A machine vision-based deer product production monitoring system

Abstract

The present application relates to the technical field of image processing, and more particularly to a machine vision-based deer product production monitoring system, comprising: an image acquisition module; a monitoring setting module configured to determine a monitoring interval length based on a proportion of ossified pixel values to obtain a plurality of monitoring points; a primary determination module configured to determine whether a production process is qualified based on an abnormality coefficient of the monitoring points; a secondary determination module configured to determine an adjusted abnormality coefficient based on a difference degree of sub-regions, adjust the abnormality coefficient based on the difference degree, or analyze a key region to obtain the adjusted abnormality coefficient, and determine whether the production process is qualified based on the adjusted abnormality coefficient; and an abnormality adjustment module configured to adjust a heating rate or a heating temperature based on an abnormality comparison value, and adjust a stirring rate based on a key region proportion under a condition of instability after a first adjustment. The present application can ensure the stability of deer horn quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to a machine vision-based deer product production monitoring system. BACKGROUND

[0002] In the deer product industry, pilose antler slices, which have both high medicinal value and nourishing effects, are one of the core categories. Since pilose antler slices need to be boiled during processing, the heating process in the boiling link plays a decisive role in the quality. However, improper heating often leads to loss of active ingredients, deterioration of shape and color, and other quality risks. The traditional production monitoring method is subjective and highly dependent on manual work, which leads to poor production quality stability and low pass rate of pilose antler slices. Therefore, how to monitor the heating process to improve the quality of pilose antler is a problem to be solved by those skilled in the art.

[0003] Chinese Patent Publication No. CN104127440A discloses a processing technology for pilose antler, which includes: 1) decocting red dates, filtering, and obtaining red date water; 2) placing pilose antler in the red date water, soaking, boiling, then taking out the pilose antler, and draining the pilose antler; and 3) drying the drained pilose antler. However, the above-mentioned scheme has the following problems: lack of real-time monitoring of the quality of pilose antler during heating, inability to actively avoid quality risks caused by improper heating, and inability to ensure the quality stability of pilose antler. SUMMARY

[0004] Therefore, the present application provides a machine vision-based deer product production monitoring system to overcome the problems of lack of real-time monitoring of the quality of pilose antler during heating, inability to actively avoid quality risks caused by improper heating, and inability to ensure the quality stability of pilose antler in the prior art.

[0005] To achieve the above-mentioned purpose, the present application provides a machine vision-based deer product production monitoring system, which comprises:

[0006] An image acquisition module is used to acquire deer product images and infrared images;

[0007] A monitoring setting module is connected to the image acquisition module, used to determine the pixel point category according to the pixel value, and determine the monitoring interval duration according to the proportion of ossification pixel value of the deer product image at the initial moment to obtain a plurality of monitoring points;

[0008] A first determination module is connected to the image acquisition module and the monitoring setting module, used to determine the abnormal coefficient of the monitoring points according to the heat expansion difference of ossification and the color and luster attenuation rate of non-ossification, and initially determine whether the production process is qualified according to the abnormal coefficient of the monitoring points;

[0009] a secondary determination module connected with the primary determination module, configured to determine whether the production process is qualified based on the adjusted abnormality coefficient according to the difference comparison degree or perform key area analysis to obtain the adjusted abnormality coefficient according to the abnormality difference of the sub-area when the production process is qualified in the primary determination;

[0010] an abnormality adjustment module connected with the primary determination module and the secondary determination module, configured to adjust the heating rate or the heating temperature according to the abnormality comparison value under abnormal conditions, and adjust the stirring rate according to the key area proportion under the condition of instability after the first adjustment.

[0011] Further, the monitoring setting module determines the pixel point category according to the pixel value, comprising:

[0012] for a single pixel point in the pilose antler slice region of the pilose product image,

[0013] if the pixel value of the pixel point is in the first preset pixel value range, the pixel point category of the pixel point is the ossification pixel point;

[0014] if the pixel value of the pixel point is in the second preset pixel value range, the pixel point category of the pixel point is the non-ossification pixel point.

[0015] Further, the monitoring setting module determines the monitoring interval duration according to the proportion of the ossification pixel value of the pilose product image at the initial moment;

[0016] the monitoring interval duration and the proportion of the ossification pixel value are in a negative correlation relationship.

