Colla corii asini quality detection method and system based on image recognition

Abstract

The invention relates to the technical field of image recognition, in particular to a donkey-hide gelatin quality detection method and system based on image recognition, and the method comprises the steps: firstly, obtaining time sequence image data sets of different stages in a donkey-hide gelatin production process through a multispectral camera, including decocting, filtering, concentrating and cooling forming; secondly, constructing a donkey-hide gelatin image abnormal region recognition model, processing the obtained time sequence image data, and recognizing abnormal regions in images at all stages; constructing a donkey-hide gelatin image abnormal region detection model based on the abnormal regions detected in the images at each stage, and comparing and analyzing the change of the abnormal regions of the images to obtain the impurity abnormity of the donkey-hide gelatin image, thereby obtaining a second region abnormal change coefficient; meanwhile, through a multi-parameter fusion technology, the abnormal change coefficients of different stages are integrated, and the donkey-hide gelatin abnormal coefficient is obtained. Finally, according to the donkey-hide gelatin abnormal coefficient, the donkey-hide gelatin is divided into first-level, second-level and third-level, and a quality evaluation mechanism is provided for donkey-hide gelatin quality

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and in particular to a method and system for detecting donkey-hide gelatin quality based on image recognition. Background Art

[0002] Donkey hide gelatin is a traditional Chinese medicinal material, which is widely used in the fields of health care and medicine for its nourishing and medical effects. With the increase in market demand, the production scale of donkey hide gelatin is expanding, and the requirements for its product quality testing are also increasing. The quality of donkey hide gelatin is mainly evaluated by its appearance, color, glossiness, transparency, bubbles and impurities. The existing donkey hide gelatin quality detection method mainly relies on sampling and judging the finished donkey hide gelatin and edge detection algorithms to detect the surface of donkey hide gelatin for leakage. The detection process relies on identifying the surface characteristics of the finished donkey hide gelatin. This method is not only unable to regulate the production process, but also inefficient and has low detection accuracy. It is easily affected by the subjective judgment of the test personnel, resulting in poor stability and consistency of the test results.

[0003] Therefore, a method and system for detecting donkey-hide gelatin quality based on image recognition was proposed. Summary of the invention

[0004] The object of the present invention is to provide a method and system for detecting the quality of donkey-hide gelatin based on image recognition. First, a multispectral camera is used to obtain a time series image data set of different stages in the donkey-hide gelatin production process, including boiling, filtering, concentration and cooling molding. Secondly, a model for identifying abnormal areas of donkey-hide gelatin images is constructed, and the acquired time series image data is processed to identify abnormal areas in the images of each stage. Then, based on the abnormal areas detected in the images of each stage, a model for detecting abnormal areas of donkey-hide gelatin images is constructed, and the changes in abnormal areas of the images are compared and analyzed to obtain the abnormal impurities of the donkey-hide gelatin images, thereby obtaining the abnormal variation coefficient of the second region. At the same time, through multi-parameter fusion technology, the abnormal variation coefficients of different stages are combined to obtain the abnormal coefficient of donkey-hide gelatin. Finally, according to the abnormal coefficient of donkey-hide gelatin, donkey-hide gelatin is divided into primary, secondary and tertiary levels, providing a standardized quality assessment mechanism.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for detecting donkey-hide gelatin quality based on image recognition, comprising:

[0007] Identify the production process of donkey-hide gelatin, which includes boiling, filtering, concentrating and cooling and molding;

[0008] Acquire a time-series image data set in a production process, wherein the time-series image data set includes a first image, a second image, a third image, a fourth image, and a fifth image;

[0009] Constructing an abnormal region recognition model for donkey-hide gelatin images to recognize the time series image data set, and obtaining a first image abnormal region, a second image abnormal region, a third image abnormal region, a fourth image abnormal region, and a fifth image abnormal region;

[0010] Constructing an abnormal region detection model for donkey-hide gelatin images to analyze the first image abnormal region, the second image abnormal region, the third image abnormal region, the fourth image abnormal region, and the fifth image abnormal region to obtain the first region abnormal variation coefficient, the second region abnormal variation coefficient, the third region abnormal variation coefficient, and the fourth region abnormal variation coefficient;

[0011] The cooled and formed donkey-hide gelatin is divided to obtain the first donkey-hide gelatin;

[0012] Obtaining the donkey-hide gelatin abnormality coefficient through multi-parameter fusion according to the abnormal variation coefficient of the first region, the abnormal variation coefficient of the second region, the abnormal variation coefficient of the third region, and the abnormal variation coefficient of the fourth region;

[0013] The first donkey-hide gelatin is graded according to the donkey-hide gelatin abnormality coefficient to obtain first-grade donkey-hide gelatin, second-grade donkey-hide gelatin and third-grade donkey-hide gelatin.

[0014] Preferably, the images in the time series image data set are acquired by a multispectral camera;

[0015] The first image is an image taken before brewing, the second image includes an image after brewing and before filtering, the third image includes an image after filtering and before concentration, the fourth image includes an image after concentration and before cooling and molding, and the fifth image is an image after cooling and molding.

