Image recognition and processing system and method based on artificial intelligence

Abstract

The invention belongs to the technical field of image processing, and provides an image recognition and processing system and method based on artificial intelligence, and the system comprises a data collection module, a preprocessing module, a feature extraction module, an intelligent recognition module, a processing decision module, a user interaction interface, and a learning optimization module. According to the image recognition and processing system and method based on artificial intelligence, efficient collection, preprocessing, feature extraction, intelligent recognition, decision processing and user interaction of image data are achieved, and the system performance is continuously improved through the learning optimization module; the system can significantly improve image quality, accurately extract image features, realize high-precision identification, automatically execute or recommend corresponding image processing operation according to an identification result, display a processing result through a user interaction interface and receive a user instruction, realize flexible man-machine interaction, and improve the user experience. And it is ensured that the system can continuously adapt to new image environments and recognition requirements.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and in particular to an image recognition and processing system and method based on artificial intelligence. Background Art

[0002] In the current field of image processing, traditional image recognition and processing methods often rely on manually designed features and rules, which not only leads to low processing efficiency, but also makes it difficult to adapt to complex and changing image environments. With the rapid development of artificial intelligence technology, especially the widespread application of deep learning algorithms, new solutions have been provided for image recognition and processing.

[0003] However, existing AI-based image recognition and processing systems still have some shortcomings; for example, some systems lack effective denoising and enhancement methods in the image preprocessing stage, resulting in poor subsequent feature extraction and recognition effects.

[0004] To this end, those skilled in the art have proposed an image recognition and processing system and method based on artificial intelligence to solve the problems raised by the background technology. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides an image recognition and processing system and method based on artificial intelligence to solve the problems that the system in the prior art lacks effective denoising and enhancement means in the image preprocessing stage, resulting in poor subsequent feature extraction and recognition effects.

[0006] An image recognition and processing system based on artificial intelligence, comprising:

[0007] A data acquisition module, used for acquiring image data to be processed;

[0008] A preprocessing module, connected to the data acquisition module, is used to clean, denoise and convert the format of the acquired image data to improve the image quality;

[0009] Feature extraction module, built based on deep learning algorithm, is used to extract key feature information from preprocessed images;

[0010] Intelligent recognition module, which integrates a convolutional neural network model and is used to perform high-precision image recognition based on the extracted feature information, including but not limited to object recognition, face recognition, and scene recognition;

[0011] The processing decision module automatically performs or recommends corresponding image processing operations, including cropping, enhancement, restoration or classification, based on the output results of the intelligent recognition module;

[0012] User interaction interface, used to display processing results and receive user instructions to achieve human-computer interaction;

[0013] As well as the learning optimization module, it dynamically adjusts and optimizes the parameters of each module to improve system performance by continuously learning from user feedback and new image data.

[0014] Preferably, in the preprocessing module, a histogram equalization algorithm is used to clean, denoise and convert the format of the acquired image data to improve the image quality and to enhance the contrast of the image.

[0015] Preferably, the deep learning algorithm uses a convolutional neural network (CNN) algorithm to extract local features from images.

[0016] Preferably, the feature extraction module further includes an adaptive feature selection unit, which can dynamically adjust the feature extraction strategy according to the image content to improve the effectiveness and pertinence of the features.

[0017] Preferably, a convolutional neural network model is integrated to introduce a softmax function for the output layer of multi-classification problems.

[0018] Preferably, the intelligent recognition module adopts a multi-model fusion strategy, combining the advantages of different artificial intelligence models to improve recognition accuracy and robustness. The multi-model fusion strategy introduces a weighted average strategy to combine the prediction results of multiple models to improve recognition accuracy and robustness.

[0019] Preferably, the processing decision module also includes an automated workflow design function, allowing users to customize the image processing process according to specific needs and achieve one-click processing.

[0020] Preferably, in the user feedback learning algorithm, the user feedback adopts the gradient descent formula in the user feedback learning algorithm to update the model parameters.

[0021] A processor is configured to execute the above-mentioned artificial intelligence-based image recognition and processing system.

[0022] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned image recognition and processing system based on artificial intelligence.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] 1. The present invention cleans, denoises and converts the format of image data through a preprocessing module, and uses a histogram equalization algorithm to enhance the contrast of the image, thereby significantly improving the image quality and laying a solid foundation for subsequent feature extraction and recognition.

[0025] 2. The feature extraction module of the present invention is constructed based on a deep learning algorithm, which uses a convolutional neural network (CNN) algorithm to extract local features from the image, and dynamically adjusts the feature extraction strategy according to the image content through an adaptive feature selection unit to improve the effectiveness and pertinence of the features.