[0017] Further, the primary determination module determines whether the production process is qualified according to the abnormality coefficient of the monitoring point, comprising:

[0018] for a single monitoring point,

[0019] if the abnormality coefficient of the monitoring point is greater than or equal to the preset abnormality coefficient, the primary determination of the production process is unqualified;

[0020] if the abnormality coefficient of the monitoring point is less than the preset abnormality coefficient, the primary determination of the production process is qualified;

[0021] the abnormality coefficient is in a positive correlation relationship with the ossification thermal expansion difference and the non-ossification color and luster attenuation rate.

[0022] Further, the secondary determination module is responsive to the sub-area abnormality difference being greater than or equal to the preset sub-area abnormality difference, and adjusts the abnormality coefficient according to the difference comparison degree;

[0023] the increase value of the abnormality coefficient and the difference comparison degree are in a positive correlation relationship.

[0024] Further, the secondary determination module responds to the sub-region abnormality difference being less than a preset sub-region abnormality difference, and performs key region analysis;

[0025] In the key region analysis, the key region is determined according to the bubble abnormality degree or the pixel change value according to the bubble uniformity, the sub-abnormal reference value is determined according to the infrared deviation value and the region characteristic value of the key region, the average value of the sub-abnormal reference values corresponding to each key region is determined as the abnormal reference value, and the abnormal coefficient is adjusted by increasing based on the abnormal reference value;

[0026] The increase value of the abnormal coefficient and the abnormal reference value are in a positive correlation.

[0027] Further, the secondary determination module determines the key region according to the bubble abnormality degree or the pixel change value according to the bubble uniformity, comprising:

[0028] If the bubble uniformity is less than a preset bubble uniformity, the key region is determined according to the bubble abnormality degree;

[0029] If the bubble uniformity is greater than or equal to the preset bubble uniformity, the key region is determined according to the pixel change value.

[0030] Further, the secondary determination module determines the sub-abnormal reference value according to the infrared deviation value and the region characteristic value of the key region;

[0031] The sub-abnormal reference value is in a positive correlation with the infrared deviation value and the region characteristic value.

[0032] Further, the abnormal adjustment module adjusts the heating temperature by decreasing according to the abnormal comparison value;

[0033] The decrease value of the heating temperature and the abnormal comparison value are in a positive correlation.

[0034] Further, the abnormal adjustment module adjusts the stirring rate by increasing according to the key region proportion under the condition of one-time adjustment instability;

[0035] The increase value of the stirring rate and the key region proportion are in a positive correlation.

[0036] Compared with the prior art, the beneficial effects of the present application are that in the technical scheme of the present application, the bone pixel value proportion effectively reflects the component distribution difference of pilose antler tablets, and then the monitoring interval length is determined according to the bone pixel value proportion, which is beneficial to realize the accurate matching of component risk and monitoring frequency, avoid the problem of poor monitoring pertinence in traditional fixed interval monitoring, and is beneficial to improve the monitoring accuracy and efficiency, and then improve the stability of pilose antler tablet production quality.

[0037] Further, in the present application, the quality change state of the pilose antler slice in the heating process is effectively reflected by the bone heat expansion difference degree and the non-bone color attenuation rate, and then the abnormal coefficient is determined according to the bone heat expansion difference degree and the non-bone color attenuation rate, the comprehensive risk degree of the heating process deviating from the historical qualified benchmark is effectively reflected by the abnormal coefficient, and then whether the production process is qualified is determined according to the abnormal coefficient, which is beneficial to reduce the human judgment error and improve the stability and consistency of the pilose antler slice production quality.

[0038] Further, in the present application, the color and luster uniformity of different sub-regions in the heating process of the pilose antler slice is effectively reflected by the sub-region abnormal difference degree, and then the abnormal coefficient is adjusted or the key region analysis is carried out according to the difference comparison degree adaptively according to the sub-region abnormal difference degree, so that the determination of the adjusted abnormal coefficient is more in line with the actual application scene, the misjudgment risk caused by a single determination standard is avoided, and the stability of the pilose antler slice production quality is ensured.