[0016] Preferably, the abnormal area recognition model of donkey-hide gelatin image includes an image defect module, an image grayscale defect module, an image thermal defect analysis module, an image defect area fusion module and an abnormal area output module;

[0017] The image defect module obtains a first image defect by identifying the image surface;

[0018] The image grayscale defect module obtains a grayscale image by grayscale processing the image; and obtains a second image defect according to the grayscale image;

[0019] The image thermal defect analysis module obtains a third image defect according to the temperature uniformity by acquiring a thermal map of the image;

[0020] The image defect area fusion module determines abnormal areas in the first image, the second image, the third image, the fourth image, and the fifth image according to the first image defect, the second image defect, and the third image defect;

[0021] The abnormal region output module marks and outputs abnormal regions in the first image, the second image, the third image, the fourth image, and the fifth image.

[0022] Preferably, the image defect module is used to identify impurities in the donkey-hide gelatin production process; the impurities are hair, grease, incompletely dissolved colloids and foam scum;

[0023] The image grayscale module is used to identify the uniformity of color in the donkey-hide gelatin production process;

[0024] The image thermal defect analysis module is used for temperature abnormality areas of the third image, the fourth image and the fifth image before and after high-temperature concentration.

[0025] Preferably, the abnormal region detection model of donkey-hide gelatin image includes a first donkey-hide gelatin impurity abnormality detection module, a second donkey-hide gelatin impurity abnormality detection module, a third donkey-hide gelatin impurity abnormality detection module and a fourth donkey-hide gelatin impurity abnormality detection module;

[0026] The first donkey-hide gelatin impurity anomaly detection module is used to analyze the first image abnormal area and the second image abnormal area to obtain the first donkey-hide gelatin impurity anomaly, which includes the change in the number of abnormal impurities, the diffusion range and the regional transformation; and the first regional abnormal change coefficient is obtained based on the first donkey-hide gelatin impurity anomaly.

[0027] Preferably, the second donkey-hide gelatin impurity anomaly detection module is used to analyze the second image abnormal area and the third image abnormal area to obtain the second donkey-hide gelatin impurity anomaly, wherein the second donkey-hide gelatin impurity anomaly includes the change in the number of abnormal impurities, the diffusion range and the regional transformation; and obtain the second regional abnormality change coefficient according to the second donkey-hide gelatin impurity anomaly;

[0028] The third donkey-hide gelatin impurity anomaly detection module is used to analyze the third image abnormal area and the fourth image abnormal area to obtain the third donkey-hide gelatin impurity anomaly, wherein the third donkey-hide gelatin impurity anomaly includes temperature anomaly, color anomaly, change in the number of abnormal impurities, diffusion range and regional change; and obtain the third regional abnormal change coefficient according to the third donkey-hide gelatin impurity anomaly;

[0029] The fourth donkey-hide gelatin impurity anomaly detection module is used to analyze the fourth image abnormal area and the fifth image abnormal area to obtain the fourth donkey-hide gelatin impurity anomaly, and the fourth donkey-hide gelatin impurity anomaly includes temperature anomaly, color anomaly, change in the number of abnormal impurities, diffusion range and regional change; the fourth region abnormal change coefficient is obtained based on the fourth donkey-hide gelatin impurity anomaly.

[0030] Preferably, the abnormal coefficient of donkey-hide gelatin includes the abnormal variation coefficient of the first region, the abnormal variation coefficient of the second region, the abnormal variation coefficient of the third region and the abnormal variation coefficient of the fourth region, and the abnormal coefficient of donkey-hide gelatin is obtained by multi-parameter fusion; the specific calculation formula of the abnormal coefficient of donkey-hide gelatin is:

[0031] E=ω1E1+ω2E2+ω3E3+ω4E4;

[0032] Among them, ω1 is the weight of the abnormal variation coefficient of the first area, E1 is the abnormal variation coefficient of the first area, ω2 is the weight of the abnormal variation coefficient of the second area, E2 is the abnormal variation coefficient of the second area, ω3 is the weight of the abnormal variation coefficient of the third area, E3 is the abnormal variation coefficient of the third area, ω4 is the weight of the abnormal variation coefficient of the fourth area, and E4 is the abnormal variation coefficient of the fourth area;

[0033] The first donkey-hide gelatin is graded according to the donkey-hide gelatin abnormality coefficient, and the grade classification includes:

[0034] Set the abnormal level threshold set TH = {S1, S2}. When the abnormal coefficient of the donkey-hide gelatin is less than S1, the corresponding first donkey-hide gelatin level is first-grade donkey-hide gelatin; when the abnormal coefficient of the donkey-hide gelatin is in the interval [S1, S2], the corresponding first donkey-hide gelatin level is second-grade donkey-hide gelatin; when the abnormal coefficient of the donkey-hide gelatin is greater than S2, the corresponding first donkey-hide gelatin level is third-grade donkey-hide gelatin; the lower the first donkey-hide gelatin level, the better the quality of the first donkey-hide gelatin.

[0035] An image recognition-based donkey-hide gelatin quality detection system, comprising:

[0036] Identify the production process of donkey-hide gelatin, which includes boiling, filtering, concentrating and cooling and molding;

[0037] An donkey-hide gelatin image acquisition unit, used to acquire a time-series image data set in a production process, wherein the time-series image data set includes a first image, a second image, a third image, a fourth image, and a fifth image;

[0038] A first donkey-hide gelatin model construction unit is used to construct a donkey-hide gelatin image abnormal region recognition model to recognize the time series image data set, and obtain a first image abnormal region, a second image abnormal region, a third image abnormal region, a fourth image abnormal region, and a fifth image abnormal region;

[0039] The second donkey-hide gelatin model construction unit is used to construct a donkey-hide gelatin image abnormal region detection model to analyze the first image abnormal region, the second image abnormal region, the third image abnormal region, the fourth image abnormal region and the fifth image abnormal region to obtain the first region abnormal variation coefficient, the second region abnormal variation coefficient, the third region abnormal variation coefficient and the fourth region abnormal variation coefficient;

[0040] A donkey-hide gelatin abnormality acquisition unit, configured to obtain the donkey-hide gelatin abnormality coefficient through multi-parameter fusion according to the first region abnormality variation coefficient, the second region abnormality variation coefficient, the third region abnormality variation coefficient, and the fourth region abnormality variation coefficient;

[0041] The donkey-hide gelatin grade acquisition unit is used to grade the first donkey-hide gelatin according to the donkey-hide gelatin abnormality coefficient to obtain first-grade donkey-hide gelatin, second-grade donkey-hide gelatin and third-grade donkey-hide gelatin.

