Malt hydration degree detection system and method based on image analysis

Abstract

The invention discloses a malt hydration degree detection system and method based on image analysis, and relates to the technical field of malt hydration degree detection. The malt hydration degree detection system based on image analysis comprises a malt image quality evaluation module, a malt hydration evaluation module and a hydration process parameter feedback module. According to the method, the malt image quality evaluation is performed through the acquired image quality parameters of the malt section image, whether the malt section image quality optimization is performed or not is judged, then the malt hydration evaluation is performed according to the malt characteristic parameters in the malt section image, and whether the hydration process parameter optimization is performed or not is judged according to the malt hydration evaluation result. Finally, the malt hydration degree is detected after the detection report is output, the detection precision of the malt hydration degree is improved, and the problem that in the prior art, due to feature extraction errors, the detection precision of the malt hydration degree is low is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of malt hydration degree detection, and in particular to a malt hydration degree detection system and method based on image analysis. Background Art

[0002] Malt hydration is a key factor affecting malt quality, particularly in the production of beverages like beer and whiskey, where hydration directly impacts the brewing process. Malt hydration involves controlling its water content; excessively high or low moisture levels can affect subsequent processing. Therefore, timely and accurate testing of malt hydration is crucial for ensuring product quality. With advances in computer vision and image processing technologies, image analysis-based hydration detection is becoming an important alternative to traditional methods, providing an efficient, accurate, and non-destructive solution for malt production and quality control.

[0003] The existing technology preprocesses and analyzes the malt images taken by the camera, establishes a relationship model between the hydration level and the image features for quantitative analysis, and determines whether to issue an alarm or suggestion based on the quantitative results, thereby achieving rapid and non-destructive detection.

[0004] For example, the invention patent announcement with publication number: CN112924337B discloses a method for evaluating malt solubility, including: malt produced in the soaking-germination step; and adjustment of the subsequent soaking and water-cutting processes based on the soaking index before the end of the dry soaking step; if the malt solubility obtained from the evaluation is not good or does not meet the requirements, the germination step after the soaking step is promptly improved based on the soaking index before the end of each dry soaking step and the requirements for malt solubility.

[0005] For example, a patent application with publication number CN118067766A discloses a method for predicting the filtration performance of beer fermentation liquid, comprising: (1) cutting malt to obtain a cross-section of the malt; (2) scanning the cross-section of the malt with a scanning electron microscope to obtain a backscattered electron image of the cross-section of the malt, and selecting the endosperm and the connected endosperm region where starch granules are concentrated as the area to be tested; (3) using a grid to segment the backscattered electron image of the area to be tested, recording the total number of all grids in the endosperm and the transition part between the endosperm and the endosperm as the total number, and calculating the proportion of the number of grids containing adhered small starch granules, wherein the proportion is positively correlated with the filtration time of the beer fermentation liquid and negatively correlated with the filtration performance of the beer fermentation liquid.

[0006] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] In existing technologies, image quality can be unstable during image acquisition due to changes in lighting conditions (such as light source angle, intensity, and color temperature), equipment vibration, or light source aging. This can lead to low accuracy in image-based feature extraction, which in turn affects the accuracy of hydration level detection. Furthermore, existing methods lack the collaborative analysis of multi-scale features, resulting in incomplete hydration level quantification and low accuracy in malt hydration level detection due to feature extraction errors. Summary of the Invention

[0008] The embodiments of the present application provide a system and method for detecting the hydration level of malt based on image analysis, thereby solving the problem of low detection accuracy of the hydration level of malt caused by feature extraction errors in the prior art and improving the detection accuracy of the hydration level of malt.

[0009] The embodiment of the present application provides a malt hydration degree detection system based on image analysis, comprising: a malt image quality assessment module, a malt hydration assessment module and a hydration process parameter feedback module; wherein the malt image quality assessment module is used to perform malt image quality assessment based on the collected image quality parameters of the malt cross-section image, and determine whether to optimize the malt cross-section image quality; the malt hydration assessment module is used to perform multi-dimensional feature extraction on the malt cross-section image to obtain malt characteristic parameters if the malt cross-section image quality optimization is not performed, perform malt hydration assessment based on the malt characteristic parameters in the malt cross-section image, and determine whether to optimize the hydration process parameters; if the malt cross-section image quality optimization is performed, the malt hydration assessment module is used to perform multi-dimensional feature extraction on the malt cross-section image to obtain malt characteristic parameters; Optimization, multi-dimensional feature extraction is performed on the malt section surface image after the malt section surface image quality is optimized to obtain malt characteristic parameters, malt hydration evaluation is performed according to the malt characteristic parameters in the malt section surface image after the malt section surface image quality is optimized, and whether to perform hydration process parameter optimization is determined according to the result of malt hydration evaluation and the soaking index. The hydration process parameter optimization is used to improve the uniformity of malt water absorption during the soaking process; the hydration process parameter feedback module is used to perform malt hydration degree detection according to the optimized hydration process parameters after outputting the detection report if hydration process parameter optimization is performed, otherwise the malt hydration degree detection is directly performed according to the current hydration process parameters after outputting the detection report.

[0010] The embodiment of the present application provides a method for detecting the hydration degree of malt based on image analysis, comprising the following steps: S1, performing malt image quality evaluation based on image quality parameters of a collected malt cross-section image, and determining whether to optimize the quality of the malt cross-section image; S2, if the malt cross-section image quality optimization is not performed, performing multi-dimensional feature extraction on the malt cross-section image to obtain malt characteristic parameters, performing malt hydration evaluation based on the malt characteristic parameters in the malt cross-section image, and determining whether to optimize the hydration process parameters; if the malt cross-section image quality optimization is performed, performing hydration evaluation on the malt after the malt cross-section image quality optimization is performed. Multi-dimensional feature extraction is performed on the bud cross-section image to obtain malt characteristic parameters, and malt hydration evaluation is performed based on the malt characteristic parameters in the malt cross-section image after the malt cross-section image quality is optimized. Based on the result of the malt hydration evaluation and the soaking index, it is determined whether to perform hydration process parameter optimization, and the hydration process parameter optimization is used to improve the uniformity of water absorption of barley during the soaking process; S3, if the hydration process parameter optimization is performed, the malt hydration degree is detected according to the optimized hydration process parameters after the test report is output; otherwise, the malt hydration degree is directly detected according to the current hydration process parameters after the test report is output.

[0011] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0012] 1. Malt image quality is evaluated by collecting image quality parameters to optimize the malt cross-section image quality. Then, malt hydration is evaluated based on the malt characteristic parameters after the malt cross-section image quality is optimized. Finally, the hydration process parameter optimization is determined based on the malt hydration evaluation results and the malt soaking index. This improves the quality of the collected malt cross-section images and further improves the detection accuracy of the malt hydration degree. This effectively solves the problem of low detection accuracy of the malt hydration degree caused by feature extraction errors in the existing technology.

[0013] 2. The image signal-to-noise ratio of a single malt cross-section image is processed to obtain the image signal-to-noise ratio contrast coefficient, which is then processed according to the image resolution to obtain the image resolution contrast coefficient. Then, the light source brightness contrast coefficient is obtained according to the light source brightness. Finally, the malt image quality assessment compensation value is introduced to process the illumination uniformity coefficient, image signal-to-noise ratio contrast coefficient, image resolution contrast coefficient, and light source brightness contrast coefficient to obtain the malt image quality assessment index, thereby quantitatively evaluating the quality of the malt cross-section image and improving the quality of the malt cross-section image.