[0039] Further, in the present application, under abnormal conditions, the temperature rise rate or the heating temperature is adjusted according to the abnormal comparison value, which is beneficial to curb the irreversible damage of temperature abnormality to the quality of the pilose antler slice, the temperature parameter is adjusted by accurately matching the abnormal severity, the active ingredient is avoided to be degraded and the color and luster are abnormal due to too high temperature, or the local temperature difference is intensified due to too fast temperature rise, the abnormal expansion is blocked from the core variable level, and under the condition of one-time adjustment instability, the stirring rate is adjusted according to the key region proportion, which is beneficial to solve the derived problem that the macro temperature is qualified but the micro heating is uneven, and the local quality abnormality caused by uneven heating can be avoided. BRIEF DESCRIPTION OF DRAWINGS

[0040] Fig. 1 It is a module connection diagram of the pilose antler product production monitoring system based on machine vision of the present application;

[0041] Fig. 2 It is a flowchart of determining the pixel point category according to the pixel value of the present application;

[0042] Fig. 3 It is a flowchart of initially determining whether the production process is qualified according to the abnormal coefficient of the monitoring point of the present application;

[0043] Fig. 4 It is a flowchart of determining the abnormal coefficient adjustment or key region analysis according to the difference comparison degree according to the sub-region abnormal difference degree of the present application. DETAILED DESCRIPTION

[0044] In order to make the purpose and advantages of the present application more clear and obvious, the present application is further described below in combination with examples; it should be understood that the specific examples described herein are only used to explain the present application, and are not used to limit the present application.

[0045] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. It should be understood that the embodiments are only used to explain the technical principles of the present application, and are not intended to limit the protection scope of the present application.

[0046] It should be noted that, in the description of the present application, the terms indicating the direction or position relationship of "up", "down", "left", "right", "inner", "outer" and the like are based on the direction or position relationship shown in the drawings, which is only for the convenience of description, and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application.

[0047] Please refer to Figs. 1 to 4 The present application provides a machine vision-based deer product production monitoring system, which comprises:

[0048] An image acquisition module is configured to acquire deer product images and infrared images.

[0049] A monitoring setting module is connected to the image acquisition module and configured to determine pixel point categories according to pixel values, and determine a monitoring interval duration according to a proportion of ossification pixel values in the deer product images at an initial time to obtain a plurality of monitoring points.

[0050] A primary determination module is connected to the image acquisition module and the monitoring setting module, and configured to determine an abnormality coefficient of the monitoring points according to a bone heat expansion difference and a non-ossification color fading rate, and determine whether the production process is qualified according to the abnormality coefficient of the monitoring points.

[0051] A secondary determination module is connected to the primary determination module, and configured to, when the production process is determined to be qualified in the primary determination, determine an adjusted abnormality coefficient according to a sub-region abnormality difference and a difference comparison degree, or perform key region analysis to obtain the adjusted abnormality coefficient according to the difference comparison degree, and determine whether the production process is qualified based on the adjusted abnormality coefficient.

[0052] An abnormality adjustment module is connected to the primary determination module and the secondary determination module, and configured to, under abnormal conditions, adjust a heating rate or a heating temperature according to an abnormality comparison value, and, under a once-adjusted instability condition, adjust a stirring rate according to a key region proportion.

[0053] The application scenario of the present application is monitoring in the heating process of pilose antler slices, and the present application correspondingly provides a plurality of historical records, each of which records at least one of the following: the boneification thermal expansion coefficient, the non-boneification color fading rate, the sub-region abnormality difference, and the abnormal reference value in the historical process of monitoring in the heating process of pilose antler slices, and each of the historical records correspondingly has a qualified mark, which records whether the process of monitoring in the heating process of pilose antler slices meets the user's demand, and the qualified mark can be recorded manually, and it can be understood that the user can determine whether the process of monitoring in the heating process of pilose antler slices meets the demand according to a self-set index, which can be but is not limited to a slice shape integrity rate, and details are not described herein, wherein, after the pilose antler slices are heated, 100 pilose antler slices are randomly selected, and the slice shape integrity rate = the number of pilose antler slices without breakage and edge damage / 100.

[0054] The heating process of the pilose antler slices includes: placing the pilose antler slices in a single layer on a pure water boiling pot at room temperature, slowly heating to 80 DEG C at a heating rate of 2 DEG C / min, and keeping the temperature at 80 DEG C for 30 min, using a stirrer for stirring, the paddle of the stirrer is installed at a height of 12 cm from the bottom of the pot to avoid directly hitting the pilose antler slices, the stirring rate is 30 rmp, and the specific model of the stirrer is not limited, and the user can select it according to actual needs;

[0055] The pilose antler product image is an image taken by a camera at a height of 1.5 m above the boiling pot after denoising and grayscale processing, the infrared thermal imager and the camera are fixed on the same bracket to ensure that the shooting angles of the two are completely consistent, and the infrared image is enlarged to the same pixel size as the pilose antler product image to obtain a preprocessed infrared image, the method for enlarging the infrared image to the same pixel size as the pilose antler product image includes but is not limited to MATLAB and OpenCV, and the user can select it according to actual needs, and the specific method is not limited;

[0056] The abnormal conditions include that the production process is determined to be unqualified for the first time and the production process is determined to be unqualified for the second time.