[0042] Preferably, the abnormal region recognition model of donkey-hide gelatin image includes an image defect module, an image grayscale defect module, an image thermal defect analysis module, an image defect region fusion module and an abnormal region output module.

[0043] Preferably, the first donkey-hide gelatin is graded according to the donkey-hide gelatin abnormality coefficient, and the grade classification includes:

[0044] Set the abnormal level threshold set TH = {S1, S2}. When the abnormal coefficient of the donkey-hide gelatin is less than S1, the corresponding first donkey-hide gelatin level is first-grade donkey-hide gelatin; when the abnormal coefficient of the donkey-hide gelatin is in the interval [S1, S2], the corresponding first donkey-hide gelatin level is second-grade donkey-hide gelatin; when the abnormal coefficient of the donkey-hide gelatin is greater than S2, the corresponding first donkey-hide gelatin level is third-grade donkey-hide gelatin; the lower the first donkey-hide gelatin level, the better the quality of the first donkey-hide gelatin.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] 1. The present invention collects and analyzes images of different stages in the donkey-hide gelatin production process through image recognition technology based on a multispectral camera. By constructing an abnormal area recognition model for donkey-hide gelatin images, the synergy of the image defect module, the grayscale defect module and the thermal defect analysis module enables comprehensive and accurate recognition of donkey-hide gelatin surface defects, color uniformity and temperature anomalies during high-temperature concentration. Compared with traditional manual detection methods, image recognition technology not only improves detection efficiency, but also reduces human errors. It can output the quality detection results of donkey-hide gelatin in real time and efficiently, ensuring the consistency and reliability of product quality.

[0047] 2. The present invention constructs an abnormal area detection model for donkey-hide gelatin images, and conducts in-depth analysis of subtle defects in images based on a multi-stage detection mechanism of time-series images, including grayscale processing, thermal map analysis and other means to ensure temperature changes, impurity quantity, diffusion range, and regional transformation indicators. This method not only enhances the comprehensiveness and sensitivity of detection, but also reduces human intervention through automated processing of image recognition technology, thereby improving detection efficiency and accuracy.

[0048] 3. The present invention realizes the automation and precision of donkey-hide gelatin quality detection through image recognition technology. First, the time series image data in the donkey-hide gelatin production process is obtained through a multi-spectral camera, and combined with the image abnormal area recognition and detection model, the abnormal parameters such as impurities, temperature, color, etc. at each stage are deeply analyzed to identify the defects in donkey-hide gelatin in real time and accurately. The abnormal coefficient of donkey-hide gelatin is calculated by multi-parameter fusion, and the donkey-hide gelatin is graded according to this coefficient. This method can effectively distinguish the quality level of donkey-hide gelatin, thereby ensuring the stability and consistency of product quality, reducing human errors, and improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A schematic diagram of a process flow of a method for detecting donkey-hide gelatin quality based on image recognition provided by an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of the structure of an image recognition-based donkey-hide gelatin quality detection system provided by an embodiment of the present invention;

[0051] Figure 3 A schematic diagram of the structure of the abnormal region recognition model for donkey-hide gelatin images provided by an embodiment of the present invention;

[0052] Figure 4 A schematic diagram of the structure of an abnormal region detection model for donkey-hide gelatin images provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] The present invention provides a method for detecting donkey-hide gelatin quality based on image recognition. The method is applied to a donkey-hide gelatin quality detection system based on image recognition. The flowchart of the specific method and system is shown in Figure 1 and Figure 2 .

[0055] Embodiment 1

[0056] The main raw material of donkey hide is donkey skin. Donkey hide needs to be cleaned and depilated before production to remove impurities and hair on the surface. The donkey hide is soaked in water and scrubbed repeatedly to remove dirt, fat and hair from the leather. The processed donkey hide is cut into small pieces for boiling, and an image is acquired before boiling as the first image; the gelatinous component in the donkey hide is boiled out to form a liquid rich in collagen, and the image after boiling is acquired at this time; impurities and residues are generated after boiling, and these impurities are removed by filtering, and images are acquired before and after filtration. As one embodiment of the present invention, refer to Figure 1 S10 in the embodiment is applied to a donkey-hide gelatin image acquisition unit of a donkey-hide gelatin quality detection system based on image recognition, and the donkey-hide gelatin image acquisition unit is used to acquire a time-series image data set in a production process, and the time-series image data set includes a first image, a second image, a third image, a fourth image, and a fifth image, and the images in the time-series image data set are acquired by a multispectral camera. This embodiment collects data of a production line for producing donkey-hide gelatin A.

[0057] Furthermore, the first image is an image obtained before brewing, the second image includes an image after brewing and before filtering, the third image includes an image after filtering and before concentration, the fourth image includes an image after concentration and before cooling and molding, and the fifth image is an image after cooling and molding.