[0014] 3. The malt morphological characteristic evaluation index was obtained by processing the average endosperm area ratio, the average cell swelling degree, and the average cell wall rupture coefficient. The malt color characteristic evaluation index was then obtained by processing the average malt brightness, the average malt saturation, and the malt contrast coefficient. Finally, the malt morphological characteristic evaluation index and the malt color characteristic evaluation index were processed to obtain the malt comprehensive hydration index, thereby comprehensively and quantitatively evaluating the hydration degree of the malt, and thereby achieving an improvement in the uniformity of the malt water absorption during the steeping process. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic structural diagram of a malt hydration degree detection system based on image analysis provided in an embodiment of the present application;

[0016] Figure 2 This is a flow chart of the method for detecting the hydration level of malt based on image analysis provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The embodiments of the present application solve the problem of low malt hydration degree detection accuracy caused by feature extraction errors in the prior art by providing a malt hydration degree detection system and method based on image analysis. The malt image quality is evaluated by collecting image quality parameters of the malt cross-section image to determine whether to optimize the malt cross-section image quality. Then, the malt hydration is evaluated based on the malt characteristic parameters in the malt cross-section image after the malt cross-section image quality is optimized. The hydration process parameters are optimized based on the results of the malt hydration evaluation and the soaking index. Finally, after outputting the detection report, subsequent malt hydration degree detection is performed based on the optimized hydration process parameters, thereby improving the detection accuracy of the malt hydration degree.

[0018] The technical solution in the embodiments of the present application is to solve the problem of low detection accuracy of malt hydration degree caused by feature extraction errors. The overall idea is as follows:

[0019] By collecting image quality parameters, malt image quality evaluation is performed to optimize the malt cross-section image quality. Then, malt hydration evaluation is performed based on the malt characteristic parameters after the malt cross-section image quality is optimized. Finally, the malt hydration evaluation results and the soaking index are used to determine whether the hydration process parameters should be optimized, thereby achieving the effect of improving the detection accuracy of the malt hydration degree.

[0020] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0021] like Figure 1As shown, it is a structural schematic diagram of the malt hydration degree detection system based on image analysis provided in an embodiment of the present application. The malt hydration degree detection system based on image analysis provided in an embodiment of the present application includes: a malt image quality assessment module, a malt hydration assessment module and a hydration process parameter feedback module.

[0022] Among them, the malt image quality assessment module is used to collect malt cross-section images through a high-resolution industrial camera and a ring-shaped shadowless light source system, and perform malt image quality assessment based on the image quality parameters of the collected malt cross-section images to determine whether to optimize the malt cross-section image quality. The malt cross-section image is an image of the malt cross-section morphology. The malt cross-section morphology is obtained by obtaining the soaked malt sample through an automated device and cutting it at a uniform speed along the longitudinal direction using precision cutting equipment; the automated device is a device used to automatically obtain malt samples. For example, the sample can be obtained through a specific robotic arm or other automated tools.

[0023] The malt hydration evaluation module is used to perform multi-dimensional feature extraction on the malt cross-section image to obtain malt characteristic parameters if the malt cross-section image quality optimization is not performed, perform malt hydration evaluation based on the malt characteristic parameters in the malt cross-section image, and determine whether to perform hydration process parameter optimization; if the malt cross-section image quality optimization is performed, perform multi-dimensional feature extraction on the malt cross-section image after the malt cross-section image quality optimization to obtain malt characteristic parameters, perform malt hydration evaluation based on the malt characteristic parameters in the malt cross-section image after the malt cross-section image quality optimization, and determine whether to perform hydration process parameter optimization based on the results of the malt hydration evaluation and the soaking index. The hydration process parameter optimization is used to improve the uniformity of malt water absorption during the soaking process.

[0024] The hydration process parameter feedback module is used to detect the malt hydration degree according to the optimized hydration process parameters after outputting the test report if the hydration process parameters are optimized. Otherwise, the malt hydration degree is directly detected according to the current hydration process parameters after outputting the test report; the malt characteristic parameters and hydration level are visually displayed through the test report.

[0025] Before designing a malt hydration degree detection system and method based on image analysis, a database for storing various setting data is established. The database includes but is not limited to a preset image signal-to-noise ratio, a preset image resolution, a malt image quality assessment compensation value, a light source brightness mapping set, and a malt morphology assessment compensation value. Various values therein are directly set by technical personnel. The setting basis of the preset image signal-to-noise ratio can be set according to a preset person. For example, the preset image signal-to-noise ratio is represented by the average value of the historical image signal-to-noise ratio within a historical time period in the database. In addition, various values in the database can be set and fine-tuned by technical personnel according to actual debugging; the historical time period is set according to a preset person, for example, it can be set to one week.

[0026] In this embodiment, during the image acquisition process, changes in lighting conditions (such as light source angle, intensity, color temperature, etc.), equipment vibration, or light source aging may cause unstable image quality, thereby affecting the accuracy of hydration detection. Existing methods mainly rely on macroscopic features (such as color and texture) and lack quantitative analysis of malt microstructure (such as cell wall rupture degree and starch granule morphology), which is closely related to hydration. There is a problem of low accuracy in malt hydration detection due to feature extraction errors.

[0027] In the present application, the annular shadowless light source system avoids shadows in the image through uniform illumination, thereby ensuring that the quality of the captured image is not affected by uneven light sources and ensuring the clarity of image details; through precision cutting equipment, the malt sample is cut at a uniform speed along the longitudinal direction (longitudinal direction) of the malt to ensure the uniformity and accuracy of the cut surface, thereby obtaining a representative cross-sectional image; the malt hydration evaluation module adaptively optimizes the hydration process parameters based on the results of the malt hydration evaluation to ensure the uniformity of the hydration process, thereby improving production efficiency; through the hydration process parameter feedback module, the process can be continuously optimized after each test to provide higher quality data support for subsequent tests; thereby achieving an improvement in the detection accuracy of the malt hydration degree.

[0028] Furthermore, the malt image quality is evaluated based on the acquired image quality parameters of the acquired malt cross-section image. The specific method is as follows:

[0029] C1, if the image signal-to-noise ratio of the single malt cross-section image is less than the preset image signal-to-noise ratio obtained from the preset database, then the image signal-to-noise ratio of the single malt cross-section image is compared with the preset image signal-to-noise ratio obtained from the preset database to obtain an image signal-to-noise ratio comparison coefficient; otherwise, the image signal-to-noise ratio of the single malt cross-section image is compared with the preset image signal-to-noise ratio obtained from the preset database to obtain an image signal-to-noise ratio comparison coefficient; the specific restriction expression of the image signal-to-noise ratio comparison coefficient is:

[0030]

[0031] Wherein, ZAO represents the image signal-to-noise ratio of the malt cross-section image, which is obtained by performing a ratio operation on the average brightness of all pixels in the initial malt cross-section image and the standard deviation of the brightness; ZAO0 represents the preset image signal-to-noise ratio, which is set according to the preset personnel, for example, by the average signal-to-noise ratio of historical images in a historical time period in a preset database.

[0032] C2, if the image resolution of the single malt cross-section image is less than the preset image resolution obtained from the preset database, then the image resolution of the single malt cross-section image is compared with the preset image resolution obtained from the preset database to obtain an image resolution comparison coefficient; otherwise, the image resolution of the single malt cross-section image is compared with the preset image resolution obtained from the preset database to obtain an image resolution comparison coefficient; the specific restriction expression of the image resolution comparison coefficient is:

[0033]

[0034] Wherein, FEB represents the image resolution of the malt cross-section image. The Sobel operator is used to calculate the gradients of the image in the horizontal and vertical directions. Then, the square sum of the horizontal and vertical gradients is performed, and the square root operation is performed to obtain the gradient amplitude of each pixel. Finally, it is expressed as the average value of the gradient amplitudes of all pixels in the image. FEB0 represents the preset image resolution, which is set according to the preset personnel. For example, it is expressed by the average value of the historical image resolutions in the historical time period in the preset database.

