Digital identification method suitable for colloidal gold detection card detection

Abstract

The invention belongs to the field of colloidal gold detection, and particularly discloses a digital identification method suitable for colloidal gold detection card detection, which comprises the following specific steps: S1, image acquisition; s2, image preprocessing; s3, area detection; s4, feature extraction; s5, data comparison and analysis; s6, integrating the system; a complete application program is integrated, a mobile phone or an iPad is utilized to shoot a colloidal gold detection card, then an image is uploaded to a cloud server to be processed, one or more areas containing C and T lines of the colloidal gold detection card are identified, the length, width and color values of the C and T lines are read and calculated, then the extracted C and T line values are compared with a standard dictionary, and the detection result of the colloidal gold detection card is obtained. The content of the target object in the sample is judged, data is uploaded to a food safety big data platform, dependence on professional detection instruments is not needed, operation is easy, food enterprises, farmer markets, food workshops and families can conveniently conduct self-inspection screening on food, and food safety is protected.

Description

Technical Field

[0001] The invention belongs to the field of colloidal gold detection, and in particular relates to a digital identification method suitable for colloidal gold detection card detection. Background Art

[0002] Colloidal gold test card is a tool for rapid testing, widely used in medicine, food safety and environmental monitoring. Its working principle is based on the binding of colloidal gold-labeled antibodies or antigens to target substances in the sample, indicating the results through color changes; The traditional detection and identification method mainly uses a special detection instrument to read the detection data of a colloidal gold single card, and then uses a colorimetric method to determine the content of the target in the sample; However, traditional detection and identification methods require reliance on professional testing instruments, which are costly and inconvenient for food companies, farmers' markets, small food workshops, and households to conduct self-inspection and screening of food, and are not conducive to the detection and identification of multi-link cards and multi-line cards. Summary of the invention

[0003] The purpose of the present invention is to provide a digital identification method suitable for colloidal gold detection card detection to solve the problems raised in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions: A digital identification method suitable for colloidal gold detection card detection, the specific steps are as follows: S1. Image acquisition: Use a mobile phone or iPad to take a photo of the colloidal gold test card. After ensuring that the image is clear and the light is even, upload the image to the cloud server for processing; S2, image preprocessing: use image processing technology to process the image; S3, region detection: use edge detection algorithm to identify C and T line regions in the image, and then use contour detection algorithm to extract the contours of C and T lines; S4, feature extraction: calculate the length, width and color values ​​of C and T lines, and set the threshold range of CT lines according to the standard dictionary; S5. Data comparison and analysis: Compare the extracted C and T line values ​​with the standard dictionary to determine the content of the target substance in the sample, record the test results, and upload the data to the food safety big data platform; S6. System integration: Integrate steps S2-S5 into a complete application, providing a user-friendly interface for users to upload images and view detection results.

[0005] Preferably, the specific steps of image preprocessing in step S2 are as follows: S2.1, Denoising: Use Gaussian filter to smooth the image to reduce noise; S2.2. Grayscale: Convert a color image into a grayscale image.

[0006] Preferably, the specific steps of region detection in step S3 are as follows: Sa3.1, calculate gradient: use Sobel operator to calculate the gradient amplitude and direction of the image; Sa3.2, non-maximum suppression: perform non-maximum suppression on the gradient amplitude, retain the local maximum value, and suppress non-edge pixels; Sa3.3, double threshold processing: set high threshold and low threshold to divide the edge into strong edge, weak edge and non-edge; Sa3.4, edge connection: forming a complete edge by connecting strong edges and weak edges; Sa3.5. Extract contours: Use OpenCV's findContours function to extract contours from edge images; Sa3.6, Draw contours: Use the drawContours function to draw the extracted contours on the original image.

[0007] Preferably, in the step Sa3.2, a decision is made whether to retain the pixel by comparing the current pixel with its adjacent pixels in the gradient direction.

[0008] Preferably, in the Sa3.3 step, a strong edge is a pixel greater than a high threshold, a weak edge is a pixel between a high threshold and a low threshold, and a non-edge is a pixel less than a low threshold.

[0009] Preferably, in the Sa3.4 step, if a weak edge is connected to a strong edge, the weak edge is retained, otherwise the weak edge is suppressed.

