A method and system for evaluating the color quality of eggshell surfaces based on color reflection

Abstract

An embodiment of the present invention provides a method and system for evaluating the color quality of the eggshell surface based on color reflection, which relates to the technical field of agricultural product quality detection. The method includes: S10: Cleaning the eggshell surface through a multi-modal collaborative cleaning system for the eggshell surface to obtain the cleaned eggshell surface; S20: Using a multi-spectral imaging system to capture spectral features of the cleaned eggshell surface to obtain spectral reflection data of the cleaned eggshell surface; S30: Extracting features and dimensionality reduction from the spectral reflection data of the eggshell surface by a computer device to obtain a multi-dimensional eggshell color feature vector; S40: Obtaining the color quality grade of the eggshell surface by the computer device according to the multi-dimensional eggshell color feature vector and the trained eggshell color quality evaluation model. This method overcomes the subjectivity and limitations of traditional manual visual inspection and introduces digital and intelligent eggshell color quality evaluation technology in agricultural product quality detection.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural product quality inspection, and particularly relates to a method and system for evaluating the color quality of eggshell surfaces based on color reflection. Background Art

[0002] In the context of the increasing importance of global agricultural production and food safety, agricultural product quality inspection technology has become an important technology in modern agriculture and food processing industries. With the continuous growth of the world's population and the improvement of food safety awareness, the demand for high-quality and high-standard agricultural products is increasing day by day. As an important source of animal protein, eggs not only occupy an important position in the global dietary structure, but their quality directly affects consumers' health and nutritional intake. The color of the eggshell surface, as one of the key indicators for judging egg quality, not only reflects the health status of laying hens and the feeding environment, but can also indirectly reveal the freshness, nutritional value and hygienic level of the production process of eggs.

[0003] Currently, the detection of the color quality of eggshell surfaces mainly relies on traditional manual visual evaluation methods. Inspectors observe the color, luster and uniformity of the eggshells with the naked eye and make quality evaluations based on personal experience and subjective judgment. This method has many defects, such as inconsistent detection standards, uneven personnel quality, highly dependent on personal experience for judgment results, low detection efficiency, and it is difficult to perform precise quantification.

[0004] Due to the fact that traditional methods mainly rely on manual visual judgment, they have serious defects such as strong subjectivity, low precision, and inability to achieve rapid and continuous detection. This evaluation method not only affects egg grading and pricing, but also restricts the intelligent development of the egg industry. There is an urgent need in the current industry for an objective and accurate eggshell color quality evaluation technology. Summary of the Invention

[0005] In view of this, the purpose of the embodiments of the present invention is to provide a method and system for evaluating the color quality of eggshell surfaces based on color reflection to solve at least one of the above technical problems.

[0006] To achieve the above object, in a first aspect, the embodiments of the present invention provide a method for evaluating the color quality of eggshell surfaces based on color reflection, which includes the following steps:

[0007] Clean the surface of the eggshell through a multi-modal collaborative cleaning system for the eggshell surface to obtain a cleaned eggshell surface;

[0008] Use a multi-spectral imaging system to capture spectral characteristics of the cleaned eggshell surface to obtain spectral reflection data of the cleaned eggshell surface;

[0009] Extract features and reduce the dimension of the spectral reflection data of the eggshell surface by a computer device to obtain a multi-dimensional eggshell color feature vector;

[0010] The computer device obtains the color quality grade of the eggshell surface according to the multi-dimensional eggshell color feature vector and the trained eggshell color quality evaluation model.

[0011] In a second aspect, an embodiment of the present invention provides a system for evaluating the color quality of an eggshell surface based on color reflection, which includes:

[0012] A multi-modal collaborative cleaning system for the eggshell surface, which is used to clean the eggshell surface and obtain the cleaned eggshell surface;

[0013] A multi-spectral imaging system, which is used to capture spectral features of the cleaned eggshell surface and obtain spectral reflection data of the cleaned eggshell surface;

[0014] A computer device, which is used to extract features and reduce the dimension of the spectral reflection data of the eggshell surface to obtain a multi-dimensional eggshell color feature vector; and obtain the color quality grade of the eggshell surface according to the multi-dimensional eggshell color feature vector and the trained eggshell color quality evaluation model.

[0015] The above technical solution has the following beneficial effects:

[0016] The present invention realizes the accurate, objective and comprehensive evaluation of the color quality of the eggshell surface through a multi-modal collaborative method. The multi-modal collaborative cleaning system ensures the standardized pretreatment of the eggshell surface and eliminates the interference of external pollution factors; the multi-spectral imaging system can capture micro-spectral features that are difficult to detect by traditional single spectra and provides more detailed and comprehensive spectral reflection data; the computer device uses advanced feature extraction and dimension reduction technologies to quickly and accurately extract key color feature vectors from complex spectral data and realizes the intelligent and quantitative rating of color quality through a pre-trained machine learning model. This system not only improves the accuracy and efficiency of eggshell color quality evaluation, but also provides a scientific and standardized solution for egg quality control in agricultural production. Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a flowchart of a method for evaluating the color quality of an eggshell surface based on color reflection according to an embodiment of the present invention;

[0019] Figure 2It is a functional block diagram of the multi-modal collaborative cleaning system for the eggshell surface in an embodiment of the present invention;

[0020] Figure 3 It is a functional block diagram of the multi-spectral imaging system in an embodiment of the present invention;

[0021] Figure 4 It is a specific flowchart of step S20 in an embodiment of the present invention;

[0022] Figure 5 It is a specific flowchart of step S30 in an embodiment of the present invention;

[0023] Figure 6 It is a flowchart of another method for evaluating the color quality of the eggshell surface based on color reflection in an embodiment of the present invention;

[0024] Figure 7 It is a specific flowchart of step S70 in an embodiment of the present invention;

[0025] Figure 8 It is a functional block diagram of a system for evaluating the color quality of the eggshell surface based on color reflection in an embodiment of the present invention;

[0026] Figure 9 It is a functional block diagram of a computer-readable storage medium in an embodiment of the present invention;

[0027] Figure 10 It is a functional block diagram of an electronic device in an embodiment of the present invention. Detailed implementation manners

[0028] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0029] The embodiments of the present invention provide a method and system for evaluating the color quality of the eggshell surface based on color reflection. Through multi-spectral imaging, accurate spectral reflectance measurement, and deep learning algorithms, quantitative, objective, and efficient evaluation of the eggshell color is achieved, which is beneficial to improving the detection accuracy, realizing automatic detection, and reducing manual intervention. The technical solution of the embodiments of the present invention can be used in multiple fields such as quality control of egg production lines, agricultural intelligent sorting systems, quality control of egg exports, and quality evaluation of agricultural product e-commerce platforms.

[0030] Embodiment 1

[0031] As Figure 1As shown in the figure, an embodiment of the present invention provides a method for evaluating the color quality of the eggshell surface based on color reflection, which includes the following steps:

[0032] S10: Clean the eggshell surface through a multi-modal collaborative cleaning system for the eggshell surface to obtain the cleaned eggshell surface.

[0033] In this step, the multi-modal collaborative cleaning system for the eggshell surface is a device integrating multiple cleaning technologies. This system may include, but is not limited to, an ultrasonic cleaning module, an air flow dust removal module, and a photocatalyst purification module. During specific operation, first use the air flow dust removal module to blow away the loose dust particles on the eggshell surface, control the air flow pressure at 0.2 - 0.5 MPa, and keep the nozzle 5 - 10 cm away from the eggshell surface; then start the ultrasonic cleaning module, use ultrasonic oscillation with a frequency of 40 - 45 kHz, supplemented with a mild cleaning agent solution, to remove the stubborn stains on the eggshell surface; finally, perform surface disinfection and deep cleaning through the photocatalyst purification module. Select the photocatalyst wavelength within the range of 365 - 420 nm, which can effectively remove microorganisms and residual pollutants. The working principle of the photocatalyst purification module is based on photocatalytic oxidation technology. This photocatalyst purification module is mainly composed of a high-efficiency photocatalyst material (titanium dioxide nanomaterial) and a specific wavelength light source. When light with a wavelength of 365 - 420 nm irradiates the surface coated with the photocatalyst material, it will activate the photocatalyst to generate highly oxidizing active free radicals. These active free radicals have extremely strong redox capabilities and can quickly degrade the organic pollutants, microorganisms, and protein residues on the eggshell surface, achieving deep disinfection and purification. The photocatalyst purification module can not only effectively remove microorganisms such as bacteria and fungi, but also decompose organic stains such as grease and protein adsorbed on the eggshell surface.