[0058] In this embodiment, a multispectral camera is used to obtain time-series images during the production process. This method captures the changes of donkey-hide gelatin at different stages and provides multi-dimensional data for subsequent operations. These data provide accurate image recognition and analysis of the quality and defect abnormalities corresponding to each stage, which helps to accurately locate problems in the production process, so as to take corrective measures in the first place and optimize the production process.

[0059] Reference Figure 1 S20 in which S20 is applied to a first donkey-hide gelatin model construction unit of a donkey-hide gelatin quality detection system based on image recognition, wherein the first donkey-hide gelatin model construction unit is used to construct a donkey-hide gelatin image abnormal region recognition model to recognize a time series image data set to obtain a first image abnormal region, a second image abnormal region, a third image abnormal region, a fourth image abnormal region, and a fifth image abnormal region;

[0060] Furthermore, the abnormal region recognition model of donkey-hide gelatin image includes an image defect module, an image grayscale defect module, an image thermal defect analysis module, an image defect region fusion module and an abnormal region output module. Figure 3 ;

[0061] The image defect module obtains a first image defect by identifying the image surface;

[0062] The image grayscale defect module obtains a grayscale image by grayscale processing the image; obtains a second image defect based on the grayscale image; the image thermal defect analysis module obtains a third image defect based on the temperature uniformity by acquiring the thermal map of the image; the image defect area fusion module determines the abnormal areas in the first image, the second image, the third image, the fourth image and the fifth image based on the first image defect, the second image defect and the third image defect; the abnormal area output module marks and outputs the abnormal areas in the first image, the second image, the third image, the fourth image and the fifth image.

[0063] In this embodiment, the abnormal region recognition model of donkey-hide gelatin images is constructed to analyze the images in the time series image data set one by one, so as to obtain the abnormal stages in the donkey-hide gelatin production process, and the image recognition technology is also used to locate the defects in donkey-hide gelatin, such as impurities, bubbles and poor molding. This model improves the detection accuracy for donkey-hide gelatin quality monitoring.

[0064] Furthermore, the image defect module is used to identify impurities in the donkey-hide gelatin production process; the impurities are hair, grease, incompletely dissolved colloids and foam scum;

[0065] The image grayscale module is used to identify the uniformity of color in the donkey-hide gelatin production process;

[0066] The image thermal defect analysis module is used for temperature abnormality areas of the third image, the fourth image and the fifth image before and after high-temperature concentration.

[0067] In this embodiment, the defective area in the image is deeply analyzed by identifying the abnormal area of ​​the image; the analysis method includes grayscale processing, thermal map analysis and other means, so as to identify the number of impurities, diffusion range, and regional transformation in the image. This method not only enhances the comprehensiveness of the detection, but also reduces human intervention through the automated processing of image recognition technology, greatly improving the detection efficiency and accuracy.

[0068] Reference Figure 1 S30 in which S30 is applied to a second donkey-hide gelatin model construction unit of an donkey-hide gelatin quality detection system based on image recognition, wherein the second donkey-hide gelatin model construction unit is used to construct a donkey-hide gelatin image abnormal region detection model to analyze the first image abnormal region, the second image abnormal region, the third image abnormal region, the fourth image abnormal region and the fifth image abnormal region to obtain the first region abnormal variation coefficient, the second region abnormal variation coefficient, the third region abnormal variation coefficient and the fourth region abnormal variation coefficient;

[0069] Furthermore, the abnormal region detection model of donkey-hide gelatin image includes a first donkey-hide gelatin impurity abnormality detection module, a second donkey-hide gelatin impurity abnormality detection module, a third donkey-hide gelatin impurity abnormality detection module and a fourth donkey-hide gelatin impurity abnormality detection module, see Figure 4 ;

[0070] The first donkey-hide gelatin impurity anomaly detection module is used to analyze the first image abnormal area and the second image abnormal area to obtain the first donkey-hide gelatin impurity anomaly, which includes the change in the number of abnormal impurities, the diffusion range and the regional transformation; and the first regional abnormal change coefficient is obtained based on the first donkey-hide gelatin impurity anomaly.

[0071] The second donkey-hide gelatin impurity anomaly detection module is used to analyze the second image abnormal area and the third image abnormal area to obtain the second donkey-hide gelatin impurity anomaly, wherein the second donkey-hide gelatin impurity anomaly includes the change in the number of abnormal impurities, the diffusion range and the regional transformation; and obtain the second regional abnormal change coefficient according to the second donkey-hide gelatin impurity anomaly;

[0072] The third donkey-hide gelatin impurity anomaly detection module is used to analyze the third image abnormal area and the fourth image abnormal area to obtain the third donkey-hide gelatin impurity anomaly, wherein the third donkey-hide gelatin impurity anomaly includes temperature anomaly, color anomaly, change in the number of abnormal impurities, diffusion range and regional change; and obtain the third regional abnormal change coefficient according to the third donkey-hide gelatin impurity anomaly;

[0073] The fourth donkey-hide gelatin impurity anomaly detection module is used to analyze the fourth image abnormal area and the fifth image abnormal area to obtain the fourth donkey-hide gelatin impurity anomaly, and the fourth donkey-hide gelatin impurity anomaly includes temperature anomaly, color anomaly, change in the number of abnormal impurities, diffusion range and regional change; the fourth region abnormal change coefficient is obtained based on the fourth donkey-hide gelatin impurity anomaly.