[0010] Preferably, in the step S3, before identifying the C and T line regions and extracting the C and T line contours, the image is segmented using the OTSU threshold segmentation algorithm, and the specific steps are as follows: Sb3.1. Calculate the image histogram: count the number of pixels at each gray level in the image and generate a gray histogram; Sb3.2, calculate the total number of pixels in the image: calculate the total number of all pixels in the image; Sb3.3. Calculate the probability of each gray level: Calculate the probability of each gray level; Sb3.4, calculate the mean of foreground and background: calculate the mean of foreground and background for each possible threshold; Sb3.5, calculate the inter-class variance: calculate the inter-class variance for each threshold; Sb3.6, Find the best threshold: Find the threshold that maximizes the inter-class variance by traversing all possible thresholds; Sb3.7. Generate binary image: Use the optimal threshold to segment the image into a binary image.

[0011] Preferably, in step S4, an extraction model is established to extract image features, and the specific steps are as follows: S4.1. Collect data: collect image datasets containing C and T lines, annotate the C and T lines in the images, and generate training and test sets; S4.2, normalization processing: normalizing the image pixel values ​​to the range of 0-1; S4.3. Construct a convolutional neural network: Design a suitable CNN architecture, train the CNN using labeled data, and optimize the loss function to improve the accuracy of feature extraction; S4.4. Extract C and T line features: Use the trained CNN to extract the features of C and T lines; S4.5, KNN training: standardize the features extracted by CNN, and use the processed features and corresponding labels to train the KNN model, and select the appropriate K value to improve the classification accuracy; S4.6, threshold setting: establish a standard dictionary for C and T lines according to the standard, and adjust the threshold range according to the standard dictionary; S4.7. Evaluation and Optimization: Use cross-validation methods to evaluate the performance of the model, ensure the rationality of the threshold setting, and regularly monitor the performance of the model, collect feedback and make adjustments.

[0012] Preferably, the CNN architecture established in step S4.3 includes an input layer, a convolutional layer, an activation layer, a pooling layer and a fully connected layer.

[0013] Preferably, in step S5, Matplotlib or Plotly is used to generate a chart of the test results to display the test results, and the test chart includes the test time, sample information and test results.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention integrates a complete application program. After taking a photo of the colloidal gold detection card with a mobile phone or iPad, the image is uploaded to a cloud server for processing, one or more areas containing the C and T lines of the colloidal gold detection card are identified, the length, width and color values ​​of the C and T lines are read and calculated, and then the extracted C and T line values ​​are compared with a standard dictionary to judge the content of the target object in the sample, record the test results, and upload the data to a food safety big data platform. There is no need to rely on professional testing instruments, the operation is simple, and the use is user-friendly. It is convenient for food companies, farmers' markets, small food workshops, and families to do self-inspection and screening of food, thereby protecting food safety.

[0015] The present invention uses the OTSU threshold segmentation algorithm to segment the image before identifying the C and T line areas in the image and extracting the contours of the C and T lines to obtain an optimal threshold, and then compares each pixel in the grayscale image with the optimal threshold to segment the image into a foreground and a background, thereby reducing noise interference in the image before edge detection, so that the detection algorithm can focus more on important edge features, and the segmented image will have clearer edges, thereby improving detection accuracy, and the segmented binary image will make the contour more obvious, so that the contour extracted by the contour detection algorithm is more complete, which is convenient for subsequent feature analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them: Figure 1 A flowchart of the method steps of the present invention; Figure 2 It is a flowchart of the steps of image preprocessing of the present invention; Figure 3 A flowchart of the steps of region detection of the present invention; Figure 4 It is a flowchart of the steps of segmenting an image using the OTSU threshold segmentation algorithm of the present invention; Figure 5 A flowchart of the steps of establishing an extraction model to extract image features according to the present invention. DETAILED DESCRIPTION

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0018] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0020] As attached Figure 1 To Attachment Figure 5 As shown: Embodiment 1: This embodiment provides a digital identification method suitable for colloidal gold detection card detection, and the specific steps are as follows: S1. Image acquisition: Use a mobile phone or iPad to take a photo of the colloidal gold test card. After ensuring that the image is clear and the light is even, upload the image to the cloud server for processing; S2, image preprocessing: use image processing technology to process the image; S3, region detection: use edge detection algorithm to identify C and T line regions in the image, and then use contour detection algorithm to extract the contours of C and T lines; S4, feature extraction: calculate the length, width and color values ​​of C and T lines, and set the threshold range of CT lines according to the standard dictionary; S5. Data comparison and analysis: Compare the extracted C and T line values ​​with the standard dictionary to determine the content of the target substance in the sample, record the test results, and upload the data to the food safety big data platform; S6. System integration: Integrate steps S2-S5 into a complete application, providing a user-friendly interface for users to upload images and view detection results.

