A Quality Control Method for Agarwood Fermentation Production Based on Image Recognition Technology

Abstract

This application relates to a quality control method for agarwood koji production based on image recognition technology. This invention utilizes big data technology to train and learn the texture features of agarwood koji slice images, constructing a quality inspection and identification model, which is then applied to identify the quality grade of the agarwood koji slice images. It can use an AI model to identify the texture features of agarwood koji slice images and output the corresponding quality grade. By using AI technology for image feature recognition, the model outputs the corresponding agarwood koji processing quality grade. Therefore, it can combine the model to perform image recognition and fingerprint spectrum identification on massive amounts of agarwood koji slice images, greatly improving the efficiency and accuracy of agarwood koji identification. Adopting this solution can lower the entry threshold and requirements for identification, enable large-scale quality inspection, and improve the processing quality standards for agarwood koji before it leaves the warehouse.

Description

Technical Field

[0001] This disclosure relates to the field of image recognition technology, and in particular to a method, system and electronic device for quality control of agarwood production based on image recognition technology. Background Technology

[0002] Agarwood broth has the following main effects:

[0003] Dispelling wind and cold: Agarwood contains a variety of warm medicinal materials that can warm the body's yang energy and promote blood circulation. It has a good effect on cold-related diseases such as colds and arthritis.

[0004] Calming and soothing effects: Its volatile oil components can calm nerves, soothe emotions, help treat symptoms such as insomnia, anxiety, and depression, and help restore a calm state.

[0005] Anti-inflammatory and antibacterial: Quercetin, quercetin and other components in agarwood broth have antibacterial and anti-inflammatory effects, which can effectively inhibit the growth of pathogenic microorganisms and reduce inflammatory reactions such as oral ulcers, sores and swelling.

[0006] Improves gastrointestinal function: It can enhance gastric juice secretion, promote digestion, improve bloating and constipation, regulate intestinal peristalsis, and relieve gastrointestinal discomfort.

[0007] The production and processing quality of agarwood koji has a significant impact on its medicinal efficacy. Therefore, quality control in the production and processing of agarwood koji is particularly important. Specifically: the production of agarwood koji requires the selection of high-quality agarwood and other medicinal materials as raw materials to ensure the purity and efficacy of the raw materials; it must be processed strictly according to traditional methods, including grinding, mixing, paste making, molding, and drying of the medicinal materials, with each step requiring precise control to ensure the quality of the agarwood koji; and modern analytical techniques such as high-performance liquid chromatography are used to test the quality of the agarwood koji, and by comparing fingerprint spectra, its quality is determined to ensure product consistency and stability.

[0008] In the process of quality testing of agarwood koji, the traditional quality inspection method requires manual identification of the fingerprint spectrum of agarwood koji (usually slices), which has the following technical drawbacks:

[0009] First, manual fingerprint identification requires extensive industry experience and a high level of expertise in fingerprint identification, making it technically challenging and demanding on the entry-level skills of the personnel involved.

[0010] Secondly, when faced with fingerprint analysis of a massive number of slices, manual inspection can only be done by random sampling. This method is not only inefficient, but also cannot achieve large-scale identification and inspection. Therefore, the production quality of agarwood koji cannot be well controlled. Summary of the Invention

[0011] To address the aforementioned issues, this application proposes a method, system, and electronic device for quality control in agarwood production based on image recognition technology.

[0012] This application proposes a method for quality control in the production of agarwood koji based on image recognition technology, comprising the following steps:

[0013] S1. Collect images of agarwood slices;

[0014] S2. Input the agarwood slice image into a preset quality inspection and identification model, and the quality inspection and identification model identifies the texture features of the agarwood slice image and outputs the corresponding quality level.

[0015] S3. Determine whether the current quality grade of the agarwood chips meets the standard:

[0016] If the standard is met, the next quality inspection of agarwood chips will proceed.

[0017] Conversely, an alarm signal will be issued.

[0018] As an optional implementation of this application, optionally, S1, acquiring images of agarwood slices includes:

[0019] A batch of agarwood slice images were acquired and preprocessed.

[0020] The agarwood slice image is sliced ​​to obtain image slices corresponding to several agarwood slices;

[0021] Check the positional correspondence between the image slice and the corresponding agarwood slice, and record the positional information of the image slice.