[0026] 3. The intelligent recognition module of the present invention integrates a convolutional neural network model and introduces a softmax function for the output layer of multi-classification problems. At the same time, a multi-model fusion strategy is adopted to combine the advantages of different artificial intelligence models to improve recognition accuracy and robustness.

[0027] 4. The user interaction interface of the present invention is used to display processing results and receive user instructions to achieve human-computer interaction. At the same time, the processing decision module also includes an automated workflow design function, allowing users to customize the image processing process according to specific needs and achieve one-click processing.

[0028] 5. The learning optimization module of the present invention continuously learns user feedback and new image data, dynamically adjusts and optimizes the parameters of each module, improves system performance, and ensures that the system can continuously adapt to new image environments and recognition requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a framework diagram of the image recognition and processing system based on artificial intelligence of the present invention;

[0030] Figure 2 The figure is a flow chart of the image recognition and processing method based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0031] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0032] Embodiment: The present invention provides an image recognition and processing system based on artificial intelligence, such as Figure 1 As shown, it includes a data acquisition module, a preprocessing module, a feature extraction module, an intelligent recognition module, a processing decision module, a user interaction interface and a learning optimization module. The data acquisition module, the preprocessing module, the feature extraction module, the intelligent recognition module and the processing decision module are electrically connected in sequence:

[0033] A data acquisition module, used for acquiring image data to be processed;

[0034] A preprocessing module, connected to the data acquisition module, is used to clean, denoise and convert the format of the acquired image data to improve the image quality;

[0035] Feature extraction module, built based on deep learning algorithm, is used to extract key feature information from preprocessed images;

[0036] Intelligent recognition module, which integrates a convolutional neural network model and is used to perform high-precision image recognition based on the extracted feature information, including but not limited to object recognition, face recognition, and scene recognition;

[0037] The processing decision module automatically performs or recommends corresponding image processing operations, including cropping, enhancement, restoration or classification, based on the output results of the intelligent recognition module;

[0038] User interaction interface, used to display processing results and receive user instructions to achieve human-computer interaction;

[0039] As well as the learning optimization module, it dynamically adjusts and optimizes the parameters of each module to improve system performance by continuously learning from user feedback and new image data.

[0040] From the above, it can be seen that through an artificial intelligence-based image recognition and processing system and method, efficient collection, preprocessing, feature extraction, intelligent recognition, processing decisions and user interaction of image data are realized, and the system performance is continuously improved through a learning optimization module; the system can significantly improve image quality, accurately extract image features, achieve high-precision recognition, and automatically execute or recommend corresponding image processing operations based on the recognition results. At the same time, it displays the processing results and receives user instructions through the user interaction interface, realizing flexible human-computer interaction, and ensuring that the system can continuously adapt to new image environments and recognition requirements.

[0041] Furthermore, in the preprocessing module, the acquired image data is cleaned, denoised and format converted to improve the image quality. A histogram equalization algorithm is used to enhance the contrast of the image. The formula of the histogram equalization algorithm is as follows:

[0042]

[0043] Where r represents the gray level in the input image, s represents the gray level in the output image, n is the total number of pixels in the image, and n j is the number of pixels with gray level j, and L is the total number of gray levels.

[0044] From the above, we can see that in the preprocessing module, the image data is cleaned, denoised and format converted by using the histogram equalization algorithm, and the image contrast is enhanced by this algorithm. The beneficial effect is that it can significantly improve the image quality and make the grayscale distribution of the image more uniform, thereby enhancing the visual effect of the image, laying a solid foundation for subsequent feature extraction and recognition, and improving the accuracy and efficiency of the entire image recognition and processing system.

[0045] Furthermore, the deep learning algorithm uses a convolutional neural network (CNN) algorithm to extract local features from images. The convolution operation in the convolutional neural network algorithm is:

[0046]

[0047] Among them, I is the input image, K is the convolution kernel, O is the output feature map, (i, j) is the position in the output feature map, and (m, n) is the size of the convolution kernel.

[0048] From the above, we can see that the beneficial effect of extracting local features from images through convolution operations is that it can efficiently capture key information in the image, such as edges, textures, etc., which is crucial for subsequent image recognition and processing; at the same time, convolutional neural networks have powerful feature representation capabilities and can automatically learn and extract hierarchical features, thus avoiding the tedious process of manually designing features in traditional methods and improving the accuracy and efficiency of image recognition.