[0021] Specifically, the specific steps of image preprocessing in step S2 are as follows: S2.1, Denoising: Use a Gaussian filter to smooth the image to reduce noise. The formula is as follows: ,in is a Gaussian function, is the standard deviation, are pixel coordinates; S2.2. Grayscale: Convert a color image into a grayscale image.

[0022] Specifically, the specific steps of region detection in step S3 are as follows: Sa3.1, calculate gradient: use Sobel operator to calculate the gradient magnitude and direction of the image. The formula of gradient magnitude is as follows: ,in is the gradient amplitude, which indicates the intensity change of the image at a certain point. is the horizontal gradient of the image, which is obtained by performing horizontal edge detection on the image. It is the gradient of the image in the vertical direction, which is obtained by performing vertical edge detection on the image; The formula for the gradient direction is as follows: ,in is the gradient direction, indicating the edge direction of the image at a certain point, is the inverse tangent function, which is used to calculate the given and The angle corresponding to the ratio of Sa3.2, non-maximum suppression: perform non-maximum suppression on the gradient amplitude, retain the local maximum value, and suppress non-edge pixels; Sa3.3, double threshold processing: set high threshold and low threshold to divide the edge into strong edge, weak edge and non-edge; Sa3.4, edge connection: forming a complete edge by connecting strong edges and weak edges; Sa3.5. Extract contours: Use OpenCV's findContours function to extract contours from edge images; Sa3.6, Draw contours: Use the drawContours function to draw the extracted contours on the original image.

[0023] Specifically, in step Sa3.2, by comparing the current pixel with its adjacent pixels in the gradient direction, it is decided whether to retain the pixel.

[0024] Specifically, in step Sa3.3, a strong edge is a pixel greater than a high threshold, a weak edge is a pixel between a high threshold and a low threshold, and a non-edge is a pixel less than a low threshold.

[0025] Specifically, in step Sa3.4, if a weak edge is connected to a strong edge, the weak edge is retained, otherwise the weak edge is suppressed.

[0026] Specifically, in step S5, Matplotlib or Plotly is used to generate a chart of the test results to display the test results. The test chart includes the test time, sample information and the test results.

[0027] From the above, it can be seen that by integrating a complete application, after taking a photo of the colloidal gold test card with a mobile phone or iPad, the image is uploaded to the cloud server for processing, and the edge detection algorithm is used to identify the C and T line areas in the image, and then the contour detection algorithm is used to extract the contours of the C and T lines, thereby identifying one or more areas containing the C and T lines of the colloidal gold test card, reading and calculating the length, width and color values ​​of the C and T lines, and then comparing the extracted C and T line values ​​with the standard dictionary to determine the content of the target in the sample, record the test results, and upload the data to the food safety big data platform. At the same time, a test chart will be generated for personnel to view the test situation, without relying on professional testing instruments, simple operation, and user-friendly use, which is convenient for food companies, farmers' markets, small food workshops, and families to do self-inspection and screening of food to protect food safety.

[0028] Embodiment 2: This embodiment is basically the same as the previous embodiment, except that, in step S3, before identifying the C and T line regions and extracting the C and T line contours, the image is segmented using the OTSU threshold segmentation algorithm. The specific steps are as follows: Sb3.1. Calculate the image histogram: count the number of pixels at each gray level in the image and generate a gray histogram; Sb3.2, calculate the total number of pixels in the image: calculate the total number of all pixels in the image; Sb3.3. Calculate the probability of each gray level: Calculate the probability of each gray level using the following formula: ,in is the number of pixels at gray level i, N is the total number of pixels in the image, is the probability of gray level i; Sb3.4, calculate the mean of foreground and background: for each possible threshold, calculate the mean of foreground and background. The foreground mean calculation formula is as follows: ; The background mean value is calculated as follows: ; Sb3.5, calculate the inter-class variance: For each threshold, calculate the inter-class variance, the formula is as follows: ,in is the inter-class variance, indicating the degree of separation between different classes, t is the threshold currently considered, is the probability of pixels below threshold t, is the probability of pixels above the threshold t, is the average gray value below the threshold t, is the average gray value above the threshold t; Sb3.6, Find the best threshold: Find the threshold that maximizes the inter-class variance by traversing all possible thresholds; Sb3.7. Generate binary image: Use the optimal threshold to segment the image into a binary image.