[0022] As an optional implementation of this application, the method for generating the quality inspection identification model may include:

[0023] Collect and preprocess several images of agarwood slices;

[0024] The process involves iterating through each of the agarwood slice images and using a CNN to extract texture features from the agarwood slice images, including gloss, texture spatial distribution, and texture morphology.

[0025] The texture features are labeled, and the labeling information includes a quality level determined based on the glossiness, texture spatial distribution, and texture morphology;

[0026] Based on the labeled texture features, a feature set is constructed;

[0027] The feature set is divided into a training set and a validation set according to a preset ratio;

[0028] The training set is input into a preset CNN model for feature training and learning to construct the quality inspection identification model.

[0029] The recognition performance of the quality inspection identification model was verified using the validation set.

[0030] If the verification is successful, the quality inspection and identification model will be deployed on the server and used for texture feature quality identification of agarwood slice images;

[0031] If the verification fails, repeat the above steps to rebuild the quality inspection identification model.

[0032] As an optional implementation of this application, the annotation information may optionally include:

[0033] The unit price is determined based on the gloss, texture spatial distribution, and texture morphology.

[0034] As an optional implementation of this application, optionally, S2, inputting the agarwood slice image into a preset quality inspection and identification model, wherein the quality inspection and identification model identifies the texture features of the agarwood slice image and outputs the corresponding quality level, including:

[0035] Input the sliced ​​image of the agarwood into the quality inspection and identification model;

[0036] The quality inspection identification model identifies the texture features in the agarwood slice image and predicts the quality level corresponding to the texture features.

[0037] The quality grade is bound to the corresponding agarwood slice image and written into the corresponding image table to obtain the agarwood quality identification table.

[0038] As an optional implementation of this application, optionally, S2, inputting the agarwood slice image into a preset quality inspection and identification model, wherein the quality inspection and identification model identifies the texture features of the agarwood slice image and outputs the corresponding quality level, including:

[0039] Input the sliced ​​image of the agarwood into the quality inspection and identification model;

[0040] The quality inspection identification model identifies the texture features in the agarwood slice image and predicts and outputs the unit price corresponding to the texture features.

[0041] The unit price is bound to the corresponding agarwood slice image and written into the corresponding image table to obtain the agarwood unit price prediction table.

[0042] In another aspect, this application proposes a quality control system for agarwood koji production based on image recognition technology, comprising:

[0043] The image acquisition module is used to acquire images of agarwood slices and input them into the agarwood quality inspection module;

[0044] The agarwood spore quality inspection module is used to input the agarwood spore slice image into a preset quality inspection recognition model, and the quality inspection recognition model identifies the texture features of the agarwood spore slice image and outputs the corresponding quality level.

[0045] The quality control module is used to determine whether the current agarwood chips meet the quality standards.

[0046] If the standard is met, the next quality inspection of agarwood chips will proceed.

[0047] Conversely, an alarm signal will be issued;

[0048] An alarm module is used to respond to the alarm signal;

[0049] The image acquisition module, agarwood quality inspection module, quality control module, and alarm module are connected in sequence.

[0050] In another aspect, this application also proposes a legal electronic device, comprising:

[0051] processor;

[0052] Memory used to store processor-executable instructions;

[0053] The processor is configured to implement the agarwood production quality control method based on image recognition technology when executing the executable instructions.

[0054] Technical effects of the present invention:

[0055] This invention utilizes big data technology to train and learn the texture features of agarwood slice images, constructing a quality inspection and identification model to identify the quality grade of agarwood slice images. It can use an AI model to identify the texture features of agarwood slice images and output the corresponding quality grade. By using AI technology for image feature recognition, the model outputs the corresponding processing quality grade of agarwood. Therefore, it can combine the model to perform image recognition and fingerprint identification on massive amounts of agarwood slice images, greatly improving the efficiency and accuracy of agarwood identification. Adopting this solution lowers the entry barrier and requirements for identification, enables large-scale quality inspection, and improves the processing quality standards for agarwood before it leaves the warehouse.

[0056] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0057] The accompanying drawings, which are included in and form part of this specification, illustrate exemplary embodiments, features, and aspects of this disclosure together with the specification and serve to explain the principles of this disclosure.