[0049] Furthermore, the feature extraction module further includes an adaptive feature selection unit, which can dynamically adjust the feature extraction strategy according to the image content to improve the effectiveness and pertinence of the features.

[0050] From the above, it can be seen that in the feature extraction module, it is further included that an adaptive feature selection unit can dynamically adjust the feature extraction strategy according to the image content, which can significantly improve the effectiveness and pertinence of the features; by adaptively adjusting according to the complexity and characteristics of the image content, the feature extraction module can more accurately extract key features that are helpful for subsequent recognition and processing, thereby improving the performance and accuracy of the entire image recognition and processing system.

[0051] Furthermore, the softmax function is introduced into the integrated convolutional neural network model for the output layer of multi-classification problems. The formula of the softmax function is as follows:

[0052]

[0053] Among them, z i is the i-th element of the input vector, K is the number of categories, σ(z i ) is the probability of the i-th category in the output vector.

[0054] From the above, we can see that in the intelligent recognition module, a convolutional neural network model is integrated and the softmax function is introduced for the output layer of the multi-classification problem, which can achieve accurate classification of image recognition results; the softmax function can convert the output of the convolutional neural network model into a probability distribution, thereby clearly representing the possibility of each category, so that the system can accurately judge the category of the image based on the maximum probability value; this design not only improves the accuracy of image recognition, but also enhances the robustness and practicality of the system.

[0055] Furthermore, the intelligent recognition module adopts a multi-model fusion strategy, combining the advantages of different artificial intelligence models to improve recognition accuracy and robustness. The multi-model fusion strategy introduces a weighted average strategy to combine the prediction results of multiple models to improve recognition accuracy and robustness. The formula of the weighted average strategy is as follows:

[0056]

[0057] Where N is the number of models, w k is the weight of the kth model, P k is the prediction result of the kth model.

[0058] From the above, we can see that by adopting a multi-model fusion strategy and introducing a weighted average strategy to combine the prediction results of multiple models, the accuracy and robustness of image recognition can be significantly improved; by combining the advantages of different artificial intelligence models, the system can understand the image content more comprehensively and reduce the misjudgment and bias that may be caused by a single model; at the same time, the weighted average strategy can reasonably allocate weights according to the performance of each model, making the final prediction results more accurate and reliable; this design not only improves the performance of image recognition, but also enhances the stability and generalization ability of the system.

[0059] Furthermore, the processing decision module also includes an automated workflow design function, allowing users to customize the image processing process according to specific needs and achieve one-click processing.

[0060] As can be seen from the above, the processing decision module includes an automated workflow design function, which allows users to customize the image processing process according to specific needs and achieve one-click processing. This design greatly improves the flexibility and user-friendliness of the system; users can easily design and save personalized image processing processes according to actual application scenarios and needs, thereby simplifying the operation steps and improving work efficiency; at the same time, the one-click processing function makes the image processing process more convenient and efficient, meeting the user's needs for fast and accurate image processing.

[0061] Furthermore, in the user feedback learning algorithm, the user feedback adopts the gradient descent formula in the user feedback learning algorithm to update the model parameters, and the formula is as follows:

[0062] θ new =θ old -η·▽ θ L(θ);

[0063] Among them, θ represents the model parameters, η represents the learning rate, L(θ) represents the loss function, ▽ θ L(θ) represents the gradient of the loss function with respect to the model parameters.

[0064] From the above, we can see that by using the gradient descent formula to update the model parameters according to user feedback, the system performance can be continuously optimized and improved; by calculating the gradient of the loss function with respect to the model parameters and gradually adjusting the model parameters in the opposite direction of the gradient, the system can gradually approach the optimal solution, thereby improving the accuracy and efficiency of image recognition; at the same time, this learning mechanism based on user feedback enables the system to continuously adapt to new image environments and recognition requirements, enhancing the robustness and practicality of the system.

[0065] An image recognition and processing method based on artificial intelligence, such as Figure 2 As shown, the above-mentioned image recognition and processing system based on artificial intelligence includes the following steps:

[0066] S1, acquiring image data through a data acquisition module;

[0067] S2, preprocessing the image data using a preprocessing module;

[0068] S3, extracting key features of the image through a feature extraction module;

[0069] S4, applying an intelligent recognition module to recognize the image;

[0070] S5. Execute or recommend image processing operations through a processing decision module according to the recognition result;

[0071] S6. Display the processing results through the user interaction interface and perform learning optimization based on user feedback.