[0034] S20: Use a multi-spectral imaging system to capture the spectral characteristics of the cleaned eggshell surface and obtain the spectral reflection data of the cleaned eggshell surface.

[0035] In this step, the multi-spectral imaging system can adopt a high-precision spectral acquisition device, including a high-resolution CCD camera, a tunable spectrometer (Tunable Filter), and a light source. When the multi-spectral imaging system works, select the wavelength range of 400 - 1000 nm and perform spectral scanning at a step interval of 10 nm. The light source uses a standard D65 light source to ensure light uniformity and color temperature stability. The CCD camera has a 16-bit gray depth, the pixel resolution is not less than 2048×2048, the shutter speed is controlled within 1 / 500 - 1 / 1000 seconds, and the spectral resolution is better than 5 nm. Capture the spectral characteristics of the cleaned eggshell surface at multiple angles and multiple wavelengths to obtain high-precision spectral reflection data including visible light and near-infrared spectra.

[0036] An adjustable spectrometer is an optical device that can continuously or discretely adjust wavelength selection. It has wavelength selectivity and can precisely select light within a specific wavelength range, enabling sequential or continuous scanning of spectra of different wavelengths, thereby improving the accuracy and flexibility of spectral acquisition. In terms of spectral resolution, an adjustable spectrometer can achieve high-precision spectral resolution. By controlling the wavelength bandwidth, it can improve the resolution of spectral information, reduce spectral noise, and enhance the quality of spectral signals. In addition, as the core optical component of a multispectral imaging system, an adjustable spectrometer can work in coordination with a CCD camera and a light source to construct a complete spectral imaging system, thus enabling accurate extraction of spectral features of samples.

[0037] The spectral reflection data of the cleaned eggshell surface is a set of multi-dimensional and high-precision optical information, specifically including: spectral reflection intensity, spectral curve, wavelength-reflectivity correspondence, angle-reflectivity correlation data, etc. For example, within the wavelength range of 400 - 1000 nm, an accurate reflectivity value is recorded every 10 nm, forming a spectral reflection data sequence containing 61 data points. These data not only reflect the color characteristics of the eggshell surface but also contain information on the microscopic surface structure, the physical composition of the eggshell, and the optical properties of the eggshell. The physical composition of the eggshell refers to its material composition and microscopic structural characteristics. Specifically, it includes the chemical composition of the eggshell (calcium carbonate, proteins, etc.), the microscopic structure of the surface (surface roughness and porosity), as well as changes in the density and thickness of the eggshell. The optical properties of the eggshell refer to the way it interacts with light, mainly including the reflection, absorption, and transmission characteristics of light, the difference in reflectivity of light of different wavelengths, and the degree of scattering and diffuse reflection of the surface to light. For example, for a brown eggshell, its spectral reflection data shows a relatively low reflectivity (15 - 20%) in the blue light region (about 450 nm), a moderate reflectivity (40 - 50%) in the green light region (about 550 nm), and a relatively high reflectivity (60 - 70%) in the red light region (about 650 nm). By analyzing these data, the optical properties of the eggshell surface, including indicators such as color uniformity, saturation, and lightness, can be accurately quantified.

[0038] S30: The computer device performs feature extraction and dimensionality reduction on the spectral reflection data of the eggshell surface to obtain a multi-dimensional eggshell color feature vector.

[0039] In this step, the computer device uses artificial intelligence algorithms for feature extraction and dimensionality reduction of spectral reflection data. First, the Principal Component Analysis (PCA) algorithm is used to perform dimensionality reduction on the spectral reflection data, retaining more than 95% of the information entropy. Then, combined with the Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM), color features are extracted to construct an eggshell color feature vector containing multi-dimensional information such as spectral features, reflectance distribution, and optical properties. During the feature extraction process, the spectral data is normalized and learned and transformed through a multi-layer neural network, and finally a feature vector with a dimension of 32 - 64 is generated.

[0040] S40: The computer device obtains the color quality grade of the eggshell surface according to the multi-dimensional eggshell color feature vector and the trained eggshell color quality evaluation model.

[0041] In this step, the computer device calls the pre-trained eggshell color quality evaluation model, which is trained based on a large-scale eggshell sample data set through transfer learning and / or ensemble learning methods. The input of the model is the multi-dimensional eggshell color feature vector generated in step S30, and a Support Vector Machine (SVM) or Random Forest ensemble algorithm is used for classification. The eggshell color quality evaluation model can pre-define the following five color quality grades: excellent (Grade A), good (Grade B), medium (Grade C), fair (Grade D), and unqualified (Grade E). According to the distance and similarity between the eggshell color feature vector and the samples of each grade, the color quality grade of the eggshell surface is finally output, and a confidence score is given.

[0042] In the embodiment of the present invention, through the organic integration of the multi-modal collaborative cleaning system on the eggshell surface, multi-spectral imaging technology, intelligent feature extraction and dimensionality reduction algorithms, and machine learning evaluation models, intelligent, precise, and objective detection of eggshell color quality is achieved. The multi-modal cleaning system ensures high-quality preprocessing of the eggshell surface and eliminates the influence of interference factors; multi-spectral imaging technology can capture the subtle features of microscopic color changes on the eggshell surface; artificial intelligence algorithms transform massive spectral data into highly concentrated color feature vectors through complex feature extraction and dimensionality reduction processing; the evaluation model trained based on a large-scale sample achieves automated, standardized, and precise grading of eggshell color quality. This technical path not only improves the detection efficiency, shortening the manual detection cycle from several minutes to the second level, but also reduces the interference of human subjective factors and enhances the objectivity and accuracy of eggshell color quality evaluation.

[0043] Embodiment 2

[0044] As Figure 2 shown, the multi-modal collaborative cleaning system on the eggshell surface specifically includes:

[0045] A directional air flow cleaning module, the directional air flow cleaning module has adjustable air flow parameters, and the air flow parameters include an air flow injection angle and an air flow pressure;

[0046] An electrostatic adsorption cleaning module, the electrostatic adsorption cleaning module is composed of an electrostatic fiber cloth installed at the end of the robotic arm, and adsorbs particles in the target particle size range on the eggshell surface through a preset electrostatic field strength;

[0047] An optical detection and feedback module, the optical detection and feedback module includes an industrial camera and an image processing module, the industrial camera is used to capture the image of the cleaning area on the eggshell surface in real time, the image processing module is used to quantify the cleaning effect according to the cleaning area image to obtain real-time feedback data, and the real-time feedback data includes at least one cleaning quality parameter such as the percentage of particle residual area, particle size distribution, surface dust density, and cleaning uniformity index;

[0048] A control module, which is used to adjust the air flow parameters of the directional air flow cleaning module and the electrostatic strength of the electrostatic adsorption cleaning module according to the real-time feedback data of the optical detection and feedback module.