[0035] C3, performs relative deviation processing based on the light source brightness and the preset image resolution obtained from the preset database to obtain the light source brightness contrast coefficient, that is, Where GYL represents the brightness of the light source when collecting the malt cross-section image, which is obtained by directly measuring the actual brightness of the light source using a illuminometer; where GYL0 represents the preset light source brightness, which is set according to the preset personnel, for example, by the average value of the historical light source brightness within a historical time period in a preset database.

[0036] C4, introduces the malt image quality assessment compensation value to perform assignment coupling processing on the illumination uniformity coefficient, image signal-to-noise ratio contrast coefficient, image resolution contrast coefficient and light source brightness contrast coefficient to obtain the malt image quality assessment index. The malt image quality assessment compensation value includes the first malt image quality assessment compensation value, the second malt image quality assessment compensation value, the third malt image quality assessment compensation value and the fourth malt image quality assessment compensation value. The malt image quality assessment index is used to quantitatively evaluate the quality of the malt cross-section image; the illumination uniformity coefficient is obtained by converting the initial malt cross-section image into a grayscale image, performing block processing to obtain the average brightness value of each image block, and finally performing a ratio operation on the average of all average brightness values and the standard deviation of all average brightness values.

[0037] The malt image quality assessment compensation values involved are obtained from a preset database. The first malt image quality assessment compensation value represents the degree of influence of the illumination uniformity coefficient on the malt image quality assessment index. The second malt image quality assessment compensation value represents the degree of influence of the light source brightness on the malt image quality assessment index. The third malt image quality assessment compensation value represents the degree of influence of the image signal-to-noise ratio on the malt image quality assessment index. The fourth malt image quality assessment compensation value represents the degree of influence of the image resolution on the malt image quality assessment index. The sum of the four is 1. For example, the illumination uniformity coefficient and the preset first malt image quality assessment compensation value form an illumination uniformity coefficient mapping set. The real-time illumination uniformity coefficient is input into the illumination uniformity coefficient mapping set to obtain the corresponding The first malt image quality assessment compensation value; the light source brightness and the preset second malt image quality assessment compensation value form a light source brightness mapping set, and the real-time light source brightness is input into the light source brightness mapping set to obtain the corresponding second malt image quality assessment compensation value; the image signal-to-noise ratio and the preset third malt image quality assessment compensation value form an image signal-to-noise ratio mapping set, and the real-time image signal-to-noise ratio is input into the image signal-to-noise ratio mapping set to obtain the corresponding third malt image quality assessment compensation value; the image resolution and the preset fourth malt image quality assessment compensation value form an image resolution mapping set, and the real-time image resolution is input into the image resolution mapping set to obtain the corresponding fourth malt image quality assessment compensation value; the mapping relationship can be one-to-one or many-to-one.

[0038] Among them, the specific restriction expression of the malt image quality evaluation index is:

[0039]

[0040] Where TU represents the malt image quality assessment index of the malt cross-section image, GJU represents the illumination uniformity coefficient of the malt cross-section image, ZA represents the image signal-to-noise ratio contrast coefficient of the malt cross-section image, FE represents the image resolution contrast coefficient of the malt cross-section image, T1 represents the first malt image quality assessment compensation value, T2 represents the second malt image quality assessment compensation value, T3 represents the third malt image quality assessment compensation value, and T4 represents the fourth malt image quality assessment compensation value.

[0041] The specific process involved in determining whether to optimize the image quality of the malt cross-section is as follows:

[0042] A1. Calculate the malt image quality assessment index of a single malt cross-section image to obtain an average malt image quality assessment index, and determine whether the average malt image quality assessment index is less than a preset malt image quality threshold obtained from a preset database. If the average malt image quality assessment index is less than the preset malt image quality threshold obtained from the preset database, perform light source optimization; otherwise, do not perform malt cross-section image quality optimization. The average malt image quality assessment index represents the average quality of the malt cross-section image. The light source optimization is used to reduce the impact of changes in lighting conditions on the quality of the malt cross-section image. The preset malt image quality threshold is represented by the average value of the average malt image quality assessment index within a historical time period.

[0043] A2, judging whether the average malt image quality evaluation index after light source optimization is less than the preset malt image quality threshold obtained from the preset database, if the average malt image quality evaluation index after light source optimization is less than the preset malt image quality threshold obtained from the preset database, then image processing is performed, otherwise the malt section image quality optimization is terminated, and image processing is used to improve the malt section image quality; image processing processes the malt section image through median filtering and histogram equalization to remove noise and enhance contrast; the processing flow of median filtering is: first, the malt section image is converted into a grayscale image, then a window of odd size is selected, and the window is slid pixel by pixel on the image, then the grayscale values of all pixels in the window are sorted, and then the middle value of the sorted grayscale values is selected as the new grayscale value of the center pixel of the window, and finally all pixels in the image are sorted. Repeat the above operation to complete the median filtering; the selection of window size needs to be determined according to the image noise characteristics and detail retention requirements. For the malt cross-section image, if the noise is smaller and more details need to be retained, for example, a 3×3 window is selected; the processing flow of histogram equalization is as follows: first, the number of pixels of each gray level in the malt cross-section image is counted to obtain a grayscale histogram, and then the cumulative distribution function is calculated based on the grayscale histogram. The cumulative distribution function reflects the cumulative proportion of pixels below each grayscale level. Then, the grayscale value of the original image is mapped through the cumulative distribution function to obtain a new grayscale value. The specific formula is: new grayscale value = total number of grayscale levels × cumulative distribution function (original grayscale value) - 1. Finally, the grayscale value of the original image is replaced with the mapped new grayscale value to obtain the image after histogram equalization; for 8-bit grayscale images, the total number of grayscale levels is usually 256.

[0044] A3, determines whether the average malt image quality evaluation index after image processing is less than the preset malt image quality threshold obtained from the preset database. If the average malt image quality evaluation index after image processing is less than the preset malt image quality threshold obtained from the preset database, feedback is given; otherwise, the malt section image quality optimization is terminated; the malt section image quality optimization includes light source optimization and image processing; the feedback here indicates that the preset personnel are prompted that the image quality does not meet the standard.

[0045] The specific method of light source optimization involved is as follows: the average malt image quality evaluation index and the light source brightness deviation are input into the light source brightness mapping set to obtain the optimized light source brightness. The light source brightness deviation is obtained by performing a difference operation between the light source brightness and the preset light source brightness. The light source brightness mapping set is a set obtained from a preset database that represents the mapping relationship between the average malt image quality evaluation index, the light source brightness deviation and the optimized light source brightness; after adjusting the light source brightness in the annular shadowless light source system to the optimized light source brightness, the malt cross-section image is re-collected. The annular shadowless light source system is used to avoid the problem of poor stability of the collected malt cross-section image caused by uneven lighting.

[0046] In this embodiment, the brightness of the light source directly affects the brightness of the malt cross-section image, and thus affects the illumination uniformity coefficient. Excessively strong or weak light source brightness will lead to uneven illumination, which in turn affects the quality of the malt cross-section image. The malt cross-section image with uniform illumination has less noise, so the larger the illumination uniformity coefficient and the larger the image signal-to-noise ratio coefficient. The malt cross-section image with higher resolution can better offset the influence of noise, so the larger the image resolution, the larger the image signal-to-noise ratio coefficient. The image resolution is also related to the illumination uniformity coefficient and the brightness of the light source. The malt cross-section image with higher resolution can more accurately capture the illumination changes and obtain more precise illumination uniformity.