[0057] Specifically, the monitoring setting module determines the pixel point category according to the pixel value, including:

[0058] For a single pixel point in the pilose antler slice region of the pilose antler product image,

[0059] If the pixel value of the pixel point is in a first preset pixel value range, the pixel point category of the pixel point is a boneification pixel point;

[0060] If the pixel value of the pixel point is in a second preset pixel value range, the pixel point category of the pixel point is a non-boneification pixel point.

[0061] The pilose antler piece region is a pixel region of the pilose antler piece itself in the pilose deer product image, and the pilose antler piece region in the pilose deer product image is recognized by OpenCV;

[0062] It should be noted that the first preset pixel value corresponding to the ossified pixel point in the pilose deer product image corresponding to different monitoring points is different, and the second preset pixel value corresponding to the non-ossified pixel point in the pilose deer product image corresponding to different monitoring points is also different;

[0063] For the pilose deer product image corresponding to a single monitoring point, any pixel value in the first preset pixel value range is less than or equal to the first preset pixel value, and any pixel value in the second preset pixel value range is greater than or equal to the second preset pixel value;

[0064] The first preset pixel value corresponding to a single monitoring point is less than the second preset pixel value;

[0065] The values of the first preset pixel value and the second preset pixel value corresponding to a single monitoring point can be determined by a user according to an actual application scenario. The greater the strictness of the user in determining the pixel category, the smaller the value of the first preset pixel value and the greater the value of the second preset pixel value. A maximum value of pixel values corresponding to each ossified pixel point in the pilose deer product image corresponding to the monitoring point in the historical record with the same time length as the time length from the initial time to the monitoring point and meeting the user's demand is recorded as the first preset pixel value, and a minimum value of pixel values corresponding to each non-ossified pixel point in the pilose deer product image corresponding to the monitoring point in the historical record with the same time length as the time length from the initial time to the monitoring point and meeting the user's demand is recorded as the second preset pixel value.

[0066] Specifically, the monitoring setting module determines the monitoring interval time length according to the ossified pixel value proportion of the pilose deer product image at the initial time;

[0067] The monitoring interval time length and the ossified pixel value proportion are in a negative correlation relationship.

[0068] The initial time is a time when the pilose antler pieces are placed in a pure water boiler at room temperature and heating is not started;

[0069] The ossified pixel value proportion = the number of ossified pixel points in the pilose antler piece region of the pilose deer product image at the initial time / the total amount of ossified pixel points and non-ossified pixel points in the pilose antler piece region of the pilose deer product image at the initial time;

[0070] The monitoring interval time length = t-t0×ossified pixel value proportion, t is 10 min, and t0 is 5 min;

[0071] Taking the initial time as a starting point, an interval point is set every monitoring interval time length until the heating is completed, and each interval point set is recorded as a monitoring point.

[0072] Specifically, the primary determination module determines whether the production process is qualified according to the abnormality coefficient of the monitoring point, comprising:

[0073] For a single monitoring point,

[0074] If the abnormality coefficient of the monitoring point is greater than or equal to the preset abnormality coefficient, the primary determination module determines that the production process is unqualified;

[0075] If the abnormality coefficient of the monitoring point is less than the preset abnormality coefficient, the primary determination module determines that the production process is qualified;

[0076] The abnormality coefficient is positively correlated with the bone heat expansion difference and the non-bone color fading rate.

[0077] The bone heat expansion difference corresponding to a single monitoring point = | bone heat expansion coefficient - average value of bone heat expansion coefficients of each monitoring point in historical records that meet user requirements and are determined to be qualified by secondary determination|.

[0078] The bone heat expansion coefficient corresponding to a single monitoring point = (number of bone pixels in the antler slice area in the image of the deer product corresponding to the monitoring point - number of bone pixels in the antler slice area in the image of the deer product corresponding to the initial time) / time length from the monitoring point to the initial time;

[0079] The non-bone color fading rate corresponding to a single monitoring point = (a1-a2) / time length from the monitoring point to the initial time, the unit of the time length from the monitoring point to the initial time is min, the average value of pixel values corresponding to each non-bone pixel in the antler slice area in the image of the deer product corresponding to the initial time is denoted as a1, and the average value of pixel values corresponding to each non-bone pixel in the antler slice area in the image of the deer product corresponding to the monitoring point is denoted as a2.