[0049] Specifically, the directional air flow cleaning module is a precision air flow control device, which consists of a high-precision air pump, an adjustable nozzle and a pressure sensor. Each component is tightly connected through pipelines and a control system to form a complete air flow cleaning system. The function of the high-precision air pump is to generate a stable and controllable air flow to provide a power source for the cleaning process. The pressure sensor monitors the air flow pressure in real time to ensure the stability and accuracy of the cleaning process and prevent damage to the eggshell surface caused by abnormal air pressure. The air flow parameters of this directional air flow cleaning module include the injection angle and the air flow pressure. The injection angle can be accurately adjusted within the range of 0-90 degrees, and the air flow pressure range is 0.1-0.6 MPa. The nozzle is made of aviation-grade polymer materials and has air flow uniformity and precise directivity. Through the nozzle angle adjustment mechanism driven by a servo motor, precise air flow cleaning of different areas on the eggshell surface can be achieved, effectively removing loose particles and slightly attached stains on the surface.

[0050] Specifically, the electrostatic adsorption cleaning module uses a high-tech electrostatic fiber cloth as the cleaning medium. This fiber cloth is woven from nanoscale conductive fibers and has good electrostatic adsorption efficiency. The fiber cloth is installed at the end of a six-axis robotic arm, enabling 360-degree omnidirectional close proximity to the eggshell surface. The electrostatic field strength can be precisely adjusted within the range of 1 - 10 kV / cm, specifically for directional adsorption of particles with a particle size range of 1 - 100 microns. The electrostatic fiber cloth surface has a gradient electrostatic field distribution, which can effectively capture particles of different polarities and sizes, ensuring the comprehensiveness and precision of eggshell surface cleaning.

[0051] Specifically, the optical detection and feedback module is a highly intelligent image analysis system. The industrial camera uses a 20-megapixel color CCD sensor with a frame rate of up to 200 fps, and its spectral response range covers the visible and near-infrared spectra. The image processing module uses deep learning algorithms, with a built-in convolutional neural network and image segmentation model, capable of real-time extraction and analysis of eggshell surface cleaning images. The system can accurately calculate cleaning quality parameters such as the percentage of particle residue area (accuracy better than 0.1%), particle size distribution (recognition accuracy 1 micron), surface dust density (resolution 0.01 g / cm 2 ) and cleaning uniformity index (coefficient of variation < 5%).

[0052] In some embodiments, the process of obtaining the percentage of particle residue area specifically includes: First, capture a high-resolution image of the eggshell surface through an industrial camera and perform image preprocessing including denoising, contrast enhancement, and color normalization. Subsequently, use image segmentation algorithms such as threshold segmentation, edge detection, or machine learning semantic segmentation to accurately identify and extract the particle regions, which will be used for subsequent area calculation, size analysis, and cleaning quality assessment. The specific image segmentation algorithm is based on features such as color, texture, and brightness to distinguish particles from the eggshell background. By statistically calculating the total pixel area of the particles and comparing it with the total area of the eggshell surface image, it is finally converted into a percentage form accurate to two decimal places. The entire process requires preset threshold parameters for particle recognition, including color threshold, gray-scale contrast threshold, minimum particle recognition area, and shape feature threshold, to ensure the accuracy and consistency of the image segmentation algorithm and thus improve the reliability of particle region extraction.

[0053] In some embodiments, the process of obtaining the particle size distribution specifically includes: Based on particle recognition, perform fine geometric measurements. Use morphological processing algorithms to extract the contour and measure the area of each individual particle. Through precise pixel-level calculations, convert the area of each particle into an actual physical size. According to the preset size classification standard (for example, tiny < 0.1 mm 2 , small 0.1 - 0.5 mm 2 , medium 0.5 - 2 mm2 , greater than 2 mm 2 ), automatically classify the particles. Generate a detailed size distribution histogram showing the number and percentage of particles in each size class. The algorithm can also additionally provide shape characteristics of the particles, such as roundness, aspect ratio, and other supplementary information.

[0054] In some embodiments, the process of obtaining the surface dust density specifically includes: First, perform background correction and color normalization of the image to eliminate the influence of uneven illumination. Adopt a blob detection algorithm, such as a blob enhancement filter, a blob detection convolutional kernel, etc., to accurately locate and extract dust particles. Screen each detected particle to exclude noise points and artifacts. Determine effective dust particles based on pixel-level area and shape characteristics. Within a preset standard reference area (such as 1 square centimeter), count the number of particles and calculate the dust density. The blob detection algorithm can simultaneously output additional information such as the number of particles and the average size, providing a comprehensive dust distribution feature.

[0055] In some embodiments, the process of obtaining the cleaning uniformity index specifically includes: In the image preprocessing stage, a high-resolution image of the eggshell surface is obtained through an image acquisition device. After the image is obtained, necessary preprocessing is performed, including removing image noise, adjusting contrast, normalizing image brightness and color, etc., to ensure the image quality and consistency for subsequent analysis. In the grid division stage, the preprocessed image is divided into grids with equal spacing and equal size. The purpose of grid division is to evenly divide the entire eggshell surface into multiple regions, with each grid region having the same size. The fineness of grid division (i.e., grid size and quantity) needs to be reasonably set according to specific analysis requirements and image resolution. In the particle analysis stage, particle residue feature extraction is independently performed within each grid region. In this stage, mainly through image processing algorithms, particles in each grid are identified and analyzed, and key feature parameters are extracted, including particle coverage rate (the ratio of particle area to grid area), average gray level (reflecting the depth of particles), particle quantity, etc. These feature parameters will serve as the basic data for uniformity evaluation. In the statistical quantification stage, statistical methods such as the coefficient of variation (CV) are used to quantitatively analyze the particle feature parameters of different grid regions. The coefficient of variation quantifies the degree of dispersion of parameters in different regions by calculating the ratio of the standard deviation to the mean. Based on these statistical indicators, a cleaning uniformity index is constructed. The closer the value is to 0, the more uniform the cleaning degree. In the visualization and evaluation stage, combined with the spatial distribution characteristics of particles, a heat map is drawn to visually display the uneven cleaning regions on the eggshell surface. At the same time, the confidence interval of the difference between regions is calculated, which not only provides a more accurate uniformity evaluation but also enhances the statistical reliability of the results. Through visualization and confidence interval analysis, the cleaning uniformity can be understood more intuitively and accurately. In the result output stage, based on the foregoing analysis, a clear uniformity index and a detailed evaluation report are output. The report includes the uniformity index value, heat map, confidence interval analysis, etc.

[0056] Specifically, the control module is the intelligent scheduling center of the entire cleaning system, adopting an industrial-grade embedded processor and a real-time operating system. It receives the data from the optical detection feedback module in real time through a closed-loop feedback control strategy, and intelligently adjusts the injection angle and air flow pressure of the directional air flow cleaning module, as well as the electrostatic field strength of the electrostatic adsorption cleaning module according to a preset algorithm. The control algorithm is based on fuzzy control and adaptive learning algorithms, and can quickly respond (response time < 50ms) and accurately adjust the cleaning parameters to ensure that the eggshell surface is always in the best cleaning state.

[0057] The advantages of the above technical solution of the embodiment of the present invention are as follows: The directional airflow cleaning module solves the problem of non-uniformity in traditional single-airflow cleaning. Through adjustable airflow angles and pressures, precise cleaning of different areas on the eggshell surface is achieved, effectively removing loose particles and slightly attached stains. Secondly, the electrostatic adsorption cleaning module uses a nano-level electrostatic fiber cloth, solving the technical bottleneck that traditional mechanical cleaning methods are difficult to remove tiny particles. It can accurately capture particles in the size range of 1 - 100 microns, improving the depth and thoroughness of cleaning. Furthermore, the optical detection feedback module introduces high-precision industrial imaging and deep learning image analysis technologies, realizing quantitative and visual evaluation of the cleaning quality of the eggshell surface. Key parameters such as the percentage of particle residue area and size distribution can be accurately measured, and the detection accuracy reaches the sub-micron level. Finally, the intelligent control module realizes real-time dynamic adjustment of cleaning parameters through closed-loop feedback and adaptive learning algorithms. Not only does it greatly improve the cleaning efficiency, shortening the cycle of traditional manual cleaning from the minute level to the second level, but it also reduces the interference of human subjective factors.

