to limit this application. For those skilled in the art, this application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims

1. An optical imaging data analysis method based on artificial intelligence, characterized in that, Applied to an optical imaging data analysis system, the method includes: Obtaining a liquid crystal imaging pattern example set corresponding to an optical image learning data set; the liquid crystal imaging pattern example set includes a first liquid crystal imaging pattern example and a second liquid crystal imaging pattern example; the first liquid crystal imaging pattern example carries a quality inspection pass annotation, and the second liquid crystal imaging pattern example carries a quality inspection defect annotation; Determining liquid crystal imaging wavelet descriptors corresponding to each liquid crystal imaging pattern example in the liquid crystal imaging pattern example set; Grouping according to a plurality of the liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern example set to obtain a plurality of wavelet description cluster sets; Determining a target wavelet description cluster set according to the liquid crystal imaging wavelet descriptors corresponding to each of the plurality of wavelet description cluster sets; Adjusting the annotation of the first liquid crystal imaging pattern example corresponding to the target wavelet description cluster set to the quality inspection defect annotation to obtain an adjusted liquid crystal imaging pattern example set; Debugging an initial image analysis algorithm according to the adjusted liquid crystal imaging pattern example set to obtain a target image analysis algorithm.

2. The method according to claim 1, wherein The grouping according to a plurality of the liquid crystal imaging wavelet descriptors corresponding to the liquid crystal imaging pattern example set to obtain a plurality of wavelet description cluster sets includes: determining a wavelet description common value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the liquid crystal imaging wavelet descriptors corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively; grouping a plurality of wavelet description common values corresponding to the liquid crystal imaging pattern example set to obtain the plurality of wavelet description cluster sets; The determining a target wavelet description cluster set according to the liquid crystal imaging wavelet descriptors corresponding to each of the plurality of wavelet description cluster sets includes: determining a target wavelet description cluster set according to the wavelet description common values corresponding to each of the plurality of wavelet description cluster sets.

3. The method according to claim 2, wherein The determining a target wavelet description cluster set according to the liquid crystal imaging wavelet descriptors corresponding to each of the plurality of wavelet description cluster sets includes: determining, as the target wavelet description cluster set, the wavelet description cluster set including an imaging defect wavelet descriptor among the plurality of wavelet description cluster sets; Wherein, the determining method of the imaging defect wavelet descriptor includes: Obtaining a past liquid crystal imaging atlas corresponding to a past optical image data set; the past liquid crystal imaging atlas includes a first past liquid crystal imaging image and a second past liquid crystal imaging image; Determining liquid crystal imaging wavelet descriptors corresponding to each past liquid crystal imaging image in the past liquid crystal imaging atlas; Grouping according to a plurality of the past liquid crystal imaging wavelet descriptors corresponding to the past liquid crystal imaging atlas to obtain a plurality of past wavelet description cluster sets; Determining the proportion of the second past liquid crystal imaging image corresponding to each past wavelet description cluster set; Determining, as a defect description cluster set, the past wavelet description cluster set in which the proportion of the second past liquid crystal imaging image is greater than a first set threshold; Determining the past liquid crystal imaging wavelet descriptors in the defect description cluster set as the imaging defect wavelet descriptors; Wherein, the first past liquid crystal imaging image and the second past liquid crystal imaging image represent different imaging conditions or qualities.

4. The method according to claim 3, characterized in that, Performing clustering on the several past liquid crystal imaging wavelet descriptors corresponding to the past liquid crystal imaging atlas to obtain several past wavelet description cluster sets, including: determining the past wavelet description commonality value between the first past liquid crystal imaging map and the second past liquid crystal imaging map according to the past liquid crystal imaging wavelet descriptors corresponding to the first past liquid crystal imaging map and the second past liquid crystal imaging map respectively; performing clustering according to the several past wavelet description commonality values corresponding to the past liquid crystal imaging atlas to obtain the several past wavelet description cluster sets; The method further includes: determining the sampling description commonality value in the defect description cluster set as the commonality metric threshold; the sampling description commonality value in the defect description cluster set is less than the first wavelet description commonality value; the first wavelet description commonality value is the wavelet description commonality value in the defect description cluster set other than the sampling description commonality value; Determining the target wavelet description cluster set according to the wavelet description commonality values corresponding to the several wavelet description cluster sets respectively, including: determining the target wavelet description commonality value in each wavelet description cluster set; the target wavelet description commonality value in any wavelet description cluster set is less than the second wavelet description commonality value in the any wavelet description cluster set; the second wavelet description commonality value in any wavelet description cluster set is the wavelet description commonality value in the any wavelet description cluster set other than the target wavelet description commonality value; determining the wavelet description cluster set with the target wavelet description commonality value not less than the commonality metric threshold as the target wavelet description cluster set.

5. The method according to claim 2, wherein The method further includes: determining the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively; determining the pixel description commonality value between the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example according to the image semantic blocks corresponding to the first liquid crystal imaging pattern example and the second liquid crystal imaging pattern example respectively; Performing clustering on the several wavelet description commonality values corresponding to the liquid crystal imaging pattern example set to obtain the several wavelet description cluster sets, including: performing clustering on the several wavelet description commonality values and the several pixel description commonality values corresponding to the liquid crystal imaging pattern example set to obtain the several wavelet description cluster sets.