[0058] Figure 1 The diagram shown is a schematic representation of the implementation process of the present invention;

[0059] Figure 2 The diagram shown is a flowchart of the training process for the quality inspection identification model of the present invention.

[0060] Figure 3 The diagram shown is a schematic representation of the system composition of the present invention.

[0061] Figure 4 The diagram shown is an application schematic of the electronic device of the present invention. Detailed Implementation

[0062] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0063] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0064] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0065] Example 1

[0066] like Figure 1 As shown, this application proposes a method for quality control in the production of agarwood koji based on image recognition technology, comprising the following steps:

[0067] S1. Collect images of agarwood slices;

[0068] S2. Input the agarwood slice image into a preset quality inspection and identification model, and the quality inspection and identification model identifies the texture features of the agarwood slice image and outputs the corresponding quality level.

[0069] S3. Determine whether the current quality grade of the agarwood chips meets the standard:

[0070] If the standard is met, the next quality inspection of agarwood chips will proceed.

[0071] Conversely, an alarm signal will be issued.

[0072] This invention utilizes big data technology to train and learn the texture features of agarwood slice images, constructing a quality inspection and identification model to identify the quality grade of agarwood slice images. It can use an AI model to identify the texture features of agarwood slice images and output the corresponding quality grade. By using AI technology for image feature recognition, the model outputs the corresponding agarwood processing quality grade. Therefore, it can combine the model to perform image recognition and fingerprint identification on massive amounts of agarwood slice images, greatly improving the efficiency and accuracy of agarwood identification.

[0073] The implementation principle of the present invention will be described in detail below.

[0074] As an optional implementation of this application, optionally, S1, acquiring images of agarwood slices includes:

[0075] A batch of agarwood slice images were acquired and preprocessed.

[0076] The agarwood slice image is sliced ​​to obtain image slices corresponding to several agarwood slices;

[0077] Check the positional correspondence between the image slice and the corresponding agarwood slice, and record the positional information of the image slice.

[0078] The image acquisition module for collecting images of agarwood slices can use industrial cameras or similar devices to capture images. It can batch acquire image data from several agarwood slices (one acquisition, one image containing images of several slices) and upload it to the backend server.

[0079] In the background, corresponding image slices are generated to produce individual slice images of the corresponding agarwood stalk. Subsequently, each slice is traversed and imported into the model for detection.

[0080] The specific steps for slicing an image to obtain several image slices can be found below:

[0081] 1. Prepare the image

[0082] Loading Images: Use image processing software (such as Python's PIL / Pillow library, OpenCV library, or professional image processing software such as Photoshop or GIMP) to load the original image to be sliced.

[0083] Confirm image format: Ensure the image format is suitable for slicing. Common formats include JPEG, PNG, and TIFF.

[0084] 2. Determine the slicing parameters

[0085] Slice size: Determine the size of each slice (such as width and height) according to the requirements. It can be a fixed size or a ratio relative to the original image.

[0086] Number of slices: Calculate or determine the number of slices that need to be generated, which is usually based on the slice size and the dimensions of the original image.

[0087] Overlap (optional): If needed, you can set the overlap area between slices to ensure that the slices can be smoothly stitched or merged in subsequent processing.

[0088] 3. Perform the slicing operation

[0089] Writing code or using tools:

[0090] In programming environments (such as Python), loops and image processing libraries can be used to iterate over images and generate slices.

[0091] In image processing software, batch processing or scripting functions can be used to automate the slicing process.

[0092] Slice saving: Save each slice as a separate file, usually in a designated folder, for later processing.

[0093] 4. Verify the slice results

[0094] Check the slices: Examine each of the generated slices to ensure that they correctly reflect the contents of the original image and that there are no missing or duplicate parts.

[0095] Adjust parameters (if needed): If the slicing results do not meet expectations, you can return to step 2 to adjust the slicing parameters and re-execute the slicing operation.

[0096] 5. Follow-up processing

[0097] Slicing: Further processing of the generated slices, such as compression, format conversion, and adding watermarks.

[0098] Slice stitching: If needed, the slices can be re-stitched into the original image or a new image layout can be created in subsequent steps. That is, after the model outputs the quality level, the quality level is labeled on the corresponding slice image, and then the slices are stitched together into a single image in the original order. This allows for batch display of the quality levels of each slice on a single image, facilitating management and statistics.