[0058] Embodiment III

[0059] As Figure 3 shown, in one embodiment, the multispectral imaging system includes:

[0060] A light source module, which includes a multi-wavelength light source and an incident angle adjustment mechanism. The light source module is installed above the sample stage, maintaining a preset fixed distance from the eggshell surface. The multi-wavelength light source adjusts the incident angle through the incident angle adjustment mechanism to ensure that the specified wavelength light emitted can evenly cover the eggshell surface;

[0061] An imaging optical component, using a zoom lens, for adjusting the focal length and field of view parameters;

[0062] A spectroscope, which is used to decompose the composite spectrum reflected from the eggshell surface into monochromatic spectra of different wavelength channels corresponding to the blue light channel, green light channel, and red light channel based on the prism or grating principle; the reflected composite spectrum is the spectral characteristic after the incident spectrum is reflected from the eggshell surface;

[0063] An image sensor, specifically used to receive the monochromatic spectra decomposed by the spectroscope, convert the optical signals corresponding to the monochromatic spectra into digital image data, and record the spectral reflection data of the cleaned eggshell surface at each incident angle and each wavelength channel.

[0064] In this embodiment, the light source module is the excitation source of the multispectral imaging system, which consists of a high-precision multi-wavelength LED array, including light sources in three wavelength channels: blue light (460 - 480 nm), green light (520 - 540 nm), and red light (620 - 640 nm). The incident angle adjustment mechanism uses a two-dimensional adjustment platform driven by a precision stepper motor, which can accurately control the incident angle of the light source within the range of 0 - 75 degrees, and the angle adjustment accuracy reaches 0.1 degree. This module is installed on a specially designed sample stage bracket, and a precision optical bracket is used to ensure a constant working distance of 100 ± 2 mm from the eggshell surface. The design of the multi-wavelength light source can simulate the spectral characteristics of the eggshell surface under different lighting conditions, providing multi-dimensional spectral excitation for accurate imaging later.

[0065] In this embodiment, the imaging optical component selects an industrial-grade high-resolution zoom lens, which has a variable aperture of 1:1.4 - 1:22 and a continuous zoom range of 10 - 200 mm. The lens uses a multi-layer anti-reflection optical coating, which can effectively suppress optical stray light and chromatic aberration, ensuring the clarity and color reproduction of images at different magnification ratios. The focal length and field of view parameters can be adjusted in real time dynamically, and the minimum resolution can reach 2 microns / pixel, ensuring the accurate capture of the microstructures and particles on the eggshell surface. The lens is equipped with an autofocus and image stabilization function, which can quickly adapt to the small height changes on the eggshell surface.

[0066] In this embodiment, the spectrometer uses high-precision diffraction grating spectroscopy technology, which consists of a precision-machined quartz prism and grating, and can accurately decompose the composite spectrum into three wavelength channels: blue, green, and red. The spectral decomposition accuracy is better than 1 nm, and the optical transmittance is greater than 95%. Based on the Bragg diffraction principle, the spectrometer can accurately extract the reflection spectral characteristics of the eggshell surface at different wavelengths. By comparing the spectral data of different wavelength channels, the microstructures, stain distribution, and cleanliness of the eggshell surface can be effectively distinguished, providing multi-dimensional spectral information for image analysis.

[0067] In this embodiment, the image sensor uses back-illuminated CMOS technology, which has 20 million effective pixels, a global shutter, and high dynamic range characteristics. The sensor quantum efficiency exceeds 85% in all three wavelength channels of blue, green, and red, and the signal-to-noise ratio is greater than 50 dB. At each wavelength channel and incident angle, the sensor can capture spectral reflection data up to 16 bits, realizing the accurate digital recording of the micro-cleaning state of the eggshell surface. The data acquisition system is equipped with a high-speed data interface and a real-time image processing unit, which can complete the acquisition and preliminary analysis of a single multi-spectral image within 50 ms.

[0068] The multi-wavelength light source and adjustable incident angle mechanism of the light source module in the embodiments of the present invention enable the system to simulate different lighting conditions and incident angles, effectively revealing the hidden features of the microscopic structure and cleaning state of the eggshell surface, and overcoming the technical bottleneck that traditional single light sources are difficult to capture fine stains and surface defects. The high-precision variable focal length and field-of-view parameters of the zoom imaging optical component, combined with the high quantum efficiency and wide dynamic range of the back-illuminated CMOS image sensor, achieve precise capture and quantitative analysis of particles on the eggshell surface with a scale of 1-100 micrometers, and the image resolution can reach the sub-micrometer level. Based on precise optical decomposition technology, the spectrometer can accurately decompose the reflection spectrum into three wavelength channels of blue, green, and red. Through cross-comparison and in-depth analysis of multi-spectral data, not only can the cleaning effect be accurately quantified, but also the spectral evolution process of the eggshell surface before and after cleaning can be reconstructed. This system improves the intelligent level of eggshell cleaning quality assessment, transforming the traditional qualitative detection relying on manual experience into quantitative analysis based on spectral big data.

[0069] Embodiment 4

[0070] As Figure 4 shown, step S20 specifically includes the following steps:

[0071] S201: Initialize and calibrate the parameters of the multi-spectral imaging system, which includes setting the wavelength range of the light source module, adjusting the intensity of the multi-wavelength light source, confirming the accuracy of the incident angle adjustment mechanism, calibrating the focal length and field of view of the imaging optical component, detecting the spectral decomposition accuracy of the spectrometer, and calibrating the sensitivity and signal-to-noise ratio of the image sensor.

[0072] Specifically, the initialization and calibration of system parameters are the key links to ensure multi-spectral imaging accuracy. During the initialization process, first use a professional spectral calibrator to accurately calibrate the multi-wavelength light source. The wavelength range is set to blue light (460-480nm), green light (520-540nm), and red light (620-640nm). The light source intensity is precisely adjusted to 100±5 mA through an adjustable current control module. The incident angle adjustment mechanism uses a high-precision stepper motor, and the angle adjustment accuracy can reach 0.1 degree. A laser interferometer is used for angle calibration. The focal length and field of view of the imaging optical component are corrected at multiple points through a standard calibration plate to ensure the linearity and consistency of the imaging system. The spectral decomposition accuracy of the spectrometer is detected using a high-precision spectral standard source, and the resolution is better than 1nm. The sensitivity and signal-to-noise ratio of the image sensor are tested for dynamic range and quantum efficiency through professional image quality assessment software to ensure that the signal-to-noise ratio of each wavelength channel is greater than 50dB.

[0073] S202: Locate and fix the preprocessed eggshell sample at the exact center of the sample stage. Use the sample fixing fixture to press and limit the eggshell sample to ensure the surface of the eggshell sample is flat and without wobbling, and the surface of the eggshell sample is perpendicular to the optical axis of the imaging optical component or the angular deviation is controlled within ±5 to 10 degrees. By adjusting the height and tilt angle of the sample stage, make the surface of the eggshell sample form a geometric alignment position with the incident light of the light source module and the optical axis of the imaging optical component.

[0074] Specifically, sample positioning and fixation are the basis for ensuring imaging quality. An eggshell sample fixing fixture is adopted and precisely positioned by a precision numerically controlled robotic arm. The fixture uses a flexible silicone gasket that can apply pressure evenly and effectively suppress sample wobbling, and the fixing pressure is controlled between 50 - 100N. Through an electric adjustment stage, micron-level precise positioning of the sample stage in the vertical and horizontal directions is achieved. A laser alignment system is used to ensure the perpendicularity between the eggshell surface and the optical axis of the optical system, with an alignment accuracy better than 0.1 degree. The sample stage is equipped with a multi-degree-of-freedom adjustment mechanism to precisely control the angle between the sample surface and the incident light, achieving the best geometric alignment of the optical system. By using the sample fixing fixture to press and limit the preprocessed eggshell sample at the exact center of the sample stage, it can be ensured that the sample surface is flat and without wobbling. The perpendicular configuration of the eggshell sample surface and the optical axis of the imaging optical component can reduce geometric distortion, ensure imaging uniformity, reduce the complexity of the optical system, and improve measurement accuracy. Through this configuration, perspective distortion can be minimized to obtain more accurate spectral information. The adjustment of the height and tilt angle of the sample stage aims to establish an ideal optical configuration so that the incident light angle can evenly cover the eggshell surface, and the imaging optical component can capture the most complete and least distorted surface features. Through careful adjustment, a relatively optimized geometric position can be found to make the spectral reflection signal intensity and signal-to-noise ratio reach a better state.