[0047] By comparing the image signal-to-noise ratio, resolution, light source brightness and the corresponding preset values, defects in the malt cross-section image (such as noise, insufficient resolution, low light brightness, etc.) can be judged; by introducing compensation values, the evaluation process is made more flexible, and the quality of the malt cross-section image is fine-tuned according to the actual acquisition environment to ensure accurate evaluation results. For example, if the ambient light source is unstable, the first malt image quality evaluation compensation value and the second malt image quality evaluation compensation value may be higher; through the above steps, the quality of the malt cross-section image is quantitatively evaluated, and problems with the malt image quality are discovered in time, which provides a basis for subsequent optimization of the malt cross-section image quality, ensures the accuracy of the subsequent malt cross-section image analysis process, and avoids misjudgment caused by poor quality of the malt cross-section image.

[0048] By reducing the impact of changing lighting conditions on the quality of malt cross-section images, the image quality can be kept relatively stable under different lighting environments. For example, it avoids overexposure or underexposure of images due to strong or weak lighting, and reduces problems such as shadows and reflections caused by uneven lighting, thereby improving image clarity and detail representation, providing a better foundation for subsequent image processing and image quality assessment. Through median filtering, the edges and details of the malt cross-section image can be preserved while removing noise interference, making the malt cross-section image smoother and clearer. By adjusting the grayscale distribution of the malt cross-section image, the grayscale level of the malt cross-section image is more evenly distributed throughout the grayscale range, thereby improving the visibility and information content of the malt cross-section image, and facilitating more accurate identification and analysis of the characteristics of the malt cross-section.

[0049] By dynamically adjusting the brightness of the light source, the brightness difference between different tissues in the malt cross-section image can be increased, the contrast can be improved, and the details of the malt cross-section can be made clearer and more visible, thereby improving the reliability of malt hydration degree detection.

[0050] Furthermore, the malt hydration is evaluated based on the malt characteristic parameters in the malt cross-section image. The specific method is as follows:

[0051] D1, introduce the malt morphology evaluation compensation value to assign and couple the average endosperm area ratio, average cell swelling degree, and average cell wall rupture coefficient in a single malt cross-section image to obtain the malt morphology characteristic evaluation index. The malt morphology evaluation compensation value includes the first malt morphology evaluation compensation value, the second malt morphology evaluation compensation value, and the third malt morphology evaluation compensation value. The malt morphology characteristic evaluation index is used to quantitatively evaluate the hydration degree of the malt in terms of morphological characteristics. The specific restricted expression of the malt morphology characteristic evaluation index is:

[0052] XT=X1×PRQ+X2×PZD+X3×XPL;

[0053] Wherein, XT represents the evaluation index of malt morphological characteristics of malt section image, PRQ represents the average endosperm area ratio of malt in malt section image, the cross-sectional image of a single malt in the malt section image is segmented by image processing software (such as ImageJ, MATLAB), the endosperm area and other tissues (such as seed coat, germ) are distinguished, the pixel area of the endosperm area is measured, and the pixel area of the endosperm area is ratioed to the cross-sectional area of the entire malt to obtain the endosperm area ratio of a single malt in the malt section image; the endosperm area ratio of all malts in the malt section image is averaged to obtain the average endosperm area ratio; PZD represents the average cell swelling degree of malt in the malt section image, the area of a single cell is measured by image processing software (such as ImageJ, MATLAB), and then the water-immersion The cell swelling degree of a single malt in the malt cross-section image is obtained by performing a ratio operation on the area of the malt after soaking and the area of the malt before soaking; the cell swelling degrees of all malts in the malt cross-section image are averaged to obtain the average cell swelling degree; XPL represents the average cell wall rupture coefficient of the malt in the malt cross-section image, and the cell wall area is segmented by image processing software (such as ImageJ, MATLAB) to obtain the area of the ruptured cell wall, and then the area of the ruptured cell wall is ratioed to the total cell wall area to obtain the cell wall rupture coefficient of a single malt in the malt cross-section image; the cell wall rupture coefficients of all malts in the malt cross-section image are averaged to obtain the average cell wall rupture coefficient; X1 represents the first malt morphology evaluation compensation value, X2 represents the second malt morphology evaluation compensation value, and X3 represents the third malt morphology evaluation compensation value.

[0054] The malt morphology evaluation compensation values involved are obtained from a preset database. The first malt morphology evaluation compensation value represents the degree of influence of the average endosperm area ratio on the malt morphology characteristic evaluation index. The second malt morphology evaluation compensation value represents the degree of influence of the average cell swelling degree on the malt morphology characteristic evaluation index. The third malt morphology evaluation compensation value represents the degree of influence of the average cell wall rupture coefficient on the malt morphology characteristic evaluation index. The sum of the three is 1. For example, the average endosperm area ratio and the preset first malt morphology evaluation compensation value form an average endosperm area ratio mapping set. The real-time average endosperm area ratio is input into the average endosperm area ratio. The area proportion mapping set obtains the corresponding first malt morphology evaluation compensation value; the average cell swelling degree and the preset second malt morphology evaluation compensation value form an average cell swelling degree mapping set, and the real-time average cell swelling degree is input into the average cell swelling degree mapping set to obtain the corresponding second malt morphology evaluation compensation value; the average cell wall rupture coefficient and the preset third malt morphology evaluation compensation value form an average cell wall rupture coefficient mapping set, and the real-time average cell wall rupture coefficient is input into the average cell wall rupture coefficient mapping set to obtain the corresponding third malt morphology evaluation compensation value; the mapping relationship therein can be a one-to-one correspondence or a many-to-one relationship.

[0055] D2, the malt contrast coefficient is obtained by performing an inverse proportional operation on the de-normalized average malt contrast in a single malt section image, i.e. Wherein, MDB represents the average malt contrast of malt in the malt cross-section image. The average malt contrast can be obtained by quantizing the grayscale image into a preset number of gray levels and calculating the gray-level co-occurrence matrix using the greycoprops function in the scikit-image library. The preset number is set by the designer, for example, 8 gray levels.

[0056] D3, introducing a malt color evaluation compensation value to perform assignment coupling processing on the de-unitized average malt brightness, the de-unitized average malt saturation, and the malt contrast coefficient in a single malt cross-section image to obtain a malt color feature evaluation index. The malt color evaluation compensation value includes a first malt color evaluation compensation value, a second malt color evaluation compensation value, and a third malt color evaluation compensation value. The malt color feature evaluation index is used to quantitatively evaluate the hydration degree of the malt in terms of color characteristics. The specific restricted expression of the malt color feature evaluation index is:

[0057]

[0058] Wherein, YT represents the malt color feature evaluation index of the malt cross-section image, MLD represents the average malt brightness of the malt in the malt cross-section image, the BGR image is converted to an HSV image using the cvtColor function of OpenCV, and then the S channel (saturation) and V channel (brightness) are separated from the HSV image. Finally, NumPy is used to calculate the average values of the S channel and the V channel to obtain the average malt brightness and average malt saturation; MBD represents the average malt saturation of the malt in the malt cross-section image, Y1 represents the first malt color evaluation compensation value, Y2 represents the second malt color evaluation compensation value, and Y3 represents the third malt color evaluation compensation value.