[0099] The identification and labeling of subsequent unit prices can also be done in the same way as described above, resulting in an image labeled with the unit price of each slice, which makes it easier to calculate the unit price of each slice.

[0100] like Figure 2 As shown, as an optional embodiment of this application, the method for generating the quality inspection identification model may include:

[0101] Collect and preprocess several images of agarwood slices;

[0102] The process involves iterating through each of the agarwood slice images and using a CNN to extract texture features from the agarwood slice images, including gloss, texture spatial distribution, and texture morphology.

[0103] The texture features are labeled, and the labeling information includes a quality level determined based on the glossiness, texture spatial distribution, and texture morphology;

[0104] Based on the labeled texture features, a feature set is constructed;

[0105] The feature set is divided into a training set and a validation set according to a preset ratio;

[0106] The training set is input into a preset CNN model for feature training and learning to construct the quality inspection identification model.

[0107] The recognition performance of the quality inspection identification model was verified using the validation set.

[0108] If the verification is successful, the quality inspection and identification model will be deployed on the server and used for texture feature quality identification of agarwood slice images;

[0109] If the verification fails, repeat the above steps to rebuild the quality inspection identification model.

[0110] Convolutional neural networks (CNNs) can perform better image feature recognition and extract image features. For information on the network structure, model training, and application principles of CNNs, please refer to existing technical descriptions of CNNs.

[0111] This invention allows for the collection and preprocessing of several agarwood slice images in the initial stage. Preprocessing can include cleaning and filtering operations. Images with uneven gloss or texture spatial distribution, or low gloss, can be removed. Subsequently, a convolutional neural network (CNN) can be used to extract texture features from the agarwood slice images. These extracted texture features include color, gloss, texture spatial distribution, and texture morphology. Annotation tools can also be used to calculate and label features such as texture size and spacing between textures. After feature extraction, the features are labeled, allowing administrators to comprehensively evaluate the quality level of the current slice based on the extracted texture features and label the corresponding quality level according to industry standards.

[0112] When labeling quality levels, the corresponding features can be labeled according to industry standards and quality inspection conditions. After labeling, a feature set consisting of several texture features can be generated. This set can be divided into a training set and a validation set according to a preset ratio (e.g., 8:2). A CNN model is then used to train and learn the texture features in the training set, thereby constructing a quality inspection recognition model. After the model is validated, it can be deployed in the backend to perform quality recognition on agarwood slice images in subsequent processing, identifying the corresponding quality level and predicting the output.

[0113] The general steps for building a CNN (Convolutional Neural Network) model include the following key parts:

[0114] Data preparation and preprocessing:

[0115] Data collection: Collect sufficient training and validation / test data from reliable sources.

[0116] Data preprocessing: Normalize, crop, scale, rotate, flip and other preprocessing operations are performed on image data to unify the data format and enhance the generalization ability of the model.

[0117] Data augmentation (optional): Increase the diversity of training data through random transformations, such as random cropping, random brightness adjustment, etc.

[0118] Data partitioning: Divide the dataset into training, validation, and test sets (if the amount of data is large enough).

[0119] Model definition:

[0120] Choose a framework: Select a suitable deep learning framework, such as TensorFlow, PyTorch, etc.

[0121] Constructing the network structure: Define the hierarchical structure of the CNN, including the input layer, convolutional layer, activation layer (such as ReLU), pooling layer (such as max pooling), fully connected layer, output layer, etc.

[0122] Configure parameters: Set parameters for each layer, such as kernel size, stride, padding method, activation function type, pooling window size, number of neurons in fully connected layers, etc.

[0123] Loss Functions and Optimizers:

[0124] Choosing a loss function: Select an appropriate loss function based on the task type (such as classification or regression), such as cross-entropy loss or mean squared error.

[0125] Select optimizer: Choose an optimization algorithm, such as SGD, Adam, RMSprop, etc., and set hyperparameters such as learning rate and momentum.

[0126] Model training:

[0127] Data loading: Use a data loader (such as DataLoader) to load the training data into memory in batches.

[0128] Forward propagation: Calculates the model's predictions on the current batch of data.