[0075] S203: Adjust the incident angle of the light source module successively according to a preset number of incident angles. At each incident angle, emit light of a specified wavelength, including blue light, green light, and red light, from the multi-wavelength light source to the eggshell surface, and the distance between the light source module and the eggshell surface is maintained at a preset distance.

[0076] Specifically, the incident angle scanning adopts a preset angle sequence, including six angle points of 0°, 15°, 30°, 45°, 60°, and 75°. At each angle, the multi-wavelength light source emits blue, green, and red light of three wavelengths successively according to a predetermined time sequence and intensity, and the irradiation time for each wavelength is 50ms. The distance between the light source and the eggshell surface is fixed at 100 ± 2mm. Angle adjustment is achieved through a rotating platform controlled by a precision motor to ensure that the light source evenly covers the eggshell surface and minimize the impact of incident angle changes on spectral acquisition.

[0077] S204: After the light of a specified wavelength emitted by the light source module irradiates the eggshell surface, the zoom lens built in the imaging optical component collects and focuses the composite spectrum reflected from the eggshell surface. The zoom lens adjusts the focal length and field of view parameters to achieve imaging of the spectral reflection characteristics of the eggshell surface and capture the spectral reflection details at the microscopic scale of the eggshell surface. Among them, the imaging optical component faces the light source module and forms a preset included angle.

[0078] Specifically, the imaging optical component and the light source module form an included angle of about 45 degrees. An industrial-grade zoom lens is used, with a focal length range of 10 - 200 mm, which can be adjusted dynamically in real time. After the light of a specified wavelength irradiates the eggshell surface, the zoom lens captures the reflected composite spectrum through automatic focusing and aperture adjustment functions. The lens is equipped with a multi-layer anti-reflection optical coating, effectively suppressing optical stray light. The minimum resolution can reach 2 microns / pixel, and it can accurately capture the spectral reflection details at the microscopic scale of the eggshell surface.

[0079] S205: The collected composite spectrum is processed by a spectroscope installed between the imaging optical component and the image sensor. The spectroscope is based on the prism or grating principle and decomposes the composite spectrum into independent monochromatic spectra including blue light, green light, and red light. The image sensor converts the optical signals corresponding to the decomposed monochromatic spectra into digital image data for recording the reflection spectral intensity information at each incident angle and wavelength channel.

[0080] Specifically, the spectroscope uses a combination of a high-precision quartz prism and a diffraction grating to accurately decompose the composite spectrum into three wavelength channels of blue, green, and red. The spectral decomposition accuracy is better than 1 nm, and the optical transmittance is greater than 95%. The back-illuminated CMOS image sensor has 20 million effective pixels, and the quantum efficiency exceeds 85% in all three wavelength channels. The sensor uses global shutter technology and can complete high-speed acquisition and data conversion of single-shot multi-spectral images within 50 ms, recording the accurate reflection spectral intensity information at each incident angle and wavelength channel.

[0081] S206: Integrate the reflection spectral intensity data at each incident angle and each wavelength channel to construct a three-dimensional spectral data matrix including the incident angle, wavelength channel, and reflection spectral intensity value. The three-dimensional spectral data matrix is a standardized representation of the spectral reflectance data of the eggshell surface.

[0082] Specifically, the data processing uses a specially developed multi-dimensional spectral data processing algorithm to organize the reflection spectral intensity data at different incident angles and wavelength channels into a three-dimensional data matrix. The matrix dimensions are: incident angle (6) × wavelength channel (3) × reflection spectral intensity. Standardization processing technology is used to eliminate the systematic error of the optical system and construct a standardized representation of the eggshell surface spectral reflectance data with high comparability and repeatability. The data matrix can be directly used for subsequent machine learning and image analysis.

[0083] Specifically, the light source module and the imaging optical component are arranged at a 45° angle, and the optical axis of the imaging optical component forms a 45° angle with the incident light ray; the wavelength range of the light source module is 400 - 700 nm; the multiple incident angles of the light source module include: 0°, 15°, 30°, 45°, 60°, 75°; the distance between the light source module and the eggshell surface is maintained at 5 - 10 cm; the image sensor includes: a CCD image sensor or a CMOS image sensor; the three-dimensional spectral data matrix includes: incident angle information, wavelength channel information, and corresponding reflected spectral intensity values.

[0084] The method of the embodiment of the present invention overcomes the limitations of traditional single-wavelength and fixed-angle imaging. Through precise scanning of a multi-wavelength light source (blue, green, red) at different incident angles, it can reveal the hidden features of the microscopic structure and cleaning state of the eggshell surface in all directions and multiple dimensions, improving the detection sensitivity of stains and surface defects. The optical system design includes a high-precision incident angle adjustment mechanism, a zoom lens, and a spectroscope, enabling the system to capture spectral reflection details at the sub-micron scale and achieve precise analysis of particles on the eggshell surface with a size of 1 - 100 microns. By constructing a three-dimensional data matrix containing incident angles, wavelength channels, and reflected spectral intensities, not only can the cleaning effect be quantitatively evaluated, but also the spectral evolution process before and after cleaning the eggshell surface can be reconstructed, transforming the traditional qualitative detection relying on manual experience into quantitative analysis based on spectral big data.

[0085] Embodiment Five

[0086] As Figure 5 shown, step S30 specifically includes the following steps:

[0087] S301: Preprocess the original spectral reflection data with multiple incident angles and multiple wavelengths to obtain a three-dimensional spectral reflection data matrix after denoising and normalization transformation, where the preprocessing includes denoising and normalization transformation.

[0088] Specifically, in this step, the wavelet denoising algorithm is first applied to the original spectral reflectance data. Specifically, the Symlet 8 wavelet basis is used, and threshold denoising is performed at the 3rd - 4th layer of wavelet decomposition to effectively suppress instrument noise and random interference. The normalization transformation uses the Z - score transformation method, and the calculation formula is Z=(X - μ) / σ, where X is the original data, μ is the mean value, and σ is the standard deviation. Through the Z - score transformation, the spectral data of different incident angles and wavelength channels are mapped to the standard normal distribution, eliminating the data scale difference and providing a unified data benchmark. The denoising and normalization processing improve the signal - to - noise ratio and comparability of the data. As an example, the three - dimensional spectral reflectance data matrix can include: the first dimension is the incident angle (such as 0°, 15°, 30°, 45°), the second dimension is the wavelength (for example, 400 - 1000 nm, with an interval of 10 nm), and the third dimension is the reflectance value.

[0089] S302: Perform discrete wavelet transform multi - scale decomposition on the three - dimensional spectral reflectance data matrix to obtain a wavelet coefficient matrix.

[0090] Specifically, the discrete wavelet transform (DWT) adopts the multi - resolution analysis method, and the Daubechies wavelet basis (db4) is selected for multi - scale decomposition. Perform two - dimensional discrete wavelet transform on the three - dimensional spectral reflectance data matrix, and the decomposition level is set to 4 layers. The transformation process decomposes the original data into approximation coefficients and detail coefficients. The approximation coefficients reflect the low - frequency characteristics of the data, and the detail coefficients capture the local characteristics at different scales. The specific decomposition process includes the extraction of wavelet coefficients in the horizontal, vertical, and diagonal directions. The obtained wavelet coefficient matrix can effectively characterize the multi - scale characteristics of the spectral reflectance on the eggshell surface.