[0080] The abnormality coefficient corresponding to a single monitoring point is y0, y0 = (bone heat expansion difference corresponding to the monitoring point / preset bone heat expansion difference) x first weight coefficient + (non-bone color fading rate corresponding to the monitoring point / preset non-bone color fading rate) x second weight coefficient.

[0081] The first weight coefficient is 0.4, the second weight coefficient is 0.6, the preset ossification heat expansion difference degree and the preset non-ossification color fading rate are determined according to the actual application scene, the greater the user's demand for improving the accuracy of the heating process quality stability, the smaller the preset ossification heat expansion difference degree and the preset non-ossification color fading rate, a method for determining the preset ossification heat expansion difference degree and the preset non-ossification color fading rate is provided, the average value of the ossification heat expansion difference degree corresponding to the historical record meeting the user's demand and the average value of the non-ossification color fading rate are detected, which are respectively recorded as the preset ossification heat expansion difference degree and the preset non-ossification color fading rate;

[0082] The preset abnormality coefficient is determined according to the actual application scene, the greater the user's demand for improving the accuracy of the abnormality monitoring, the smaller the preset abnormality coefficient, and a method for determining the preset abnormality coefficient is provided, and the preset abnormality coefficient is 0.5.

[0083] It can be understood that the ossification area is the supporting structure of the pilose antler slice, and if the ossification heat expansion difference degree is large, it means that the ossification area may be over-expanded, cracked or deformed during the heating process. The non-ossification area of the pilose antler slice is rich in active ingredients such as proteins and polypeptides, and the color and component retention degree are strongly related: the higher the non-ossification color fading rate, the more likely it is that the active ingredients are degraded, oxidized or lost during heating. Therefore, the abnormality coefficient determined by the ossification heat expansion difference degree and the non-ossification color fading rate can reflect the risk degree of the pilose antler slice quality deviating from the historical qualified benchmark during the heating process.

[0084] Specifically, the secondary determination module increases the abnormality coefficient according to the difference comparison degree in response to the sub-region abnormality difference degree being greater than or equal to the preset sub-region abnormality difference degree.

[0085] The increase value of the abnormality coefficient and the difference comparison degree are in a positive correlation relationship.

[0086] Among them, for the pilose antler image corresponding to a single monitoring point, a plurality of rectangular regions with the same area and adjacent to each other are divided, the rectangular region overlapping with the pilose antler slice region in the divided rectangular region is recorded as a sub-region, the sub-region abnormality difference degree is the standard deviation of the average value of the pixels corresponding to each sub-region, and the average value of the pixel values corresponding to each pixel point in the pilose antler slice region in a single sub-region;

[0087] The preset sub-region abnormality difference degree is determined according to the actual application scene, the greater the user's demand for improving the monitoring accuracy, the smaller the preset sub-region abnormality difference degree, and a method for determining the preset sub-region abnormality difference degree is provided, and the average value of the sub-region abnormality difference degrees of each monitoring point in the historical record meeting the user's demand and the secondary determination production process is recorded as the preset sub-region abnormality difference degree.

[0088] The difference comparison degree = the sub-region abnormal difference degree - the preset sub-region abnormal difference degree.

[0089] The increase value of the abnormal coefficient = y0 x (the sub-region abnormal difference degree - the preset sub-region abnormal difference degree) / the preset sub-region abnormal difference degree.

[0090] The adjusted abnormal coefficient = the increase value of the abnormal coefficient + y0.

[0091] Specifically, the secondary determination module responds to the sub-region abnormal difference degree being less than the preset sub-region abnormal difference degree, and then performs key region analysis.

[0092] In the key region analysis, the key region is determined according to the bubble uniformity or the pixel change value, the sub-abnormal reference value is determined according to the infrared deviation value and the region representation value of the key region, the abnormal reference value is determined based on the average value of the sub-abnormal reference values corresponding to each key region, and the abnormal coefficient is adjusted based on the abnormal reference value.

[0093] The increase value of the abnormal coefficient and the abnormal reference value are in a positive correlation.

[0094] Wherein, the bubble uniformity corresponding to a single monitoring point = 1 / (the standard deviation of the bubble reference values corresponding to each sub-region in the image of the deer product corresponding to the monitoring point + 1), the bubbles in the cooking pot region and each sub-region are identified by OpenCV, which is a common technical means for those skilled in the art, and will not be described in detail, and the cooking pot region is the pixel range corresponding to the cooking pot in the image of the deer product.