[0129] Calculate the loss: Use a loss function to calculate the difference between the predicted value and the actual value.

[0130] Backpropagation: Calculate the gradient based on the loss value and update the model parameters through the optimizer.

[0131] Iterative training: Repeat the above steps until the predetermined number of training rounds is reached or other stopping conditions are met.

[0132] Monitor the training process: Record metrics such as loss value and accuracy during training, and use the validation set to evaluate model performance.

[0133] Model validation and evaluation:

[0134] Model validation: Evaluate the model's performance on the validation set to check for overfitting or underfitting. For example, the F1 score is widely used to evaluate the performance of segmentation models, especially for tasks such as tumor detection. The F1 score can comprehensively consider accuracy and recall, helping doctors to understand the model's performance more holistically. Validation can be completed by the administrator.

[0135] Adjust hyperparameters: Adjust hyperparameters such as model structure, learning rate, and batch size based on the validation results, and retrain the model.

[0136] Test Model (Optional): Evaluate the final performance of the model on an independent test set to obtain unbiased model evaluation results.

[0137] Model deployment and optimization (optional):

[0138] Model export: Export the trained model to a deployable format, such as TensorFlow SavedModel, PyTorch model file, etc.

[0139] Model optimization: Perform optimization operations such as quantization and pruning on the model to reduce model size and inference time.

[0140] Deployment Model: Deploy the model to the target platform (such as server, mobile device, embedded device, etc.) and put it into practical use.

[0141] The above are the general steps for building a CNN model. The specific implementation may vary depending on the task requirements, data characteristics, and hardware conditions.

[0142] As an optional implementation of this application, optionally, S2, inputting the agarwood slice image into a preset quality inspection and identification model, wherein the quality inspection and identification model identifies the texture features of the agarwood slice image and outputs the corresponding quality level, including:

[0143] Input the sliced ​​image of the agarwood into the quality inspection and identification model;

[0144] The quality inspection identification model identifies the texture features in the agarwood slice image and predicts the quality level corresponding to the texture features.

[0145] The quality grade is bound to the corresponding agarwood slice image and written into the corresponding image table to obtain the agarwood quality identification table.

[0146] In the process of assessing the quality of agarwood koji processing, images of agarwood koji slices can be collected and uploaded to the backend system. After preprocessing the slices, each slice is sequentially input into the quality inspection and identification model. The model identifies the image texture features of each agarwood koji slice and predicts and outputs the corresponding quality grade.

[0147] Subsequently, the quality level output by the model can be bound to each slice, or the quality level can be labeled on the corresponding agarwood slice image, and each slice can be written into the corresponding image table to generate a batch of agarwood quality assessment tables. The assessment table can be traversed and browsed to obtain the quality assessment results of each slice, which is convenient for quality statistics. The sequence number and quality level label of the corresponding image slice can be labeled and bound according to its position or preset arrangement information, etc.

[0148] If a slice fails to meet quality standards during the quality inspection process, an alarm signal can be generated in the background and sent to the quality inspection terminal. This terminal can be a PDA or similar device, prompting the administrator to remove the substandard agarwood slice. This allows for timely quality monitoring and removal of unqualified agarwood slices.

[0149] The removal of substandard agarwood slices can be accomplished by a robotic arm. Specifically, the backend can generate the robotic arm's trajectory based on the identified location of the substandard slices, control the robotic arm to move to the location of the substandard slices, grab them, and remove them. The corresponding robotic arm control software (installed according to the configured device) can be deployed in the backend. The generation and control of the robotic arm's trajectory can refer to the motion principles of existing robots; this embodiment is not limited to these principles.

[0150] As an optional implementation of this application, the annotation information may optionally include:

[0151] The unit price is determined based on the gloss, texture spatial distribution, and texture morphology.

[0152] As an optional implementation of this application, optionally, S2, inputting the agarwood slice image into a preset quality inspection and identification model, wherein the quality inspection and identification model identifies the texture features of the agarwood slice image and outputs the corresponding quality level, including:

[0153] Input the sliced ​​image of the agarwood into the quality inspection and identification model;

[0154] The quality inspection identification model identifies the texture features in the agarwood slice image and predicts and outputs the unit price corresponding to the texture features.