[0091] S303: Perform principal component analysis on the wavelet coefficient matrix after discrete wavelet transform, and identify and retain the principal components with the largest explained variance through the cumulative variance contribution rate threshold.

[0092] Specifically, principal component analysis is used for dimensionality reduction and feature extraction. After centering the mean value of the wavelet coefficient matrix, the covariance matrix is calculated to measure the linear correlation between features. Subsequently, the covariance matrix is subjected to eigenvalue decomposition to extract the principal components. The magnitude of the eigenvalue reflects the explanatory ability of each principal component for the data. According to the sorting of eigenvalues and the cumulative variance contribution rate threshold (85%), the first 20 - 30 principal components that can retain the main information are selected, and the original data is projected into a low - dimensional space to obtain the dimensionality - reduced feature data. This process not only effectively reduces the data dimension and the computational complexity of analysis, but also removes redundant and less - relevant features, while highlighting the key features related to the spectral reflectance information on the eggshell surface.

[0093] S304: Reconstruct the spectral reflectance curve using the spline interpolation method, and calculate the target spectral parameters based on the reconstructed spectral reflectance curve.

[0094] Specifically, the spline interpolation method is used to reconstruct the spectral reflectance curve. The cubic spline interpolation algorithm is selected, which has the characteristics of good continuity and smoothness. In the interpolation process, the discrete spectral reflection data points are first smoothed, and then the continuous reflectance curve is reconstructed through the spline function. The calculation of the target spectral parameters includes: average reflectance (calculating the arithmetic mean of the curve), standard deviation of reflectance (reflecting the degree of dispersion of the spectral distribution), peak reflectance (the maximum value of the curve), spectral curve entropy (measuring the complexity of the spectral distribution), and spectral asymmetry index (reflecting the skewness of the spectral curve). These parameters comprehensively describe the statistical characteristics of the spectral reflection on the eggshell surface.

[0095] S305: Construct a multi-dimensional eggshell color feature vector by integrating the wavelet coefficient matrix, the principal components, and the target spectral parameters.

[0096] Specifically, the feature vector construction adopts the information entropy and discrimination weighted fusion method. First, the wavelet coefficient matrix, the principal components, and the target spectral parameters are normalized. The minimum-maximum normalization method is used to map each feature to the interval [0, 1]. The weight coefficients are calculated based on the information entropy and discrimination of each feature. The information entropy of each feature is determined through the information entropy formula H = -Σ(p * log(p)), and the discrimination of the feature is determined through variance calculation. In addition, the discrimination is also calculated through the coefficient of variation (CV) of the eigenvalue. The calculation formula is: CV = (standard deviation / mean) * 100%. Finally, through the weighted summation method, the normalized features are integrated into a 20-30 dimensional eggshell color feature vector. The weight assignment fully considers the information content and discrimination ability of each feature, ensuring that the constructed feature vector can accurately represent the spectral characteristics of the eggshell surface. The target spectral parameters include at least one of the following: average reflectance, standard deviation of reflectance, peak reflectance, spectral curve entropy, spectral asymmetry index.

[0097] In the embodiments of the present invention, signal processing technologies such as wavelet transform, principal component analysis, and spline interpolation are integrated into the extraction of eggshell spectral features, achieving multi-dimensional and multi-scale precise capture of the microscopic spectral features on the eggshell surface. Through wavelet denoising and normalization transformation, instrument noise and data inconsistency are effectively suppressed, improving data quality; the discrete wavelet multi-scale decomposition technology can capture both the macroscopic and microscopic features of the spectral reflection on the eggshell surface, breaking through the limitations of traditional single-scale analysis; principal component analysis compresses high-dimensional spectral data to 20 - 30 dimensions, significantly reducing the computational complexity while retaining key information. Spline interpolation reconstructs the spectral reflectance curve, and through multi-dimensional parameters such as average reflectance, entropy, and asymmetry, comprehensively characterizes the statistical attributes of the spectral features on the eggshell surface. The weighted fusion strategy dynamically adjusts the feature weights based on information entropy and discrimination, and the constructed 20 - 30-dimensional eggshell color feature vector not only has high information concentration but can also accurately reflect the changes in the cleanliness state of the eggshell surface, providing an intelligent solution for the quality control of egg processing.

[0098] Embodiment 6

[0099] As Figure 6 shown, the method further includes the following steps:

[0100] S50: According to the spectral reflection data on the eggshell surface, through a spectral analysis algorithm, obtain a description of the eggshell color features.

[0101] Specifically, the spectral analysis algorithm adopts a multi-feature fusion method, and first deeply analyzes the obtained eggshell color feature vector. In specific implementation, two machine learning algorithms, Support Vector Machine (SVM) and Random Forest (RF), are selected for feature mapping and classification. The algorithm process includes:

[0102] S51: Construct a spectral feature space. In the first step of the spectral analysis algorithm, the 20 - 30-dimensional eggshell color feature vector is used as input data. The purpose of this step is to establish a multi-dimensional feature space, providing a representative data basis for subsequent machine learning algorithms. The feature vector contains various dimensional information of the spectral reflection on the eggshell surface.

[0103] S52: Select the optimal classification hyperparameters through the cross-validation method. In this step, two machine learning algorithms, Support Vector Machine (SVM) and Random Forest (RF), will compare their performance and tune parameters through the cross-validation method. Cross-validation techniques will be used to evaluate the classification performance of the two algorithms under different hyperparameter combinations, and select the algorithm and parameter configuration that can most accurately capture the eggshell color features.

[0104] S53: Based on the eggshell color feature vector, construct an eggshell color quality recognition model. Based on the preparatory work in the previous two steps, the optimized SVM algorithm or RF algorithm will be used to construct a color quality recognition model according to the eggshell color feature vector. This model will focus on extracting and analyzing key features such as spectral curve entropy and asymmetry index, which can sensitively capture the subtle changes in the microscopic structure and cleanliness of the eggshell surface. The model will finally output quantitative descriptions such as color uniformity score, cleanliness index, and spectral consistency score, providing precise quantitative indicators for eggshell quality assessment.

[0105] The spectral analysis algorithm focuses on the key information in the feature vector, such as spectral curve entropy, asymmetry index, etc., which can sensitively capture the subtle changes in the microscopic structure and cleanliness of the eggshell surface. The algorithm output includes quantitative descriptions of color features, such as color uniformity score, cleanliness index, spectral consistency score, etc.

[0106] S60: Generate an eggshell surface color quality assessment report according to the eggshell color quality grade and the eggshell color feature description.

[0107] Specifically, the generation of the eggshell surface color quality assessment report adopts intelligent templates and automated reporting techniques. The report generation process first conducts multi-dimensional evaluations based on the feature descriptions output by the spectral analysis algorithm and in combination with the preset quality grade standards. The report template includes the following key contents: a basic information module that records the egg product batch, detection time, and detection equipment parameters; a spectral feature analysis module that details the quantitative analysis results of the color feature vector, including the numerical values of each dimension feature and a radar chart visualization display; a quality grade evaluation module that maps the spectral features to predefined quality grades (such as excellent, good, qualified, unqualified) based on a pre-trained machine learning model; an anomaly detection module that marks and details the spectral features deviating from the normal range; and a suggestions and conclusions module that provides corresponding processing suggestions for different quality grades. The report is in an interactive electronic document format, supporting PDF and customizable visualization charts, facilitating quick understanding and further analysis.