[0074] When the temperature anomaly, color anomaly, abnormal impurity quantity change, diffusion range and regional transformation change, the effect produced is positive correlation or negative correlation. For example, when the abnormal impurity quantity change in the second donkey-hide gelatin impurity abnormality detection module is reduced compared with the first donkey-hide gelatin impurity abnormality detection module, the abnormal impurity quantity change rate is a negative value; the regional abnormality change coefficient is obtained by weighted average calculation of each change rate, refer to Table 1 for details;

[0075] Table 1 Abnormal detection rate of donkey-hide gelatin impurities

[0076]

[0077] Among them, the image detected by the second donkey-hide gelatin impurity abnormality detection module is the image before and after filtering, so the impurity quantity and diffusion range are reduced compared with the impurity quantity and diffusion range of the first donkey-hide gelatin impurity abnormality detection module; the temperature difference in the third donkey-hide gelatin impurity abnormality detection module and the fourth donkey-hide gelatin impurity abnormality detection module is because the fourth image is an image after high-temperature concentration, and the temperature of donkey-hide gelatin needs to reach 120°C during the high-temperature concentration process; the color abnormality difference is caused by uneven heating at different positions of donkey-hide gelatin during the high-temperature concentration and cooling process, and the color difference calculation is calculated by the representation method of color space.

[0078] In this embodiment, the image abnormal area detection model provides a scientific basis for the comprehensive evaluation of donkey-hide gelatin quality by analyzing the abnormal areas in multiple images. The model calculates the abnormal variation coefficient of each abnormal area in each image according to the changes in the abnormal areas in different images, and identifies the temperature anomaly, color unevenness and impurity diffusion in the donkey-hide gelatin production process by analyzing the changes in the abnormal areas between images, thereby effectively capturing the slight quality changes in the donkey-hide gelatin production process and providing detailed data support for subsequent quality optimization.

[0079] Reference Figure 1 S40 in which S40 is applied to a donkey-hide gelatin abnormality acquisition unit of a donkey-hide gelatin quality detection system based on image recognition, wherein the donkey-hide gelatin abnormality acquisition unit is used to obtain the donkey-hide gelatin abnormality coefficient through multi-parameter fusion according to the first region abnormality variation coefficient, the second region abnormality variation coefficient, the third region abnormality variation coefficient and the fourth region abnormality variation coefficient;

[0080] The donkey-hide gelatin anomaly acquisition unit fuses all the anomaly coefficients to generate an donkey-hide gelatin anomaly coefficient. First, the anomaly coefficients of color, uniformity, impurities and bubbles are integrated into the preliminary anomaly assessment results, and then further fused with the anomaly coefficients generated in the first stage and the current stage to obtain the donkey-hide gelatin anomaly coefficient.

[0081] The fusion process combines the anomaly detection results of multiple stages by assigning different weights to form a global quality evaluation index. The anomaly coefficient of donkey-hide gelatin is ultimately used to determine whether the donkey-hide gelatin product meets the production standards, ensuring that the produced donkey-hide gelatin meets consistency and high standards in appearance, internal structure and quality. The multi-step processing and multi-dimensional analysis methods of this model provide strong data support and guarantee for quality control in donkey-hide gelatin production.

[0082] The donkey-hide gelatin abnormal coefficient includes the abnormal variation coefficient of the first region, the abnormal variation coefficient of the second region, the abnormal variation coefficient of the third region and the abnormal variation coefficient of the fourth region, and the donkey-hide gelatin abnormal coefficient is obtained by multi-parameter fusion. The specific calculation formula of the donkey-hide gelatin abnormal coefficient is:

[0083] E=ω1E1+ω2E2+ω3E3+ω4E4;

[0084] Among them, ω1 is the weight of the abnormal change coefficient of the first area, E1 is the abnormal change coefficient of the first area, ω2 is the weight of the abnormal change coefficient of the second area, E2 is the abnormal change coefficient of the second area, ω3 is the weight of the abnormal change coefficient of the third area, E3 is the abnormal change coefficient of the third area, ω4 is the weight of the abnormal change coefficient of the fourth area, and E4 is the abnormal change coefficient of the fourth area.

[0085] In this embodiment, the donkey-hide gelatin abnormality coefficient is calculated by weighted combination of multiple features. Since the donkey-hide gelatin abnormality coefficient is a fusion of multiple stages and multi-dimensional features, it not only provides a comprehensive analysis for donkey-hide gelatin quality monitoring, but also combines the key quality control points in the entire production process to ensure the qualification and consistency of the final product.

[0086] Reference Figure 1 S50 in the figure is applied to a donkey-hide gelatin grade acquisition unit of a donkey-hide gelatin quality detection system based on image recognition, and the donkey-hide gelatin grade acquisition unit is used to grade the first donkey-hide gelatin according to the donkey-hide gelatin abnormality coefficient to obtain first-grade donkey-hide gelatin, second-grade donkey-hide gelatin and third-grade donkey-hide gelatin.