[0095] The bubble reference value corresponding to a single sub-region = the number of bubbles corresponding to the sub-region / the area of the sub-region overlapping with the cooking pot region; the number of bubbles corresponding to a single sub-region is the number of bubbles in the sub-region.

[0096] The bubble abnormality degree corresponding to a single sub-region = | the bubble reference value corresponding to the sub-region - the average value of the bubble reference values corresponding to each sub-region | / (the average value of the bubble reference values corresponding to each sub-region + 1).

[0097] The pixel change value corresponding to a single sub-region = | the standard deviation of the pixel values corresponding to each pixel point in the deer horn slice region in the sub-region - the standard deviation of the pixel values corresponding to each pixel point in the deer horn slice region in the image of the deer product |.

[0098] The increase value of the abnormal coefficient = y0 x (the abnormal reference value / the average value of the abnormal reference values corresponding to the historical records that can meet the user's demand).

[0099] The adjusted abnormal coefficient = the increase value of the abnormal coefficient + y0.

[0100] If the adjustment abnormality coefficient is greater than or equal to the preset abnormality coefficient, the secondary determination module determines that the production process is unqualified;

[0101] If the adjustment abnormality coefficient is less than the preset abnormality coefficient, the secondary determination module determines that the production process is qualified;

[0102] The abnormality reference value corresponding to the single monitoring point is an average value of the sub-abnormality reference values corresponding to the key regions in the image of the deer product corresponding to the monitoring point.

[0103] It can be understood that the sub-region abnormality difference degree effectively reflects the color difference degree of the deer horn slices in different sub-regions, and when the sub-region abnormality difference degree is greater than or equal to the preset sub-region abnormality difference degree, it indicates that the color difference degree of the deer horn slices in different sub-regions is large, so the difference comparison degree is adjusted according to the abnormality coefficient;

[0104] When the sub-region abnormality difference degree is less than the preset sub-region abnormality difference degree, it indicates that the color difference degree of the deer horn slices in different sub-regions is small, and the key region analysis is performed, that is, even if the color has not yet shown significant differences, potential risks can also be identified in advance through bubble abnormalities, temperature deviations, etc.

[0105] Specifically, the secondary determination module determines the key region according to the bubble uniformity, and determines the key region according to the bubble abnormality degree or the pixel change value, comprising:

[0106] If the bubble uniformity is less than the preset bubble uniformity, the key region is determined according to the bubble abnormality degree;

[0107] If the bubble uniformity is greater than or equal to the preset bubble uniformity, the key region is determined according to the pixel change value.

[0108] The value of the preset bubble uniformity can be determined by the user according to the actual application scene, the greater the value of the preset bubble uniformity, the greater the user's demand for determining the key region according to the bubble abnormality degree, and a value method of the preset bubble uniformity is provided, the average value of the bubble uniformity corresponding to the historical record that can meet the user's demand is recorded as the preset bubble uniformity;

[0109] When the key region is determined according to the bubble abnormality degree, the sub-region with a bubble abnormality degree greater than the preset bubble abnormality degree is recorded as the key region;

[0110] When the key region is determined according to the pixel change value, the sub-region with a pixel change value greater than the preset pixel change value is recorded as the key region;

[0111] The preset bubble abnormality degree and the preset pixel change value can be determined by the user according to the actual application scene, and the smaller the preset bubble abnormality degree and the preset pixel change value, the greater the user's demand for improving the monitoring accuracy. A method for determining the preset bubble abnormality degree and the preset pixel change value is provided, and the average value of the bubble abnormality degree corresponding to each key area in the historical record of the key area determined according to the bubble abnormality degree is recorded as the preset bubble abnormality degree. The average value of the pixel change value corresponding to each key area in the historical record of the key area determined according to the pixel change value is recorded as the preset pixel change value.

[0112] Specifically, the secondary determination module determines a sub-abnormal reference value according to the infrared deviation value of the key area and the area representation value;

[0113] The sub-abnormal reference value is positively correlated with the infrared deviation value and the area representation value.