[0108] In the embodiments of the present invention, through the spectral analysis algorithm and intelligent report generation technology, the intelligent, precise, and interpretable level of eggshell surface color quality assessment is improved. The spectral analysis method of multi-feature fusion avoids the limitations of traditional single-feature evaluation. Through machine learning algorithms such as support vector machines and random forests, it can accurately capture the subtle changes in microscopic spectral features from a 20-30-dimensional eggshell color feature vector, achieving high-precision quantitative evaluation of the cleanliness and uniformity of the eggshell surface. The intelligent report generation technology converts complex spectral data into intuitive and easy-to-read visualization reports, which not only provide quantitative quality grade evaluations but can also intelligently identify abnormal features and give targeted suggestions, greatly reducing the subjectivity and blindness of manual detection.

[0109] Example VI

[0110] As Figure 7 shown, the method further includes step S70, which comprises the following steps:

[0111] S71: Collect spectral reflection data of the surface of cleaned eggshells of multiple breeds, multiple breeding environments, and multiple growth stages through a multispectral imaging system, and establish an eggshell color quality standard database containing eggshell color feature vectors and corresponding eggshell surface color quality grade labels.

[0112] Specifically, in specific implementation, 3-5 main egg chicken breeds including blue-shell chickens, brown-shell chickens, and white-shell chickens were selected, covering different breeding environments such as large-scale farms, ecological farms, and household free-range farming, and different growth stages of chickens from the chick stage, adult stage to the peak egg production stage were tracked. The multispectral imaging system uses a high-precision spectrometer with a wavelength range of 400-1000 nm, and each sample is photographed with no less than 50 high-resolution images under multiple angles and multiple lighting conditions. The data collection process strictly controls the environmental temperature (20-25 °C), humidity (45%-55%), and lighting conditions to ensure the standardization and comparability of the data. The finally established database contains 1000-5000 samples, and each sample records detailed spectral reflection data, color feature vectors, and eggshell surface color quality grade labels evaluated by experts.

[0113] S72: Preprocess the feature vectors in the eggshell color quality standard database. The preprocessing includes missing value processing, outlier detection processing, feature standardization processing, and feature dimensionality reduction processing to obtain a normalized feature matrix.

[0114] Specifically, the missing value processing uses the multiple imputation method, and the mean, median, or Gaussian distribution is randomly imputed according to the statistical characteristics of the samples; the outlier detection combines box plot analysis and Mahalanobis distance method to identify and process extreme data points exceeding 3 standard deviations; the feature standardization uses the Z-score standardization method to map each dimension feature to a standard normal distribution with a mean of 0 and a variance of 1; the feature dimensionality reduction uses the principal component analysis (PCA) technique to compress the 20-30 dimensional feature vector to 5-10 principal components while retaining more than 95% of the original information, which not only reduces the computational complexity but also retains the key information. The preprocessed normalized feature matrix not only eliminates data noise but also improves the data quality for model training.

[0115] S73: Take the normalized feature matrix as training data, select the radial basis kernel function, and construct and optimize the eggshell color quality evaluation model through grid search and cross-validation methods to ensure that the model can be directly applied to the spectral reflection data of the surface of cleaned eggshells.

[0116] Specifically, the radial basis kernel function (RBF) support vector machine (SVM) is used to construct the eggshell color quality assessment model. This method is particularly suitable for dealing with non-linear classification problems. During the grid search process, the system traversed the range of the penalty parameter C [10 -3 , 10 3 and the range of the kernel function parameter γ [10 -3 , 10 3 , and selected the optimal parameter combination through the 5-fold cross-validation method. 80% of the data was used as the training set and 20% as the validation set for model training. The evaluation metrics included accuracy, precision, recall, and F1 score. The classification accuracy of the final model on the validation set reached over 92%, which was better than the traditional linear classification method. The model can not only be directly applied to the spectral reflection data of the cleaned eggshell surface, but also has good generalization ability and can adapt to the eggshell color quality assessment of different varieties and different breeding environments.

[0117] In an alternative embodiment, for the eggshell color quality assessment, random forest and gradient boosting trees (such as XGBoost) can be used. These two ensemble learning algorithms are suitable for dealing with non-linear complex data and can capture the complex relationships between features. For a data set with obvious non-linear features such as spectral reflection data, these algorithms can provide more robust classification performance through the integration of multiple decision trees. In other alternative ways, deep learning methods can be used. For the eggshell color quality assessment, the convolutional neural network (CNN) and the recurrent neural network (RNN) each have their own characteristics. CNN is good at capturing local features and spatial dependencies, and can automatically extract the key feature patterns in the spectral reflection data through convolutional and pooling layers, and is particularly suitable for dealing with data with spatial or spectral correlations. While RNN, especially the long short-term memory network (LSTM), is good at dealing with sequence data and can capture the temporal or continuous change features in the spectral reflection data.

[0118] In some embodiments, in step S72, the median filling or multiple imputation method is used for missing value processing; the box plot or interquartile range method is used for outlier detection; the Z-score normalization or min-max normalization method is used for feature normalization processing; the principal component analysis or mutual information method is used for feature dimensionality reduction processing to screen key features; in step S73, the grid search and cross-validation method are used to tune the penalty parameter C and the kernel function parameter γ.

[0119] In the embodiments of the present invention, through comprehensive data collection across different breeds, breeding environments, and multiple growth stages, a standard database of eggshell color feature vectors is established, which is superior to the traditional limited evaluation methods under a single breed and single environment. Secondly, multi-dimensional data preprocessing techniques including missing value handling, outlier detection, feature standardization, and dimensionality reduction are proposed, effectively eliminating data noise and extracting the key features of eggshell color quality. Furthermore, by using a radial basis kernel function support vector machine and combining grid search and cross-validation methods, an eggshell color quality evaluation model with high accuracy and strong generalization ability is constructed. Not only is the classification accuracy improved, but it can also be directly applied to the spectral reflection data of eggshell surfaces from different sources.

[0120] Embodiment 8

[0121] As Figure 8 shown, a system for evaluating the surface color quality of eggshells based on color reflection includes:

[0122] A multi-modal collaborative cleaning system for the eggshell surface, used to clean the eggshell surface to obtain a cleaned eggshell surface;

[0123] A multi-spectral imaging system, used to capture spectral features of the cleaned eggshell surface to obtain spectral reflection data of the cleaned eggshell surface;

[0124] A computer device, used to extract features and reduce the dimension of the spectral reflection data of the eggshell surface to obtain multi-dimensional eggshell color feature vectors; and to obtain the surface color quality grade of the eggshell according to the multi-dimensional eggshell color feature vectors and a trained eggshell color quality evaluation model.

[0125] In a further embodiment, the multi-modal collaborative cleaning system for the eggshell surface specifically includes:

[0126] A directional air flow cleaning module, the directional air flow cleaning module having adjustable air flow parameters, the air flow parameters including air flow injection angle and air flow pressure;

[0127] An electrostatic adsorption cleaning module, the electrostatic adsorption cleaning module being composed of an electrostatic fiber cloth installed at the end of a robotic arm, and adsorbing particles on the eggshell surface within a target particle size range through a preset electrostatic field strength;

[0128] An optical detection and feedback module, the optical detection and feedback module including an industrial camera and an image processing module, the industrial camera being used to capture images of the cleaned area on the eggshell surface in real time, and the image processing module being used to quantify the cleaning effect according to the images of the cleaned area to obtain real-time feedback data, the real-time feedback data including at least one cleaning quality parameter such as the percentage of particle residue area, particle size distribution, surface dust density, and cleaning uniformity index;

[0129] A control module, configured to adjust the air flow parameters of the directional air flow cleaning module and the electrostatic strength of the electrostatic adsorption cleaning module according to the real-time feedback data of the optical detection feedback module.