[0087] Furthermore, the first donkey-hide gelatin is graded according to the donkey-hide gelatin abnormality coefficient, and the grade classification includes:

[0088] Set the abnormal level threshold set TH = {S1, S2}. When the abnormal coefficient of donkey-hide gelatin is less than S1, the corresponding first donkey-hide gelatin grade is first-grade donkey-hide gelatin, which is the highest quality grade, meaning that the product has the least abnormalities in terms of color, uniformity, impurities and bubbles, and the overall quality is close to the ideal state; when the abnormal coefficient of donkey-hide gelatin is in the interval [S1, S2], the corresponding first donkey-hide gelatin grade is second-grade donkey-hide gelatin; although this type of donkey-hide gelatin has a certain degree of abnormality, it still meets most quality standards and is suitable for general market demand; when the abnormal coefficient of donkey-hide gelatin is greater than S2, the corresponding first donkey-hide gelatin grade is third-grade donkey-hide gelatin; indicating that the product has more significant quality problems, such as more impurities, obvious bubbles or uneven surface, which is suitable for price-sensitive markets; the lower the first donkey-hide gelatin grade, the better the quality of the first donkey-hide gelatin; where S1 = 0.1, S2 = 0.3, the specific classification of donkey-hide gelatin grades is shown in Table 2;

[0089] Table 2 Classification of donkey-hide gelatin grades

[0090]

[0091] Among them, the weight ratio is obtained through training on historical donkey-hide gelatin production data, and ω4>ω3>ω2>ω1.

[0092] In this embodiment, the grading mechanism of the donkey-hide gelatin abnormality coefficient realizes the grading of donkey-hide gelatin of different quality levels. At the same time, the application of the donkey-hide gelatin abnormality coefficient can not only control the production quality, but also provide suitable products for different customer groups, thereby improving the market competitiveness and production efficiency of donkey-hide gelatin products.

[0093] The donkey-hide gelatin quality detection method based on image recognition technology of the present invention has significant practical value in improving the transparency and quality control of donkey-hide gelatin production. The present invention first collects time-series images of each key link in the donkey-hide gelatin production process through a multi-spectral camera, and combines image defect recognition, grayscale processing and thermal map analysis to identify potential quality anomalies in the donkey-hide gelatin production process, wherein quality anomalies include impurities, uneven color and temperature fluctuations. Secondly, the method further analyzes the abnormal areas between the detection images by constructing an abnormal area detection model to obtain the changes in quality anomalies between images. Finally, the abnormal coefficient of donkey-hide gelatin is obtained based on multi-parameter fusion technology, thereby realizing the quality assessment and grading of donkey-hide gelatin quality. Compared with traditional quality detection methods, the donkey-hide gelatin detection method based on image recognition of the present invention not only greatly improves the detection accuracy and efficiency of donkey-hide gelatin, but also provides a scientific basis for the quality determination of donkey-hide gelatin.

[0094] Embodiment 2

[0095] In another embodiment of the present invention, a quality detection system of donkey-hide gelatin based on image recognition is also introduced. Figure 1 and Figure 2 ;

[0096] Identify the production process of donkey-hide gelatin, which includes boiling, filtering, concentrating and cooling and molding;

[0097] An donkey-hide gelatin image acquisition unit, used to acquire a time-series image data set in a production process, wherein the time-series image data set includes a first image, a second image, a third image, a fourth image, and a fifth image;

[0098] A first donkey-hide gelatin model construction unit is used to construct a donkey-hide gelatin image abnormal region recognition model to recognize the time series image data set, and obtain a first image abnormal region, a second image abnormal region, a third image abnormal region, a fourth image abnormal region, and a fifth image abnormal region;

[0099] The second donkey-hide gelatin model construction unit is used to construct a donkey-hide gelatin image abnormal region detection model to analyze the first image abnormal region, the second image abnormal region, the third image abnormal region, the fourth image abnormal region and the fifth image abnormal region to obtain the first region abnormal variation coefficient, the second region abnormal variation coefficient, the third region abnormal variation coefficient and the fourth region abnormal variation coefficient;

[0100] A donkey-hide gelatin abnormality acquisition unit, configured to obtain the donkey-hide gelatin abnormality coefficient through multi-parameter fusion according to the first region abnormality variation coefficient, the second region abnormality variation coefficient, the third region abnormality variation coefficient, and the fourth region abnormality variation coefficient;

[0101] The donkey-hide gelatin grade acquisition unit is used to grade the first donkey-hide gelatin according to the donkey-hide gelatin abnormality coefficient to obtain first-grade donkey-hide gelatin, second-grade donkey-hide gelatin and third-grade donkey-hide gelatin.

[0102] The first donkey-hide gelatin is graded according to the donkey-hide gelatin abnormality coefficient, and the grade classification includes:

[0103] The donkey-hide gelatin abnormal coefficient includes the abnormal variation coefficient of the first region, the abnormal variation coefficient of the second region, the abnormal variation coefficient of the third region and the abnormal variation coefficient of the fourth region, and the donkey-hide gelatin abnormal coefficient is obtained by multi-parameter fusion; the specific calculation formula of the donkey-hide gelatin abnormal coefficient is:

[0104] E=ω1E1+ω2E2+ω3E3+ω4E4;

[0105] Among them, ω1 is the weight of the abnormal variation coefficient of the first area, E1 is the abnormal variation coefficient of the first area, ω2 is the weight of the abnormal variation coefficient of the second area, E2 is the abnormal variation coefficient of the second area, ω3 is the weight of the abnormal variation coefficient of the third area, E3 is the abnormal variation coefficient of the third area, ω4 is the weight of the abnormal variation coefficient of the fourth area, and E4 is the abnormal variation coefficient of the fourth area;

[0106] Set the abnormal level threshold set TH = {S1, S2}. When the abnormal coefficient of the donkey-hide gelatin is less than S1, the corresponding first donkey-hide gelatin level is first-grade donkey-hide gelatin; when the abnormal coefficient of the donkey-hide gelatin is in the interval [S1, S2), the corresponding first donkey-hide gelatin level is second-grade donkey-hide gelatin; when the abnormal coefficient of the donkey-hide gelatin is greater than S2, the corresponding first donkey-hide gelatin level is third-grade donkey-hide gelatin; the lower the first donkey-hide gelatin level, the better the quality of the first donkey-hide gelatin.