[0114] Wherein, for the deer product image and the infrared image of a single monitoring point, the infrared reference value of a single sub-area at the monitoring point is the average value of the pixel values of each pixel point in the area in the preprocessed infrared image which has the same coordinates and size as the sub-area;

[0115] The infrared deviation value of a single key area at a single monitoring point = | the infrared reference value of the key area at the monitoring point - the average value of the infrared reference values of each sub-area at the monitoring point |;

[0116] The sub-abnormal reference value = the infrared deviation value / the preset infrared deviation value + the area representation value / the preset area representation value;

[0117] The area representation value corresponding to a single key area = the bubble abnormality degree / the preset bubble abnormality degree + the pixel change value / the preset pixel abnormality degree;

[0118] The preset infrared deviation value and the preset area representation value can be determined by the user according to the actual application scene, and the smaller the preset infrared deviation value and the preset area representation value, the greater the user's demand for improving the monitoring accuracy of the heating process. A method for determining the preset infrared deviation value and the preset area representation value is provided, and the average value of the infrared deviation value corresponding to the historical record that can meet the user's demand is recorded as the preset infrared deviation value, and the preset area representation value is 1.4;

[0119] Specifically, the abnormality adjustment module adjusts the heating rate or the heating temperature to be reduced according to the abnormality comparison value;

[0120] The reduction value of the heating rate is positively correlated with the abnormality comparison value, and the reduction value of the heating temperature is positively correlated with the abnormality comparison value.

[0121] It should be noted that for a single monitoring point, if the heating temperature reaches over 80℃ from the initial time to the whole process of the monitoring point, the heating temperature is adjusted for reduction, and if the heating temperature does not reach over 80℃, the heating temperature is adjusted for reduction; the heating temperature is the water temperature of any point in the pot, which is measured by a temperature sensor;

[0122] The abnormal comparison value is y-preset abnormal coefficient;

[0123] If the initial determination of the production process is unqualified, y is the abnormal coefficient;

[0124] If the secondary determination of the production process is unqualified, y is the adjusted abnormal coefficient;

[0125] The reduction value of the heating temperature is abnormal comparison value / preset abnormal coefficient×heating temperature threshold, and the heating temperature threshold is 10℃;

[0126] The reduction value of the heating temperature is abnormal comparison value / preset abnormal coefficient×heating temperature threshold, and the heating temperature threshold is 10℃;

[0127] It can be understood that if the heating rate is too fast, it will exacerbate the temperature gradient of different sub-regions, further amplifying the difference in color and texture, and if the heating temperature is too high, it may quickly cause the local color of the pilose antler tablet to deepen, the internal water to evaporate rapidly to form a large number of bubbles, at this time, the heating rate or the heating temperature is adjusted preferentially, and by adjusting the heating rate or the heating temperature, the continuous damage of temperature imbalance to the quality of the pilose antler tablet can be directly relieved.

[0128] Specifically, the abnormal adjustment module increases the stirring rate according to the key area ratio under the first adjustment instability condition;

[0129] The increase value of the stirring rate and the key area ratio are in a positive correlation relationship.

[0130] The first adjustment instability condition is that the key area ratio is greater than the preset key area ratio 2 minutes after the reduction adjustment of the heating rate according to the abnormal comparison value;

[0131] The time point 2 minutes after the reduction adjustment of the heating rate according to the abnormal comparison value is recorded as the reference time point;

[0132] The key area ratio is the number of key areas in the image of the deer product taken at the reference time point / the number of sub-regions in the image of the deer product taken at the reference time point;

[0133] The value of the preset key area proportion can be determined by the user according to the actual application scene. The greater the user's demand for improving the production stability, the smaller the value of the preset key area proportion. A value of the preset key area proportion is provided, and the preset key area proportion is 40%.

[0134] The increase value of the stirring rate = the key area proportion / the key area proportion threshold value x the stirring rate threshold value; the key area proportion threshold value is 1, and the ultrasonic oscillation frequency threshold value is 20 rmp.

[0135] It should be noted that if the key area proportion is still greater than the preset key area proportion after the increase adjustment of the stirring rate according to the key area proportion, the heating is stopped to avoid continuous abnormal processing to damage the quality of the deer product.

[0136] It can be understood that by adjusting the heating rate or the heating temperature according to the abnormal comparison value, the heating rate and the heating temperature of the boiling pot have been controlled in a reasonable range. The instability condition of one-time adjustment indicates that the deer horn slices in the boiling pot are unevenly heated, and the more sub-regions with quality abnormalities exist in the image of the deer product, the more serious the uneven heating of the material, and stronger stirring intervention is needed to break the local temperature difference to ensure the stability of the production quality of the deer product.

[0137] So far, the technical solutions of the present application have been described in combination with the preferred embodiments shown in the drawings, but those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical solutions after the changes or replacements will fall within the protection scope of the present application.