[0059] The malt color evaluation compensation values involved are obtained from a preset database. The first malt color evaluation compensation value represents the degree of influence of the average malt brightness on the malt color characteristic evaluation index, the second malt color evaluation compensation value represents the degree of influence of the average malt saturation on the malt color characteristic evaluation index, and the third malt color evaluation compensation value represents the degree of influence of the average malt contrast on the malt color characteristic evaluation index; the sum of the three is 1. For example, the average malt brightness and the preset first malt color evaluation compensation value form a brightness mapping set, and the real-time average malt brightness is input into the brightness mapping set to obtain the corresponding first malt color evaluation compensation value; the average malt saturation and the preset second malt color evaluation compensation value form a saturation mapping set, and the real-time average malt saturation is input into the saturation mapping set to obtain the corresponding second malt color evaluation compensation value; the average malt contrast and the preset third malt color evaluation compensation value form a contrast mapping set, and the real-time average malt contrast is input into the contrast mapping set to obtain the corresponding third malt color evaluation compensation value; the mapping relationship can be one-to-one or many-to-one.

[0060] D4, introducing the malt comprehensive hydration compensation value to perform assignment coupling processing on the malt morphological characteristic evaluation index and the malt color characteristic evaluation index in the single malt cross-section image to obtain the malt comprehensive hydration index, which is used to comprehensively and quantitatively evaluate the hydration degree of the malt;

[0061] The specific limiting expression of malt comprehensive hydration index is:

[0062] SH=α×XT+(1-α)×YT;

[0063] Where SH represents the comprehensive hydration index of malt cross-section image, and α represents the comprehensive hydration compensation value of malt.

[0064] The malt comprehensive hydration compensation value involved is obtained from a preset database. The malt comprehensive hydration compensation value indicates the degree of influence of the malt morphological characteristic evaluation index on the malt comprehensive hydration index. Its value range is between 0 and 1. For example, the malt morphological characteristic evaluation index and the preset first malt color evaluation compensation value form a morphological mapping set. The real-time malt morphological characteristic evaluation index is input into the morphological mapping set to obtain the corresponding first malt color evaluation compensation value. The mapping relationship can be one-to-one or many-to-one.

[0065] In this embodiment, the average endosperm area ratio, the average cell swelling degree, and the average cell wall rupture coefficient reflect the morphological changes of the malt, such as the size of the endosperm area, the degree of cell swelling, and whether the cell wall is ruptured. The hydration degree of the malt in terms of morphological characteristics is quantitatively evaluated. If the endosperm area ratio of the malt increases, the cell swelling degree increases, and the degree of cell wall rupture is greater, it indicates that the hydration degree of the malt is higher.

[0066] In the malt morphological characteristic evaluation index algorithm, as the cell swelling increases, the hydration of the endosperm region will also accelerate, and the water permeability will increase. After the cell swelling, the effective hydration area of the endosperm region increases. Therefore, the greater the cell swelling, the larger the proportion of the endosperm region. When the cell swelling increases, the rupture of the cell wall may be aggravated, which means that the process of water penetration into the cell will be accelerated, thereby increasing the degree of hydration. Therefore, the greater the cell swelling, the greater the cell wall rupture coefficient.

[0067] The contrast reflects the color difference or brightness difference between different parts of the malt cross-section image; the malt brightness and saturation reflect the color characteristics of the malt in the malt cross-section image, and quantitatively evaluate the hydration degree of the malt in terms of color characteristics. If the malt brightness and malt saturation are higher and the malt contrast is lower, it indicates that the hydration degree of the malt is higher.

[0068] In the malt color feature evaluation index algorithm, the higher the hydration degree, the higher the malt brightness and malt saturation; the higher the malt saturation, the clarity of the malt surface texture may decrease and the malt contrast will be weakened; as the malt brightness increases, the smooth and moist surface characteristics may lead to a decrease in contrast.

[0069] By comprehensively and quantitatively assessing the hydration level of malt across two dimensions (morphology and color), we provide a foundation for optimizing subsequent hydration process parameters and improve the uniformity of malt water absorption during the steeping process. Changes in morphological characteristics (such as cell swelling and an increase in the proportion of the endosperm area) are often accompanied by changes in color characteristics. For example, increases in the cell wall rupture coefficient, cell swelling, and endosperm area indicate better hydration, resulting in higher malt brightness, malt saturation, and malt contrast.

[0070] Furthermore, before determining whether to optimize the hydration process parameters based on the malt hydration evaluation results and the malt steeping index, the hydration level classification threshold is obtained. The specific process is as follows:

[0071] B1. The soaking index is initially divided into hydration levels according to the initial hydration level division threshold. The initial hydration level division threshold includes the qualified maximum value of the initial soaking index and the qualified minimum value of the initial soaking index. The initial hydration level division threshold is set according to the preset personnel; the soaking index represents the water absorption rate of the wheat grains within the preset soaking time, in grams per hour. The preset soaking time is set according to the preset personnel.

[0072] B2, judging whether to adjust the qualified maximum value of the initial malt soaking index based on the average malt comprehensive hydration index corresponding to the qualified maximum value of the initial malt soaking index in the historical time period in the preset database, the average malt comprehensive hydration index represents the average hydration degree of the current batch of malt, and the qualified maximum value of the initial malt soaking index represents the maximum value of the qualified malt soaking index in the historical time period in the preset database.

[0073] If the average malt comprehensive hydration index corresponding to the maximum qualified value of the initial soaking index is not within the preset malt hydration qualified range obtained from the preset database, the first-level division adjustment factor is introduced to correct the maximum qualified value of the initial soaking index to obtain the maximum qualified value of the soaking index. The first-level division adjustment factor is obtained by performing a difference operation on the average malt comprehensive hydration index corresponding to the maximum qualified value of the initial soaking index and the preset maximum qualified value of the malt hydration obtained from the preset database. Otherwise, the maximum qualified value of the initial soaking index is directly recorded as the maximum qualified value of the soaking index. The preset malt hydration qualified range is between the preset malt hydration qualified minimum value and the preset malt hydration qualified maximum value. The preset malt hydration qualified minimum value is represented by the minimum value of the average malt comprehensive hydration index in the historical time period, and the preset malt hydration qualified maximum value is represented by the maximum value of the average malt comprehensive hydration index in the historical time period. The maximum qualified value of the soaking index is obtained by multiplying the first-level division adjustment factor and the maximum qualified value of the initial soaking index.

[0074] B3, judging whether to adjust the qualified minimum value of the initial malt soaking index based on the average malt comprehensive hydration index corresponding to the qualified minimum value of the initial malt soaking index in the historical time period in the preset database, where the qualified minimum value of the initial malt soaking index represents the minimum value of the qualified malt soaking index in the historical time period in the preset database.

[0075] If the average malt comprehensive hydration index corresponding to the initial minimum qualified malt soaking index value is not within the preset malt hydration qualified range obtained from the preset database, the second-level division adjustment factor is introduced to correct the initial minimum qualified malt soaking index value to obtain the minimum qualified malt soaking index value. The second-level division adjustment factor is obtained by performing a difference operation on the average malt comprehensive hydration index corresponding to the initial minimum qualified malt soaking index value and the preset minimum qualified malt hydration value obtained from the preset database. Otherwise, the initial minimum qualified malt soaking index value is directly recorded as the minimum qualified malt soaking index value. The minimum qualified malt soaking index value is obtained by multiplying the second-level division adjustment factor and the initial minimum qualified malt soaking index value.