[0107] The present invention provides a donkey-hide gelatin quality detection system based on image recognition, thereby improving the quality control capability in the donkey-hide gelatin production process. The present invention first obtains a time-series image data set in the donkey-hide gelatin production process to comprehensively monitor key links such as boiling, filtering, concentration and cooling molding. Secondly, the image abnormal area recognition model is used to identify and analyze features such as impurities, color and temperature in the image. The model not only improves the accuracy of donkey-hide gelatin detection, but also provides a data basis for donkey-hide gelatin quality assessment. By calculating the abnormal variation coefficient of donkey-hide gelatin and grading the quality of donkey-hide gelatin according to the industry standard threshold, the subjectivity and error of manual detection are significantly reduced, ensuring the quality consistency of different grades of donkey-hide gelatin.

[0108] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for detecting donkey-hide gelatin quality based on image recognition, characterized in that: include: Identify the production process of donkey-hide gelatin, which includes boiling, filtering, concentrating and cooling and molding; Acquire a time-series image data set in a production process, wherein the time-series image data set includes a first image, a second image, a third image, a fourth image, and a fifth image; Constructing an abnormal region recognition model for donkey-hide gelatin images to recognize the time series image data set, and obtaining a first image abnormal region, a second image abnormal region, a third image abnormal region, a fourth image abnormal region, and a fifth image abnormal region; Constructing an abnormal region detection model for donkey-hide gelatin images to analyze the first image abnormal region, the second image abnormal region, the third image abnormal region, the fourth image abnormal region, and the fifth image abnormal region to obtain the first region abnormal variation coefficient, the second region abnormal variation coefficient, the third region abnormal variation coefficient, and the fourth region abnormal variation coefficient; The cooled and formed donkey-hide gelatin is divided to obtain the first donkey-hide gelatin; Obtaining the donkey-hide gelatin abnormality coefficient through multi-parameter fusion according to the abnormal variation coefficient of the first region, the abnormal variation coefficient of the second region, the abnormal variation coefficient of the third region, and the abnormal variation coefficient of the fourth region; The first donkey-hide gelatin is graded according to the donkey-hide gelatin abnormality coefficient to obtain first-grade donkey-hide gelatin, second-grade donkey-hide gelatin and third-grade donkey-hide gelatin.

2. The method for detecting donkey-hide gelatin quality based on image recognition according to claim 1, characterized in that: The images in the time series image data set are acquired by a multispectral camera; The first image is an image taken before brewing, the second image includes an image after brewing and before filtering, the third image includes an image after filtering and before concentration, the fourth image includes an image after concentration and before cooling and molding, and the fifth image is an image after cooling and molding.

3. The method for detecting donkey-hide gelatin quality based on image recognition according to claim 1, characterized in that: The abnormal area recognition model of donkey-hide gelatin image includes an image defect module, an image grayscale defect module, an image thermal defect analysis module, an image defect area fusion module and an abnormal area output module; The image defect module obtains a first image defect by identifying the image surface; The image grayscale defect module obtains a grayscale image by grayscale processing the image; and obtains a second image defect according to the grayscale image; The image thermal defect analysis module obtains a third image defect according to the temperature uniformity by acquiring a thermal map of the image; The image defect area fusion module determines abnormal areas in the first image, the second image, the third image, the fourth image, and the fifth image according to the first image defect, the second image defect, and the third image defect; The abnormal region output module marks and outputs abnormal regions in the first image, the second image, the third image, the fourth image, and the fifth image.

4. The method for detecting donkey-hide gelatin quality based on image recognition according to claim 3, characterized in that: The image defect module is used to identify impurities in the donkey-hide gelatin production process; the impurities are hair, grease, incompletely dissolved colloids and foam scum; The image grayscale module is used to identify the uniformity of color in the donkey-hide gelatin production process; The image thermal defect analysis module is used for temperature abnormality areas of the third image, the fourth image and the fifth image before and after high-temperature concentration.

5. The method for detecting donkey-hide gelatin quality based on image recognition according to claim 1, characterized in that: The abnormal area detection model of donkey-hide gelatin image includes a first donkey-hide gelatin impurity abnormality detection module, a second donkey-hide gelatin impurity abnormality detection module, a third donkey-hide gelatin impurity abnormality detection module and a fourth donkey-hide gelatin impurity abnormality detection module; The first donkey-hide gelatin impurity anomaly detection module is used to analyze the first image abnormal area and the second image abnormal area to obtain the first donkey-hide gelatin impurity anomaly, which includes the change in the number of abnormal impurities, the diffusion range and the regional transformation; and the first regional abnormal change coefficient is obtained based on the first donkey-hide gelatin impurity anomaly.