Claims

1. A machine vision-based deer product production monitoring system, characterized by, The method comprises the following steps: an image acquisition module is configured to acquire images of deer products and infrared images; a monitoring setting module is connected to the image acquisition module and configured to determine pixel point categories according to pixel values and determine a monitoring interval duration according to a proportion of ossification pixel values in the deer product images at an initial time to obtain a plurality of monitoring points; a first judgment module is connected to the image acquisition module and the monitoring setting module and configured to determine an abnormality coefficient of the monitoring points according to a heat expansion difference of ossification and a color and luster attenuation rate of non-ossification and initially judge whether the production process is qualified according to the abnormality coefficient of the monitoring points; a second judgment module is connected to the first judgment module and configured to, when the production process is initially judged to be qualified, determine a difference comparison degree according to a sub-region abnormality difference, adjust the abnormality coefficient according to the difference comparison degree or perform key region analysis to obtain an adjusted abnormality coefficient, and secondarily judge whether the production process is qualified based on the adjusted abnormality coefficient; an abnormality adjustment module is connected to the first judgment module and the second judgment module and configured to, under abnormal conditions, adjust a temperature rising rate or a heating temperature according to an abnormality comparison value, and, under a condition of instability after a first adjustment, adjust a stirring rate according to a key region proportion.

2. The machine vision-based deer product production monitoring system of claim 1, wherein, The monitoring setting module determines pixel point categories according to pixel values, which comprises: for a single pixel point in a region of deer horn slices in the deer product images, if the pixel value of the pixel point is in a first preset pixel value range, the pixel point category of the pixel point is an ossification pixel point; if the pixel value of the pixel point is in a second preset pixel value range, the pixel point category of the pixel point is a non-ossification pixel point.

3. The machine vision-based deer product production monitoring system of claim 2, wherein, The monitoring setting module determines a monitoring interval duration according to a proportion of ossification pixel values in the deer product images at an initial time. The monitoring interval duration and the proportion of ossification pixel values are in a negative correlation relationship.

4. The machine vision-based deer product production monitoring system of claim 3, wherein, The first judgment module determines whether the production process is qualified according to the abnormality coefficient of the monitoring points, which comprises: for a single monitoring point, if the abnormality coefficient of the monitoring point is greater than or equal to a preset abnormality coefficient, the production process is initially judged to be unqualified; if the abnormality coefficient of the monitoring point is less than the preset abnormality coefficient, the production process is initially judged to be qualified; the abnormality coefficient is in a positive correlation relationship with the heat expansion difference of ossification and the color and luster attenuation rate of non-ossification.

5. The machine vision-based deer product production monitoring system of claim 1, wherein, The second judgment module, in response to a sub-region abnormality difference greater than or equal to a preset sub-region abnormality difference, adjusts the abnormality coefficient according to a difference comparison degree; the increase value of the abnormality coefficient and the difference comparison degree are in a positive correlation relationship.

6. The machine vision-based deer product production monitoring system of claim 1, wherein, The second judgment module, in response to a sub-region abnormality difference less than a preset sub-region abnormality difference, performs key region analysis; in the key region analysis, a key region is determined according to a bubble uniformity or a pixel change value, a sub-abnormality reference value is determined according to an infrared deviation value and a region representation value of the key region, an abnormality reference value is determined based on an average value of the sub-abnormality reference values corresponding to each key region, and the abnormality coefficient is adjusted according to the abnormality reference value; the increase value of the abnormality coefficient and the abnormality reference value are in a positive correlation relationship.

7. The machine vision-based deer product production monitoring system of claim 6, wherein, The secondary determination module determines the key region according to the bubble uniformity, the bubble abnormality, or the pixel change value, comprising: If the bubble uniformity is less than a preset bubble uniformity, the key region is determined according to the bubble abnormality; If the bubble uniformity is greater than or equal to the preset bubble uniformity, the key region is determined according to the pixel change value.

8. The machine vision-based deer product production monitoring system of claim 6, wherein, The secondary determination module determines the sub-abnormal reference value according to the infrared deviation value and the region representation value of the key region; The sub-abnormal reference value is positively correlated with the infrared deviation value and the region representation value.

9. The machine vision-based deer product production monitoring system of claim 1, wherein, The abnormality adjustment module adjusts the heating rate or the heating temperature according to the abnormality comparison value; The decrease value of the heating rate is positively correlated with the abnormality comparison value, and the decrease value of the heating temperature is positively correlated with the abnormality comparison value.

10. The machine vision-based deer product production monitoring system of claim 9, wherein, The abnormality adjustment module adjusts the stirring rate according to the key region proportion under the condition of instability of the primary adjustment; The increase value of the stirring rate is positively correlated with the key region proportion.

Images