[0076] The decision on whether to optimize hydration process parameters is based on the results of malt hydration assessment and the malt steeping index. The specific process is as follows:

[0077] The hydration grade is divided based on the soaking index and the hydration grade division threshold, and the hydration grade division threshold includes the maximum qualified soaking index and the minimum qualified soaking index.

[0078] When the soaking index is greater than the qualified maximum value of the soaking index, the corresponding soaking index is divided into the first hydration level, and the first hydration process parameter optimization is performed; when the soaking index is not greater than the qualified maximum value of the soaking index, and is greater than the qualified minimum value of the soaking index, the corresponding soaking index is divided into the second hydration level, and the hydration process parameter optimization is not performed; when the soaking index is not greater than the qualified minimum value of the soaking index, the corresponding soaking index is divided into the third hydration level, and the second hydration process parameter optimization is performed.

[0079] The specific method for optimizing the first hydration process parameters involved is as follows:

[0080] The average malt comprehensive hydration index, soaking index, and soaking time deviation are input into the soaking time mapping set to obtain the optimized maximum soaking time. The soaking time deviation is obtained by taking the difference between the current soaking time and the maximum soaking time in the second hydration level; the maximum soaking time in the second hydration level is represented by the maximum value of the soaking time in the second hydration level in the historical time period.

[0081] The average malt comprehensive hydration index, soaking index, and soaking temperature deviation are input into the soaking temperature mapping set to obtain the optimized maximum soaking temperature. The soaking temperature deviation is obtained by taking the difference between the current soaking temperature and the maximum soaking temperature in the second hydration level; the maximum soaking temperature in the second hydration level is represented by the maximum value of the soaking temperature in the second hydration level in the historical time period.

[0082] A first pre-adjustment is performed according to a preset ratio of the optimized maximum soaking time to obtain the optimized soaking time, and a first pre-adjustment is performed according to a preset ratio of the optimized maximum soaking temperature to obtain the optimized soaking temperature, until the termination condition is met; the preset ratio is set by a preset person, for example, 10%; the first pre-adjustment represents a gradual reduction.

[0083] The specific method for optimizing the second hydration process parameters is:

[0084] The average malt comprehensive hydration index, soaking index, and soaking time deviation are input into the soaking time mapping set to obtain the optimized maximum soaking time. The soaking time deviation is obtained by subtracting the current soaking time and the maximum soaking time in the second hydration level. The average malt comprehensive hydration index represents the average hydration degree of the current batch of malt.

[0085] The average malt comprehensive hydration index, the steeping index, and the steeping temperature deviation are input into the steeping temperature mapping set to obtain the optimized maximum steeping temperature. The steeping temperature deviation is obtained by calculating the difference between the current steeping temperature and the maximum steeping temperature in the second hydration level.

[0086] A second pre-adjustment is performed according to a preset ratio of the optimized maximum soaking time to obtain the optimized soaking time, and a second pre-adjustment is performed according to a preset ratio of the optimized maximum soaking temperature to obtain the optimized soaking temperature, until the termination condition is met; the second pre-adjustment represents a gradual increase.

[0087] The termination conditions involved are as follows:

[0088] When the optimized soaking time is less than the optimized maximum soaking time, and the optimized soaking temperature is less than the optimized maximum soaking temperature, determine whether the hydration level of the corresponding batch of malt is at the second hydration level. If the hydration level of the corresponding batch of malt is at the second hydration level, terminate the optimization of the first hydration process parameters, otherwise continue the optimization of the first hydration process parameters; when the optimized soaking time is less than the optimized maximum soaking time, and the optimized soaking temperature is not less than the optimized maximum soaking temperature, determine whether the hydration level of the corresponding batch of malt is at the second hydration level. If the hydration level of the corresponding batch of malt is not at the second hydration level, terminate the optimization of the soaking temperature and keep the optimization of the soaking time, otherwise terminate The first hydration process parameter is optimized; when the optimized soaking time is not less than the optimized maximum soaking time, and the optimized soaking temperature is less than the optimized maximum soaking temperature, it is judged whether the hydration level of the corresponding batch of malt is in the second hydration level. If the hydration level of the corresponding batch of malt is not in the second hydration level, feedback is given, otherwise the optimization of the first hydration process parameter is terminated; when the optimized soaking time is not less than the optimized maximum soaking time, and the optimized soaking temperature is not less than the optimized maximum soaking temperature, it is judged whether the hydration level of the corresponding batch of malt is in the second hydration level. If the hydration level of the corresponding batch of malt is not in the second hydration level, feedback is given, otherwise the optimization of the first hydration process parameter is terminated.

[0089] In this embodiment, the hydration degree of malt is preliminarily divided according to the steeping index, which provides an initial standard for the subsequent optimization of hydration process parameters; based on the steeping index and the corresponding average malt comprehensive hydration index, it is checked whether the initial steeping index qualified maximum value and the initial steeping index qualified minimum value need to be adjusted, thereby improving the accuracy of hydration grade division, ensuring that the hydration process parameters can adapt to the actual conditions of different batches of malt, effectively avoiding the errors caused by static threshold setting, and ensuring the rationality of the hydration process parameters; by introducing the adjustment factor, it is possible to avoid overly strict or overly loose evaluation criteria and reduce errors caused by inaccurate hydration grade division.

[0090] Malt is divided into different hydration levels according to its steeping index to determine whether further hydration process optimization is needed; the hydration process is optimized by adjusting the steeping time and temperature to ensure that the hydration level of the malt is within the appropriate range; ensuring that each batch of malt is processed in an ideal hydration state, thereby improving production efficiency.

[0091] Based on the optimized soaking time and temperature, it is judged whether the required hydration level has been reached and whether the termination conditions have been met, and the optimization is stopped to ensure that the optimization process has termination conditions and will not be adjusted endlessly, avoiding waste of time and resources; through gradual adjustment and feedback judgment of the optimization parameters, the process optimization is made more precise, ensuring that the process is not over-adjusted, and improving the accuracy and controllability of malt hydration degree detection.

[0092] like Figure 2 As shown, it is a flow chart of the method for detecting the hydration degree of malt based on image analysis provided by an embodiment of the present application, comprising the following steps: S1, collecting a malt cross-section image by using a high-resolution industrial camera and an annular shadowless light source system, performing a malt image quality assessment based on the image quality parameters of the collected malt cross-section image, and judging whether to perform malt cross-section image quality optimization, the malt cross-section image is an image of the malt cross-section morphology, the malt cross-section morphology is obtained by obtaining a soaked malt sample by an automated device, and cutting it at a uniform speed along the longitudinal direction using a precision cutting device; S2, if the malt cross-section image quality optimization is not performed, performing multi-dimensional feature extraction on the malt cross-section image to obtain malt feature parameters, and performing malt hydration evaluation based on the malt feature parameters in the malt cross-section image. and determining whether to optimize the hydration process parameters. If the malt section image quality is optimized, multi-dimensional feature extraction is performed on the malt section image after the malt section image quality is optimized to obtain malt feature parameters. Malt hydration is evaluated based on the malt feature parameters in the malt section image after the malt section image quality is optimized. Based on the result of the malt hydration evaluation and the soaking index, determining whether to optimize the hydration process parameters is performed. The hydration process parameter optimization is used to improve the uniformity of water absorption of barley during the soaking process. S3, if the hydration process parameter optimization is performed, the malt hydration degree is detected according to the optimized hydration process parameters after the test report is output. Otherwise, the malt hydration degree is directly detected according to the current hydration process parameters after the test report is output.