[0072] Working principle: The system obtains the image data to be processed through the data acquisition module, and then the preprocessing module cleans, denoises and converts the image format to improve the image quality; the feature extraction module uses deep learning algorithms, especially convolutional neural networks (CNN), to extract key features from the preprocessed images; the intelligent recognition module uses the extracted feature information and combines multi-model fusion strategies to perform high-precision image recognition; the processing decision module automatically executes or recommends corresponding image processing operations based on the recognition results, and provides automated workflow design functions to meet user-specific needs; the user interaction interface displays the processing results and receives user instructions, while the learning optimization module dynamically adjusts and optimizes the parameters of each module by continuously learning user feedback and new image data to continuously improve system performance.

[0073] Furthermore, the effects of the artificial intelligence-based image recognition and processing system of this embodiment and the existing artificial intelligence-based image recognition and processing system (comparative example) are compared to obtain the following table:

[0074]

[0075]

[0076] It can be seen from the above table that the artificial intelligence-based image recognition and processing system of this embodiment is superior to the comparison example in terms of image preprocessing, feature extraction, intelligent recognition, processing decision-making, user interaction, learning optimization and overall performance. The system is suitable for large-scale promotion and application.

[0077] The embodiment of the present application provides an electronic device, which is applicable to the above-mentioned artificial intelligence-based image recognition and processing system, including:

[0078] Memory, used to protect computer programs and data;

[0079] Processor, used to run system programs.

[0080] An embodiment of the present application provides a computer storage medium, which is suitable for the above-mentioned artificial intelligence-based image recognition and processing system, and performs hierarchical confidentiality management on the above-mentioned system and data in accordance with confidentiality management requirements.

[0081] Those skilled in the art will appreciate that the embodiments of the present application may be provided as a system or a computer program product. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0082] The present application is described with reference to the flowcharts and / or block diagrams of the devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0083] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0084] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0085] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0086] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0087] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0088] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, commodity or device including the elements.

[0089] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. An image recognition and processing system based on artificial intelligence, characterized in that: include: A data acquisition module, used for acquiring image data to be processed; A preprocessing module, connected to the data acquisition module, for cleaning, denoising and format conversion of acquired image data; Feature extraction module, built based on deep learning algorithm, is used to extract key feature information from preprocessed images; Intelligent recognition module, which integrates a convolutional neural network model and is used to perform high-precision image recognition based on the extracted feature information; The processing decision module automatically executes or recommends corresponding image processing operations based on the output results of the intelligent recognition module; User interaction interface, used to display processing results and receive user instructions; As well as the learning optimization module, it dynamically adjusts and optimizes the parameters of each module by continuously learning from user feedback and new image data.

2. The image recognition and processing system based on artificial intelligence as claimed in claim 1, characterized in that: In the preprocessing module, the acquired image data is cleaned, denoised and format converted to enhance the contrast of the image.

3. The image recognition and processing system based on artificial intelligence as claimed in claim 1, characterized in that: The deep learning algorithm uses a convolutional neural network algorithm to extract local features from images.

4. The image recognition and processing system based on artificial intelligence as claimed in claim 1, characterized in that: The feature extraction module further includes an adaptive feature selection unit capable of dynamically adjusting the feature extraction strategy according to the image content.

5. The image recognition and processing system based on artificial intelligence as claimed in claim 1, characterized in that: The ensemble introduces a softmax function into the convolutional neural network model, which is used in the output layer of the multi-classification problem.

6. The image recognition and processing system based on artificial intelligence as claimed in claim 1, characterized in that: The intelligent recognition module adopts a multi-model fusion strategy, combining the advantages of different artificial intelligence models. The multi-model fusion strategy introduces a weighted average strategy to combine the prediction results of multiple models.

7. The image recognition and processing system based on artificial intelligence as claimed in claim 1, characterized in that: The processing decision module also includes an automated workflow design function, allowing users to customize the image processing process according to specific needs.

8. The image recognition and processing system based on artificial intelligence as claimed in claim 1, characterized in that: In the user feedback learning algorithm, the user feedback adopts the gradient descent formula in the user feedback learning algorithm to update the model parameters.

9. An image recognition and processing method based on artificial intelligence, characterized in that: An artificial intelligence-based image recognition and processing system according to any one of claims 1 to 8, comprising the following steps: S1, acquiring image data through a data acquisition module; S2, preprocessing the image data using a preprocessing module; S3, extracting key features of the image through a feature extraction module; S4, applying an intelligent recognition module to recognize the image; S5. Execute or recommend image processing operations through a processing decision module according to the recognition result; S6. Display the processing results through the user interaction interface and perform learning optimization based on user feedback.

Images