[0155] The unit price is bound to the corresponding agarwood slice image and written into the corresponding image table to obtain the agarwood unit price prediction table.

[0156] In addition to the aforementioned quality level prediction output, this invention also allows administrators to comprehensively evaluate and label the value (i.e., unit price) of corresponding slices based on the texture features of the identified slice images during feature annotation. The unit price of various slices can be labeled separately based on the differences in their texture features. This enables the model to predict and output the unit price of the corresponding slice after recognizing its texture features.

[0157] Based on the aforementioned method of recording quality grades, the value (unit price) of each slice can be predicted in batches. Then, the unit price of each slice is linked to its corresponding image and entered into a table, resulting in a predicted unit price table for each agarwood slice in this batch. This facilitates subsequent statistical analysis and evaluation of the value of the processed agarwood slices by administrators. Therefore, it allows enterprise users to simultaneously assess the quality of the slices and estimate their value.

[0158] Therefore, this invention utilizes big data technology to train and learn the texture features of agarwood slice images, constructing a quality inspection and identification model to identify the quality grade of agarwood slice images. It can use an AI model to identify the texture features of agarwood slice images and output the corresponding quality grade, employing AI technology for image feature recognition to allow the model to output the corresponding agarwood processing quality grade. Therefore, it can combine the model to perform image recognition and fingerprint spectrum identification on massive amounts of agarwood slice images, greatly improving the efficiency and accuracy of agarwood identification. Adopting this solution lowers the entry barrier and requirements for identification, enables large-scale quality inspection, and improves the processing quality standards for agarwood before it leaves the warehouse.

[0159] It should be noted that although CNN has been used as an example in the above description, those skilled in the art will understand that this disclosure is not limited thereto. In fact, users can flexibly set the training model according to the actual application scenario, as long as the technical functions of this application can be achieved by following the above techniques.

[0160] Obviously, those skilled in the art should understand that implementing all or part of the processes in the above embodiments can be accomplished by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the control embodiments described above. Those skilled in the art will understand that implementing all or part of the processes in the above embodiments can be accomplished by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the control embodiments described above. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0161] Example 2

[0162] like Figure 3 As shown, based on the implementation principle of Embodiment 1, this application, in another aspect, proposes a quality control system for agarwood koji production based on image recognition technology, comprising:

[0163] The image acquisition module is used to acquire images of agarwood slices and input them into the agarwood quality inspection module;

[0164] The agarwood spore quality inspection module is used to input the agarwood spore slice image into a preset quality inspection recognition model, and the quality inspection recognition model identifies the texture features of the agarwood spore slice image and outputs the corresponding quality level.

[0165] The quality control module is used to determine whether the current agarwood chips meet the quality standards.

[0166] If the standard is met, the next quality inspection of agarwood chips will proceed.

[0167] Conversely, an alarm signal will be issued;

[0168] An alarm module is used to respond to the alarm signal;

[0169] The image acquisition module, agarwood quality inspection module, quality control module, and alarm module are connected in sequence.

[0170] The module functions and interactions of the above system can be understood by referring to the corresponding steps in Embodiment 1, and will not be repeated in this embodiment.

[0171] The modules or steps of the present invention described above can be implemented using a general-purpose computing system. They can be centralized on a single computing system or distributed across a network of multiple computing systems. Optionally, they can be implemented using program code executable by a computing system, thereby storing them in a storage system for execution by the computing system, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps into a single integrated circuit module. Thus, the present invention is not limited to any specific hardware and software combination.

[0172] Example 3

[0173] like Figure 4 As shown, further, in another aspect, this application also proposes an electronic device, comprising:

[0174] processor;

[0175] Memory used to store processor-executable instructions;

[0176] The processor is configured to implement the agarwood production quality control method based on image recognition technology as described in Embodiment 1 when executing the executable instructions.

[0177] The electronic device of this disclosure includes a processor and a memory for storing processor-executable instructions. The processor is configured to implement the agarwood production quality control method based on image recognition technology described in Embodiment 1 when executing the executable instructions.

[0178] It should be noted here that the number of processors can be one or more. Furthermore, the electronic device in this embodiment may also include an input system and an output system. The processor, memory, input system, and output system can be connected via a bus or other means, without specific limitations herein.