[0093] In this embodiment, image quality assessment is performed to ensure that the collected malt cross-section image has sufficient resolution and clarity, can effectively display the internal structure of the malt, and provide an accurate data source for subsequent feature extraction and hydration evaluation; if the quality of the malt cross-section image is poor, optimization processing is performed to avoid misjudgment caused by the poor quality of the malt cross-section image in subsequent analysis; through multi-dimensional feature extraction, the hydration of the malt can be deeply analyzed to understand key information such as its water absorption uniformity and endosperm structure; through malt cross-section image quality optimization, the extracted features are ensured to be more accurate and the results of the malt hydration evaluation are more reliable; by optimizing the hydration process, the hydration degree of the malt during the soaking process is ensured to be moderate, avoiding excessive or insufficient water absorption, thereby improving production quality; and thereby achieving an improvement in the detection accuracy of the malt hydration degree.

[0094] In summary, the embodiment of the present application collects image quality parameters to evaluate the malt image quality in order to optimize the malt cross-section image quality, then performs malt hydration evaluation based on the malt characteristic parameters after the malt cross-section image quality is optimized, and finally determines whether to optimize the hydration process parameters based on the results of the malt hydration evaluation and the malt soaking index, thereby improving the quality of the collected malt cross-section image, and further achieving an improvement in the detection accuracy of the malt hydration degree, effectively solving the problem of low detection accuracy of the malt hydration degree caused by feature extraction errors in the prior art.

[0095] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0097] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0099] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0100] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A malt hydration degree detection system based on image analysis, characterized in that: include: Malt image quality assessment module, malt hydration assessment module and hydration process parameter feedback module; The malt image quality assessment module is used to assess the malt image quality according to the acquired image quality parameters of the acquired malt cross-section image, and determine whether to optimize the malt cross-section image quality; The malt hydration evaluation module is used for, if the malt section image quality optimization is not performed, performing multi-dimensional feature extraction on the malt section image to obtain malt characteristic parameters, performing malt hydration evaluation based on the malt characteristic parameters in the malt section image, and judging whether to perform hydration process parameter optimization; if the malt section image quality optimization is performed, performing multi-dimensional feature extraction on the malt section image after the malt section image quality optimization is performed to obtain malt characteristic parameters, performing malt hydration evaluation based on the malt characteristic parameters in the malt section image after the malt section image quality optimization is performed, and judging whether to perform hydration process parameter optimization based on the result of the malt hydration evaluation and the soaking index, wherein the hydration process parameter optimization is used to improve the uniformity of malt water absorption during the soaking process; The hydration process parameter feedback module is used to perform malt hydration degree detection according to the optimized hydration process parameters after outputting the detection report if the hydration process parameters are optimized; otherwise, the malt hydration degree detection is directly performed according to the current hydration process parameters after outputting the detection report.

2. The malt hydration degree detection system based on image analysis as claimed in claim 1, characterized in that: The malt image quality assessment is performed based on the image quality parameters of the collected malt cross-section image, and the specific method is as follows: If the image signal-to-noise ratio of the single malt cross-section image is less than the preset image signal-to-noise ratio obtained from the preset database, the image signal-to-noise ratio of the single malt cross-section image and the preset image signal-to-noise ratio obtained from the preset database are compared to obtain an image signal-to-noise ratio contrast coefficient; otherwise, the image signal-to-noise ratio contrast coefficient is directly recorded as 0; If the image resolution of the single malt cross-section image is smaller than the preset image resolution obtained from the preset database, the image resolution of the single malt cross-section image and the preset image resolution obtained from the preset database are compared to obtain an image resolution comparison coefficient; otherwise, the image resolution comparison coefficient is directly recorded as 0; Perform relative deviation processing based on the light source brightness and the preset image resolution obtained from the preset database to obtain the light source brightness contrast coefficient; A malt image quality assessment compensation value is introduced to perform assignment coupling processing on the illumination uniformity coefficient, the image signal-to-noise ratio contrast coefficient, the image resolution contrast coefficient and the light source brightness contrast coefficient to obtain a malt image quality assessment index. The malt image quality assessment compensation value includes a first malt image quality assessment compensation value, a second malt image quality assessment compensation value, a third malt image quality assessment compensation value and a fourth malt image quality assessment compensation value. The malt image quality assessment index is used to quantitatively evaluate the quality of the malt cross-section image.

3. The malt hydration degree detection system based on image analysis as claimed in claim 2, characterized in that: The specific process of determining whether to optimize the image quality of the malt cross section is as follows: A1, performing statistical analysis on the malt image quality assessment index of a single malt cross-section image to obtain an average malt image quality assessment index. If the average malt image quality assessment index is less than a preset malt image quality threshold obtained from a preset database, performing light source optimization; otherwise, performing no malt cross-section image quality optimization. The average malt image quality assessment index represents the average quality of the malt cross-section image. The light source optimization is used to reduce the impact of changes in lighting conditions on the quality of the malt cross-section image. A2, if the average malt image quality evaluation index after light source optimization is less than a preset malt image quality threshold obtained from a preset database, image processing is performed; otherwise, the malt section image quality optimization is terminated, wherein the image processing is used to improve the malt section image quality; The image processing is to process the malt section image by median filtering and histogram equalization to remove noise and enhance contrast; A3, if the average malt image quality evaluation index after image processing is less than a preset malt image quality threshold obtained from a preset database, feedback is given; otherwise, the malt section image quality optimization is terminated; The malt section image quality optimization includes light source optimization and image processing.

4. The malt hydration degree detection system based on image analysis as claimed in claim 3, characterized in that: The specific method of light source optimization is as follows: Inputting the average malt image quality assessment index and the light source brightness deviation into a light source brightness mapping set to obtain an optimized light source brightness, wherein the light source brightness deviation is obtained by performing deviation processing on the light source brightness and the preset light source brightness, and the light source brightness mapping set is a set obtained from a preset database that represents a mapping relationship between the average malt image quality assessment index, the light source brightness deviation, and the optimized light source brightness; After adjusting the light source brightness in the annular shadowless light source system to the optimized light source brightness, the malt cross-section image is recaptured. The annular shadowless light source system is used to avoid the problem of poor stability of the collected malt cross-section image caused by uneven lighting.

5. The malt hydration degree detection system based on image analysis according to claim 1, characterized in that: The malt hydration evaluation is performed based on the malt characteristic parameters in the malt cross-section image, and the specific method is as follows: Introducing malt morphology evaluation compensation values to perform assignment coupling processing on the average endosperm area ratio, average cell swelling degree, and average cell wall rupture coefficient in a single malt cross-section image to obtain a malt morphology characteristic evaluation index, wherein the malt morphology evaluation compensation values include a first malt morphology evaluation compensation value, a second malt morphology evaluation compensation value, and a third malt morphology evaluation compensation value. The malt morphology characteristic evaluation index is used to quantitatively evaluate the degree of hydration of the malt in terms of morphological characteristics; The malt contrast coefficient is obtained by performing an inverse proportional operation on the de-normalized average malt contrast in a single malt section image; Introducing malt color evaluation compensation values to perform assignment coupling processing on a de-unitized average malt brightness, a de-unitized average malt saturation, and a malt contrast coefficient in a single malt cross-section image to obtain a malt color feature evaluation index, wherein the malt color evaluation compensation values include a first malt color evaluation compensation value, a second malt color evaluation compensation value, and a third malt color evaluation compensation value. The malt color feature evaluation index is used to quantitatively evaluate the hydration degree of the malt in terms of color characteristics; The malt comprehensive hydration compensation value is introduced to perform assignment coupling processing on the malt morphological characteristic evaluation index and the malt color characteristic evaluation index in a single malt cross-section image to obtain the malt comprehensive hydration index, which is used to comprehensively and quantitatively evaluate the hydration degree of malt.