[0029] From the above, it can be seen that before identifying the C and T line areas in the image and extracting the contours of the C and T lines, the OTSU threshold segmentation algorithm is used to segment the image to obtain the optimal threshold, and then each pixel in the grayscale image is compared with the optimal threshold. If the pixel value is greater than or equal to the threshold, it is set to white, and if the pixel value is less than the threshold, it is set to black, thereby segmenting the image into foreground and background, and then using the edge detection algorithm to identify the C and T line areas in the image, and then using the contour detection algorithm to extract the contours of the C and T lines, so that before edge detection, the noise interference in the image can be reduced, so that the detection algorithm can focus more on important edge features instead of being disturbed by noise. At the same time, the segmented image will have clearer edges, so that the edge detection algorithm can more accurately identify the edges of the C and T lines, improve the detection accuracy, and the segmented binary image will make the contour more obvious, so that the contour extracted by the contour detection algorithm is more complete, which is convenient for subsequent feature analysis.

[0030] Embodiment 3: This embodiment is basically the same as the previous embodiment, except that in step S4, an extraction model is established to extract image features. The specific steps are as follows: S4.1. Collect data: collect image datasets containing C and T lines, annotate the C and T lines in the images, and generate training and test sets; S4.2, normalization processing: normalizing the image pixel values ​​to the range of 0-1; S4.3. Construct a convolutional neural network: Design a suitable CNN architecture, train the CNN using labeled data, and optimize the loss function to improve the accuracy of feature extraction; S4.4. Extract C and T line features: Use the trained CNN to extract the features of C and T lines; S4.5, KNN training: standardize the features extracted by CNN, and use the processed features and corresponding labels to train the KNN model, and select the appropriate K value to improve the classification accuracy; S4.6, threshold setting: establish a standard dictionary for C and T lines according to the standard, and adjust the threshold range according to the standard dictionary; S4.7. Evaluation and Optimization: Use cross-validation methods to evaluate the performance of the model, ensure the rationality of the threshold setting, and regularly monitor the performance of the model, collect feedback and make adjustments.

[0031] Specifically, the CNN architecture established in step S4.3 includes an input layer, a convolutional layer, an activation layer, a pooling layer, and a fully connected layer.

[0032] From the above, we can see that the image is input through the input layer, the convolution layer is used to extract features, the activation layer uses the ReLU activation function, the pooling layer reduces the feature dimension, and then the features of the C and T lines are output through the fully connected layer. The labeled data is used to train CNN, and the loss function is optimized to improve the accuracy of feature extraction. By constructing a recognition analysis model, which combines the feature extraction ability of CNN and the classification ability of KNN, the accuracy of calculating the length, width and color values ​​of C and T lines can be significantly improved, and the threshold range of C and T lines can be set according to the standard dictionary to improve the accuracy and speed of recognition analysis.

[0033] This design application is applied to food companies, farmers' markets, small food workshops, families, etc. for self-inspection and screening of food. The colloidal gold test card is photographed by mobile phone or iPad and uploaded to the cloud server, and then one or more areas containing the C and T lines of the colloidal gold test card are identified, and the values ​​of the C and T lines of the colloidal gold test card are read. Then, the standard dictionary is compared to determine the content of the target object in the sample. The test data can be uploaded to the food safety big data platform for food safety big data analysis. It is designed not to rely on professional instruments, but only through mobile phones and other equipment to complete detection and identification, reduce costs, and facilitate personnel to do self-inspection and screening of food.

[0034] It is important to note that the construction and arrangement of the present application shown in the various exemplary embodiments is illustrative only. Therefore, the present invention is not limited to specific embodiments, but extends to a variety of modifications still within the scope of the appended claims.

[0035] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A digital identification method suitable for colloidal gold detection card detection, characterized in that: The specific steps are as follows: S1. Image acquisition: Use a mobile phone or iPad to take a photo of the colloidal gold test card. After ensuring that the image is clear and the light is even, upload the image to the cloud server for processing; S2, image preprocessing: use image processing technology to process the image; S3, region detection: use edge detection algorithm to identify C and T line regions in the image, and then use contour detection algorithm to extract the contours of C and T lines; S4, feature extraction: calculate the length, width and color values ​​of C and T lines, and set the threshold range of CT lines according to the standard dictionary; S5. Data comparison and analysis: Compare the extracted C and T line values ​​with the standard dictionary to determine the content of the target substance in the sample, record the test results, and upload the data to the food safety big data platform; S6. System integration: Integrate steps S2-S5 into a complete application, providing a user-friendly interface for users to upload images and view detection results.