6. The method for detecting donkey-hide gelatin quality based on image recognition according to claim 5, characterized in that: The second donkey-hide gelatin impurity abnormality detection module is used to analyze the abnormal area of ​​the second image and the abnormal area of ​​the third image to obtain the second donkey-hide gelatin impurity abnormality, wherein the second donkey-hide gelatin impurity abnormality includes the change in the number of abnormal impurities, the diffusion range and the regional transformation; and obtain the second regional abnormality change coefficient according to the second donkey-hide gelatin impurity abnormality; The third donkey-hide gelatin impurity anomaly detection module is used to analyze the third image abnormal area and the fourth image abnormal area to obtain the third donkey-hide gelatin impurity anomaly, wherein the third donkey-hide gelatin impurity anomaly includes temperature anomaly, color anomaly, change in the number of abnormal impurities, diffusion range and regional change; and obtain the third regional abnormal change coefficient according to the third donkey-hide gelatin impurity anomaly; The fourth donkey-hide gelatin impurity anomaly detection module is used to analyze the fourth image abnormal area and the fifth image abnormal area to obtain the fourth donkey-hide gelatin impurity anomaly, and the fourth donkey-hide gelatin impurity anomaly includes temperature anomaly, color anomaly, change in the number of abnormal impurities, diffusion range and regional change; the fourth region abnormal change coefficient is obtained based on the fourth donkey-hide gelatin impurity anomaly.

7. The method for detecting donkey-hide gelatin quality based on image recognition according to claim 1, characterized in that: The donkey-hide gelatin abnormal coefficient includes the abnormal variation coefficient of the first region, the abnormal variation coefficient of the second region, the abnormal variation coefficient of the third region and the abnormal variation coefficient of the fourth region, and the donkey-hide gelatin abnormal coefficient is obtained by multi-parameter fusion; the specific calculation formula of the donkey-hide gelatin abnormal coefficient is: E=ω1E1+ω2E2+ω3E3+ω4E4; Among them, ω1 is the weight of the abnormal variation coefficient of the first area, E1 is the abnormal variation coefficient of the first area, ω2 is the weight of the abnormal variation coefficient of the second area, E2 is the abnormal variation coefficient of the second area, ω3 is the weight of the abnormal variation coefficient of the third area, E3 is the abnormal variation coefficient of the third area, ω4 is the weight of the abnormal variation coefficient of the fourth area, and E4 is the abnormal variation coefficient of the fourth area; The first donkey-hide gelatin is graded according to the donkey-hide gelatin abnormality coefficient, and the grade classification includes: Set the abnormal level threshold set TH = {S1, S2}. When the abnormal coefficient of the donkey-hide gelatin is less than S1, the corresponding first donkey-hide gelatin level is first-grade donkey-hide gelatin; when the abnormal coefficient of the donkey-hide gelatin is in the interval [S1, S2], the corresponding first donkey-hide gelatin level is second-grade donkey-hide gelatin; when the abnormal coefficient of the donkey-hide gelatin is greater than S2, the corresponding first donkey-hide gelatin level is third-grade donkey-hide gelatin; the lower the first donkey-hide gelatin level, the better the quality of the first donkey-hide gelatin.

8. A donkey-hide gelatin quality detection system based on image recognition, characterized in that: include: Identify the production process of donkey-hide gelatin, which includes boiling, filtering, concentrating and cooling and molding; An donkey-hide gelatin image acquisition unit, used to acquire a time-series image data set in a production process, wherein the time-series image data set includes a first image, a second image, a third image, a fourth image, and a fifth image; A first donkey-hide gelatin model construction unit is used to construct a donkey-hide gelatin image abnormal region recognition model to recognize the time series image data set, and obtain a first image abnormal region, a second image abnormal region, a third image abnormal region, a fourth image abnormal region, and a fifth image abnormal region; The second donkey-hide gelatin model construction unit is used to construct a donkey-hide gelatin image abnormal region detection model to analyze the first image abnormal region, the second image abnormal region, the third image abnormal region, the fourth image abnormal region and the fifth image abnormal region to obtain the first region abnormal variation coefficient, the second region abnormal variation coefficient, the third region abnormal variation coefficient and the fourth region abnormal variation coefficient; A donkey-hide gelatin abnormality acquisition unit, configured to obtain the donkey-hide gelatin abnormality coefficient through multi-parameter fusion according to the first region abnormality variation coefficient, the second region abnormality variation coefficient, the third region abnormality variation coefficient, and the fourth region abnormality variation coefficient; The donkey-hide gelatin grade acquisition unit is used to grade the first donkey-hide gelatin according to the donkey-hide gelatin abnormality coefficient to obtain first-grade donkey-hide gelatin, second-grade donkey-hide gelatin and third-grade donkey-hide gelatin.

9. The image recognition-based donkey-hide gelatin quality detection system according to claim 8, characterized in that: The abnormal area recognition model of donkey-hide gelatin image includes an image defect module, an image grayscale defect module, an image thermal defect analysis module, an image defect area fusion module and an abnormal area output module.

10. The image recognition-based donkey-hide gelatin quality detection system according to claim 8, characterized in that: The first donkey-hide gelatin is graded according to the donkey-hide gelatin abnormality coefficient, and the grade classification includes: Set the abnormal level threshold set TH = {S1, S2}. When the abnormal coefficient of the donkey-hide gelatin is less than S1, the corresponding first donkey-hide gelatin level is first-grade donkey-hide gelatin; when the abnormal coefficient of the donkey-hide gelatin is in the interval [S1, S2], the corresponding first donkey-hide gelatin level is second-grade donkey-hide gelatin; when the abnormal coefficient of the donkey-hide gelatin is greater than S2, the corresponding first donkey-hide gelatin level is third-grade donkey-hide gelatin; the lower the first donkey-hide gelatin level, the better the quality of the first donkey-hide gelatin.

Images