6. The method according to claim 2, wherein The method further includes: constructing a first mapping rule corresponding to the image semantic block in the liquid crystal imaging pattern example; the first mapping rule includes adjusting the pixel features of the object label into a first linear vector, adjusting the pixel features of the table label into a second linear vector, and adjusting the pixel features of the curve label into a third linear vector; Determining the liquid crystal imaging wavelet descriptors corresponding to the respective liquid crystal imaging pattern examples in the liquid crystal imaging pattern example set, including: mapping the respective liquid crystal imaging pattern examples in the liquid crystal imaging pattern example set into first liquid crystal imaging wavelet descriptors according to the first mapping rule; determining the liquid crystal imaging wavelet descriptors corresponding to the respective liquid crystal imaging pattern examples according to the first liquid crystal imaging wavelet descriptors corresponding to the respective liquid crystal imaging pattern examples.

7. The method according to claim 6, wherein The method further includes: constructing a second mapping rule corresponding to the image semantic block; the second mapping rule is to construct a semantic feature relationship network of a target scale; wherein, the target scale corresponds to a set number of vertically distributed labels, and the set number of vertically distributed labels includes a plurality of first vertically distributed labels and a plurality of second vertically distributed labels; each first vertically distributed label corresponds to an imaging object, and the linear vector in each first vertically distributed label represents whether the imaging object corresponding to each first vertically distributed label exists in the image semantic block; each second vertically distributed label corresponds to a non-imaging object pixel feature; the non-imaging object pixel feature includes a linear vector and a curve feature; the linear vector in each second vertically distributed label represents whether the non-imaging object pixel feature corresponding to each second vertically distributed label exists in the image semantic block. Determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptors corresponding to the respective liquid crystal imaging pattern examples includes: mapping each of the liquid crystal imaging pattern examples into a second liquid crystal imaging wavelet descriptor according to the second mapping rule; and determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptors and the second liquid crystal imaging wavelet descriptors corresponding to the respective liquid crystal imaging pattern examples. Wherein, the method further includes: constructing a third mapping rule corresponding to the image semantic block; the third mapping rule includes dividing the image semantic block into two local image semantic blocks according to the target pixel feature in the image semantic block; mapping the two local image semantic blocks into local liquid crystal imaging wavelet descriptors respectively according to the first mapping rule; and determining the averaging calculation result of the two local liquid crystal imaging wavelet descriptors to obtain a liquid crystal imaging wavelet descriptor; determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptors and the second liquid crystal imaging wavelet descriptors corresponding to the respective liquid crystal imaging pattern examples includes: mapping each of the liquid crystal imaging pattern examples into a third liquid crystal imaging wavelet descriptor according to the third mapping rule; and determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptors, the second liquid crystal imaging wavelet descriptors, and the third liquid crystal imaging wavelet descriptors corresponding to the respective liquid crystal imaging pattern examples. Wherein, the method further includes: constructing a fourth mapping rule corresponding to the image semantic block; the fourth mapping rule includes dividing the image semantic block into two local image semantic blocks according to the target pixel features in the image semantic block; mapping the two local image semantic blocks into local liquid crystal imaging wavelet descriptors respectively according to the second mapping rule; determining the mean calculation result of the two local liquid crystal imaging wavelet descriptors to obtain a liquid crystal imaging wavelet descriptor; the determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptor, the second liquid crystal imaging wavelet descriptor, and the third liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example includes: mapping each liquid crystal imaging pattern example into a fourth liquid crystal imaging wavelet descriptor according to the fourth mapping rule; determining the liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example according to the first liquid crystal imaging wavelet descriptor, the second liquid crystal imaging wavelet descriptor, the third liquid crystal imaging wavelet descriptor, and the fourth liquid crystal imaging wavelet descriptor corresponding to each liquid crystal imaging pattern example.

8. The method according to claim 1, wherein The adjusting the initial image analysis algorithm according to the liquid crystal imaging map adjustment sample set to obtain a target image analysis algorithm includes: inputting each liquid crystal imaging map adjustment sample in the liquid crystal imaging map adjustment sample set into the initial image analysis algorithm to obtain a semantic quantization vector corresponding to each liquid crystal imaging map adjustment sample; determining a quality inspection status prediction result corresponding to each liquid crystal imaging map adjustment sample according to the semantic quantization vectors corresponding to each liquid crystal imaging map adjustment sample; adjusting the algorithm weight of the initial image analysis algorithm according to the difference between the quality inspection status prediction result corresponding to each liquid crystal imaging map adjustment sample and the quality inspection status certification result corresponding to each liquid crystal imaging map adjustment sample to obtain the target image analysis algorithm. The method further includes: obtaining a to-be-analyzed liquid crystal imaging map of the to-be-analyzed optical image data; inputting the to-be-analyzed liquid crystal imaging map into the target image analysis algorithm to obtain an imaging quality inspection view; if the imaging quality inspection view indicates that the to-be-analyzed liquid crystal imaging map is a quality inspection defect view, determining the to-be-analyzed optical image data as unqualified optical image data.

9. An optical imaging data analysis system, characterized in that, Including: a memory for storing program instructions and data; a processor for being coupled with the memory and executing the instructions in the memory to implement the method according to any one of claims 1-8.

10. A computer storage medium, characterized in that, including instructions which, when executed on the processor, implement the method according to any one of claims 1-8.

Images