6. The malt hydration degree detection system based on image analysis according to claim 5, characterized in that: The step of determining whether to optimize hydration process parameters based on the malt hydration evaluation results and the malt steeping index also includes obtaining a hydration level classification threshold; The specific process of obtaining the hydration level threshold is as follows: B1, performing initial hydration level classification on the soaked wheat index according to the initial hydration level classification threshold, wherein the initial hydration level classification threshold includes a qualified maximum value of the initial soaked wheat index and a qualified minimum value of the initial soaked wheat index; B2, judging whether to adjust the qualified maximum value of the initial malt soaking index based on the average malt comprehensive hydration index corresponding to the qualified maximum value of the initial malt soaking index in the historical time period in the preset database; If the average malt comprehensive hydration index corresponding to the maximum qualified initial malt soaking index is not within the preset malt hydration qualified range obtained from the preset database, a first grade classification adjustment factor is introduced to correct the maximum qualified initial malt soaking index to obtain the maximum qualified malt soaking index, wherein the first grade classification adjustment factor is obtained by performing deviation processing on the average malt comprehensive hydration index corresponding to the maximum qualified initial malt soaking index and the preset maximum qualified malt hydration value obtained from the preset database; otherwise, the maximum qualified initial malt soaking index is directly recorded as the maximum qualified malt soaking index, and the preset qualified malt hydration range is between the preset minimum qualified malt hydration value and the preset maximum qualified malt hydration value; B3, judging whether to adjust the minimum qualified value of the initial malt soaking index based on the average malt comprehensive hydration index corresponding to the minimum qualified value of the initial malt soaking index in the historical time period in the preset database; If the average malt comprehensive hydration index corresponding to the initial minimum qualified malt soaking index value is not within the preset malt hydration qualified range obtained from the preset database, the second level division adjustment factor is introduced to correct the initial minimum qualified malt soaking index value to obtain the minimum qualified malt soaking index value. The second level division adjustment factor is obtained by performing deviation processing on the average malt comprehensive hydration index corresponding to the initial minimum qualified malt soaking index value and the preset minimum qualified malt hydration value obtained from the preset database. Otherwise, the initial minimum qualified malt soaking index value is directly recorded as the minimum qualified malt soaking index value.

7. The malt hydration degree detection system based on image analysis according to claim 6, characterized in that: The specific process of determining whether to optimize hydration process parameters based on the malt hydration evaluation results and the malt steeping index is as follows: Performing hydration grade classification based on the soaking index and the hydration grade classification threshold, wherein the hydration grade classification threshold includes a maximum soaking index qualified value and a minimum soaking index qualified value; When the soaking index is greater than the qualified maximum soaking index, the corresponding soaking index is classified as the first hydration level, and the first hydration process parameters are optimized; When the soaking index is not greater than the qualified maximum value of the soaking index and greater than the qualified minimum value of the soaking index, the corresponding soaking index is classified as the second hydration level, and the hydration process parameters are not optimized; When the soaking wheat index is not greater than the qualified minimum value of the soaking wheat index, the corresponding soaking wheat index is classified into the third hydration level, and the second hydration process parameters are optimized.

8. The malt hydration degree detection system based on image analysis according to claim 7, characterized in that: The specific method for optimizing the first hydration process parameters is as follows: The average malt comprehensive hydration index, the steeping index, and the steeping time deviation are input into the steeping time mapping set to obtain the optimized maximum steeping time, wherein the steeping time deviation is obtained by performing a deviation process on the current steeping time and the maximum steeping time in the second hydration level; The average malt comprehensive hydration index, the steeping index, and the steeping temperature deviation are input into the steeping temperature mapping set to obtain an optimized maximum steeping temperature, wherein the steeping temperature deviation is obtained by performing a deviation process on the current steeping temperature and the maximum steeping temperature in the second hydration level; Performing a first pre-adjustment according to a preset ratio of the optimized maximum soaking time to obtain an optimized soaking time, and performing a first pre-adjustment according to a preset ratio of the optimized maximum soaking temperature to obtain an optimized soaking temperature, until a termination condition is met; A specific method for optimizing the second hydration process parameters; Inputting the average malt comprehensive hydration index, the steeping index, and the steeping time deviation into the steeping time mapping set to obtain an optimized maximum steeping time, wherein the steeping time deviation is obtained by performing a deviation process on the current steeping time and the maximum steeping time in the second hydration level, and the average malt comprehensive hydration index represents the average hydration degree of the current batch of malt; The average malt comprehensive hydration index, the steeping index, and the steeping temperature deviation are input into the steeping temperature mapping set to obtain an optimized maximum steeping temperature, wherein the steeping temperature deviation is obtained by performing a deviation process on the current steeping temperature and the maximum steeping temperature in the second hydration level; A second pre-adjustment is performed according to a preset ratio of the optimized maximum soaking time to obtain the optimized soaking time, and a second pre-adjustment is performed according to a preset ratio of the optimized maximum soaking temperature to obtain the optimized soaking temperature, until the termination condition is met.

9. The malt hydration degree detection system based on image analysis according to claim 7, characterized in that: The termination conditions are as follows: When the optimized soaking time is less than the optimized maximum soaking time, and the optimized soaking temperature is less than the optimized maximum soaking temperature, if the hydration level of the corresponding batch of malt is at the second hydration level, the optimization of the first hydration process parameters is terminated; otherwise, the optimization of the first hydration process parameters is continued; When the optimized soaking time is less than the optimized maximum soaking time, and the optimized soaking temperature is not less than the optimized maximum soaking temperature, if the hydration level of the corresponding batch of malt is not at the second hydration level, the optimization of the soaking temperature is terminated, and the optimization of the soaking time is maintained; otherwise, the optimization of the first hydration process parameters is terminated; When the optimized soaking time is not less than the optimized maximum soaking time, and the optimized soaking temperature is less than the optimized maximum soaking temperature, if the hydration level of the corresponding batch of malt is not at the second hydration level, feedback is given; otherwise, the optimization of the first hydration process parameters is terminated; When the optimized soaking time is not less than the optimized maximum soaking time, and the optimized soaking temperature is not less than the optimized maximum soaking temperature, if the hydration level of the corresponding batch of malt is not at the second hydration level, feedback is given; otherwise, the optimization of the first hydration process parameters is terminated.

10. A method for detecting malt hydration degree based on image analysis, characterized in that: The following steps are involved: S1, performing malt image quality assessment based on image quality parameters of the acquired malt cross-section image, and determining whether to optimize the malt cross-section image quality; S2, if the malt cross-section image quality optimization is not performed, then multi-dimensional feature extraction is performed on the malt cross-section image to obtain malt characteristic parameters, malt hydration is evaluated based on the malt characteristic parameters in the malt cross-section image, and it is determined whether to perform hydration process parameter optimization; if the malt cross-section image quality optimization is performed, then multi-dimensional feature extraction is performed on the malt cross-section image after the malt cross-section image quality optimization is performed to obtain malt characteristic parameters, malt hydration is evaluated based on the malt characteristic parameters in the malt cross-section image after the malt cross-section image quality optimization is performed, and it is determined whether to perform hydration process parameter optimization based on the result of the malt hydration evaluation and the steeping index, wherein the hydration process parameter optimization is used to improve the uniformity of malt water absorption during the steeping process; S3. If the hydration process parameters are optimized, the malt hydration degree is tested according to the optimized hydration process parameters after the test report is output; otherwise, the malt hydration degree is tested directly according to the current hydration process parameters after the test report is output.

Images