[0179] As a computer-readable storage medium, the memory can be used to store software programs, computer-executable programs, and various modules, such as the program or module corresponding to the agarwood production quality control method based on image recognition technology in this embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0180] The input system can be used to receive input digital numbers or signals. These signals can be key signals related to user settings and function control of the device / terminal / server. The output system can include display devices such as screens.

[0181] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for quality control in the production of agarwood koji based on image recognition technology, characterized in that, Includes the following steps: S1. Collect images of agarwood slices; S2. Input the agarwood slice image into a preset quality inspection and identification model, and the quality inspection and identification model identifies the texture features of the agarwood slice image and outputs the corresponding quality level. The method for generating the quality inspection identification model includes: Collect and preprocess several images of agarwood slices; The process involves iterating through each of the agarwood slice images and using a CNN to extract texture features from the agarwood slice images, including gloss, texture spatial distribution, and texture morphology. The texture features are labeled, and the labeling information includes a quality level determined based on the glossiness, texture spatial distribution, and texture morphology; Based on the labeled texture features, a feature set is constructed; The feature set is divided into a training set and a validation set according to a preset ratio; The training set is input into a preset CNN model for feature training and learning to construct the quality inspection identification model. The recognition performance of the quality inspection identification model was verified using the validation set. If the verification is successful, the quality inspection and identification model will be deployed on the server and used for texture feature quality identification of agarwood slice images; If the verification fails, repeat the above steps to rebuild the quality inspection identification model; S3. Determine whether the current quality grade of the agarwood chips meets the standard: If the standard is met, the next quality inspection of agarwood chips will proceed. Conversely, an alarm signal will be issued.

2. The agarwood koji production quality control method based on image recognition technology according to claim 1, characterized in that, S1. Acquire images of agarwood slices, including: A batch of agarwood slice images were acquired and preprocessed. The agarwood slice image is sliced ​​to obtain image slices corresponding to several agarwood slices; Check the positional correspondence between the image slice and the corresponding agarwood slice, and record the positional information of the image slice.

3. The agarwood koji production quality control method based on image recognition technology according to claim 1, characterized in that, The annotation information also includes: The unit price is determined based on the gloss, texture spatial distribution, and texture morphology.

4. The agarwood koji production quality control method based on image recognition technology according to claim 1, characterized in that, S2. Input the agarwood slice image into a preset quality inspection and recognition model. The quality inspection and recognition model identifies the texture features of the agarwood slice image and outputs the corresponding quality level, including: Input the sliced ​​image of the agarwood into the quality inspection and identification model; The quality inspection identification model identifies the texture features in the agarwood slice image and predicts the quality level corresponding to the texture features. The quality grade is bound to the corresponding agarwood slice image and written into the corresponding image table to obtain the agarwood quality identification table.

5. The agarwood koji production quality control method based on image recognition technology according to claim 4, characterized in that, S2. Input the agarwood slice image into a preset quality inspection and recognition model. The quality inspection and recognition model identifies the texture features of the agarwood slice image and outputs the corresponding quality level, including: Input the sliced ​​image of the agarwood into the quality inspection and identification model; The quality inspection identification model identifies the texture features in the agarwood slice image and predicts and outputs the unit price corresponding to the texture features. The unit price is bound to the corresponding agarwood slice image and written into the corresponding image table to obtain the agarwood unit price prediction table.

6. A quality control system for agarwood koji production based on image recognition technology, used to implement the quality control method for agarwood koji production based on image recognition technology as described in any one of claims 1-5, characterized in that, include: The image acquisition module is used to acquire images of agarwood slices and input them into the agarwood quality inspection module; The agarwood spore quality inspection module is used to input the agarwood spore slice image into a preset quality inspection recognition model, and the quality inspection recognition model identifies the texture features of the agarwood spore slice image and outputs the corresponding quality level. The quality control module is used to determine whether the current agarwood chips meet the quality standards. If the standard is met, the next quality inspection of agarwood chips will proceed. Conversely, an alarm signal will be issued; An alarm module is used to respond to the alarm signal; The image acquisition module, agarwood quality inspection module, quality control module, and alarm module are connected in sequence.

7. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to implement the agarwood production quality control method based on image recognition technology as described in any one of claims 1-5 when executing the executable instructions.

Images