2. A digital identification method suitable for colloidal gold detection card detection according to claim 1, characterized in that: The specific steps of image preprocessing in step S2 are as follows: S2.1, Denoising: Use Gaussian filter to smooth the image to reduce noise; S2.

2. Grayscale: Convert a color image into a grayscale image.

3. A digital identification method suitable for colloidal gold detection card detection according to claim 1, characterized in that: The specific steps of region detection in step S3 are as follows: Sa3.1, calculate gradient: use Sobel operator to calculate the gradient amplitude and direction of the image; Sa3.2, non-maximum suppression: perform non-maximum suppression on the gradient amplitude, retain the local maximum value, and suppress non-edge pixels; Sa3.3, double threshold processing: set high threshold and low threshold to divide the edge into strong edge, weak edge and non-edge; Sa3.4, edge connection: forming a complete edge by connecting strong edges and weak edges; Sa3.

5. Extract contours: Use OpenCV's findContours function to extract contours from edge images; Sa3.6, Draw contours: Use the drawContours function to draw the extracted contours on the original image.

4. A digital identification method suitable for colloidal gold detection card detection according to claim 3, characterized in that: In the Sa3.2 step, a decision is made as to whether to retain the pixel by comparing the current pixel with its adjacent pixels in the gradient direction.

5. A digital identification method suitable for colloidal gold detection card detection according to claim 3, characterized in that: In the Sa3.3 step, a strong edge is a pixel greater than a high threshold, a weak edge is a pixel between a high threshold and a low threshold, and a non-edge is a pixel less than a low threshold.

6. A digital identification method suitable for colloidal gold detection card detection according to claim 3, characterized in that: In the Sa3.4 step, if a weak edge is connected to a strong edge, the weak edge is retained; otherwise, the weak edge is suppressed.

7. A digital identification method suitable for colloidal gold detection card detection according to claim 1, characterized in that: In the step S3, before identifying the C and T line regions and extracting the C and T line contours, the image is segmented using the OTSU threshold segmentation algorithm. The specific steps are as follows: Sb3.

1. Calculate the image histogram: count the number of pixels at each gray level in the image and generate a gray histogram; Sb3.2, calculate the total number of pixels in the image: calculate the total number of all pixels in the image; Sb3.

3. Calculate the probability of each gray level: Calculate the probability of each gray level; Sb3.4, calculate the mean of foreground and background: calculate the mean of foreground and background for each possible threshold; Sb3.5, calculate the inter-class variance: calculate the inter-class variance for each threshold; Sb3.6, Find the best threshold: Find the threshold that maximizes the inter-class variance by traversing all possible thresholds; Sb3.

7. Generate binary image: Use the optimal threshold to segment the image into a binary image.

8. A digital identification method suitable for colloidal gold detection card detection according to claim 1, characterized in that: In step S4, an extraction model is established to extract image features. The specific steps are as follows: S4.

1. Collect data: collect image datasets containing C and T lines, annotate the C and T lines in the images, and generate training and test sets; S4.2, normalization processing: normalizing the image pixel values ​​to the range of 0-1; S4.

3. Construct a convolutional neural network: Design a suitable CNN architecture, train the CNN using labeled data, and optimize the loss function to improve the accuracy of feature extraction; S4.

4. Extract C and T line features: Use the trained CNN to extract the features of C and T lines; S4.5, KNN training: standardize the features extracted by CNN, and use the processed features and corresponding labels to train the KNN model, and select the appropriate K value to improve the classification accuracy; S4.6, threshold setting: establish a standard dictionary for C and T lines according to the standard, and adjust the threshold range according to the standard dictionary; S4.

7. Evaluation and Optimization: Use cross-validation methods to evaluate the performance of the model, ensure the rationality of the threshold setting, and regularly monitor the performance of the model, collect feedback and make adjustments.

9. A digital identification method suitable for colloidal gold detection card detection according to claim 8, characterized in that: The CNN architecture established in step S4.3 includes an input layer, a convolutional layer, an activation layer, a pooling layer and a fully connected layer.

10. A digital identification method suitable for colloidal gold detection card detection according to claim 1, characterized in that: In the step S5, Matplotlib or Plotly is used to generate a chart of the test results to display the test results. The test chart includes the test time, sample information and the test results.

Images