[0130] In a further embodiment, the multispectral imaging system specifically includes:

[0131] A light source module, which includes a multi-wavelength light source and an incident angle adjustment mechanism. The light source module is installed above the sample stage and maintains a preset fixed distance from the eggshell surface. The multi-wavelength light source adjusts the incident angle through the incident angle adjustment mechanism to ensure that the specified wavelength light emitted can uniformly cover the eggshell surface;

[0132] An imaging optical component, using a zoom lens, for adjusting the focal length and field of view parameters;

[0133] A spectrometer, for decomposing the reflected composite spectrum into monochromatic spectra of different wavelength channels corresponding to the blue light channel, green light channel, and red light channel based on the principle of prism or grating; the reflected composite spectrum is the spectral characteristic after the incident spectrum is reflected by the eggshell surface;

[0134] An image sensor, specifically configured to receive the monochromatic spectra decomposed by the spectrometer, convert the optical signals corresponding to the monochromatic spectra into digital image data, and record the spectral reflection data of the cleaned eggshell surface at each incident angle and each wavelength channel.

[0135] In a further embodiment, the computer device specifically includes:

[0136] A data preprocessing module, for performing denoising processing and normalization transformation on the original spectral reflection data of multiple incident angles and multiple wavelengths;

[0137] A feature extraction module, for performing discrete wavelet transform multi-scale decomposition on the preprocessed spectral reflection data and performing principal component analysis;

[0138] A feature vector construction module, for constructing a multi-dimensional eggshell color feature vector based on the wavelet coefficient matrix, principal components, and target spectral parameters.

[0139] In a further embodiment, the computer device further includes:

[0140] A color feature description module, for describing the features of the spectral reflection data on the eggshell surface through a spectral analysis algorithm;

[0141] An evaluation report generation module, for generating an evaluation report on the color quality of the eggshell surface according to the eggshell color quality grade and the eggshell color feature description.

[0142] In a further embodiment, the system further includes:

[0143] A database construction module, which is used to collect spectral reflection data on the surface of cleaned eggshells of multiple varieties, multiple breeding environments, and multiple growth stages through a multispectral imaging system, and establish an eggshell color quality standard database containing eggshell color feature vectors and corresponding eggshell surface color quality grade labels;

[0144] A data preprocessing module, which is used to perform missing value processing, outlier detection processing, feature standardization processing, and feature dimension reduction processing on the feature vectors in the eggshell color quality standard database to obtain a normalized feature matrix;

[0145] A model training module, which is used to use the normalized feature matrix as training data, select a radial basis kernel function, and construct and optimize an eggshell color quality evaluation model through grid search and cross-validation methods.

[0146] Compared with traditional detection methods, the technical solution of the embodiment of the present invention can improve the detection accuracy and speed, and greatly reduce the labor cost. Through precise spectral sensors and data processing algorithms, the embodiment of the present invention can capture tiny color differences that cannot be recognized by traditional methods, and improve the accuracy and objectivity of eggshell color quality evaluation.

[0147] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In practical applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0148] Embodiment Nine

[0149] As Figure 9 shown, the embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, each step of the above-mentioned method for evaluating the surface color quality of eggshells based on color reflection is implemented.

[0150] When the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. Of course, there are other ways of readable storage media, such as quantum memory, graphene memory, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice within the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0151] Embodiment Ten

[0152] As Figure 10 shown, an embodiment of the present invention further provides an electronic device, which includes one or more processors 901, a communication interface 902, a memory 909, and a communication bus 904. Among them, the processor 901, the communication interface 902, and the memory 903 communicate with each other through the communication bus 904.

[0153] The memory 909 is used to store a computer program;

[0154] The processor 901 is used to implement the steps of the above-mentioned method for evaluating the color quality of the eggshell surface based on color reflection when executing the program stored on the memory 903.

[0155] The processor 901 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0156] The memory 903 can include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 909 can include a Hard Disk Drive (HDD), a floppy disk drive, a flash memory, an optical disc, a magneto-optical disc, a magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. In a suitable case, the memory 903 can include removable or non-removable (or fixed) media. In a particular embodiment, the memory 903 is a non-volatile solid-state memory. In a particular embodiment, the memory 903 includes a Read-Only Memory (ROM). In a suitable case, the ROM can be a mask-programmed ROM, a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), an Electrically Rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0157] The communication bus 904 includes hardware, software, or both, for coupling the above components to each other. By way of example, the bus can include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front-Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or a combination of two or more of these. In a suitable case, the bus can include one or more buses. Although the embodiments of the present invention describe and illustrate specific buses, the present invention contemplates any suitable bus or interconnect.

[0158] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0159] Although this application provides method operation steps such as in the embodiments or flowcharts, based on routine or non-creative labor, there may be more or fewer operation steps. The order of steps listed in the embodiments is only one way among many orderings of steps executed and does not represent the only execution order. When actually implemented in a device or client product, it can be executed in the order of the method shown in the embodiments or the drawings or in parallel (such as in an environment with parallel processors or multithreaded processing).

[0160] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows 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 the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0161] These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0162] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0163] In this invention, specific embodiments are used to elaborate on the principles and implementation manners of the invention. The description of the above embodiments is only used to help understand the method and its core idea of the invention; at the same time, for those of ordinary skill in the art, according to the idea of the invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the invention.

Claims

1. A method for evaluating eggshell surface color quality based on color reflection, characterized in that: The following steps are involved: S10: cleaning the eggshell surface by the eggshell surface multimodal collaborative cleaning system to obtain a cleaned eggshell surface; S20: using a multispectral imaging system to capture spectral features of the cleaned eggshell surface to obtain spectral reflectance data of the cleaned eggshell surface; S30: performing feature extraction and dimensionality reduction on the spectral reflectance data of the eggshell surface by a computer device to obtain a multi-dimensional eggshell color feature vector; S40: obtaining, by a computer device, an eggshell surface color quality grade based on the multi-dimensional eggshell color feature vector and the trained eggshell color quality assessment model; The eggshell surface multimodal collaborative cleaning system specifically includes: A directional airflow cleaning module having adjustable airflow parameters, including an airflow injection angle and airflow pressure; the directional airflow cleaning module comprises an air pump, an adjustable nozzle, and a pressure sensor; the air pump is used to generate an airflow with controllable airflow pressure; the pressure sensor is used to monitor the airflow pressure in real time; and the airflow injection angle of the adjustable nozzle can be adjusted; An electrostatic adsorption cleaning module, comprising an electrostatic fiber cloth mounted on the end of a robotic arm, which adsorbs particles within a target size range from the eggshell surface using a preset electrostatic field strength; An optical detection feedback module includes an industrial camera and an image processing module. The industrial camera is used to capture images of the clean area on the eggshell surface in real time. The image processing module is used to quantify the cleaning effect based on the clean area images to obtain real-time feedback data. The real-time feedback data includes the percentage of residual particle area, particle size distribution, surface dust density, and cleaning uniformity index. a control module, configured to adjust the airflow parameters of the directional airflow cleaning module and the electrostatic intensity of the electrostatic adsorption cleaning module according to the real-time feedback data of the optical detection feedback module; The multispectral imaging system comprises: A light source module includes a multi-wavelength light source and an incident angle adjustment mechanism. The light source module is installed above the sample stage and maintains a preset fixed distance from the eggshell surface. The multi-wavelength light source adjusts the incident angle through the incident angle adjustment mechanism to ensure that the emitted light of the specified wavelength can evenly cover the eggshell surface. The multi-wavelength light source includes light sources of three wavelength channels: blue light, green light, and red light. Imaging optical components, using a zoom lens to adjust focal length and field of view parameters; The spectrometer is configured to decompose the composite spectrum reflected from the eggshell surface into monochromatic spectra of different wavelength channels corresponding to a blue light channel, a green light channel, and a red light channel based on a prism or grating principle; the reflected composite spectrum is a spectral characteristic of the incident spectrum after being reflected from the eggshell surface; The image sensor is specifically used to receive the monochromatic spectrum decomposed by the spectrometer, convert the optical signal corresponding to the monochromatic spectrum into digital image data, and record the spectral reflectance data of the cleaned eggshell surface at each incident angle and each wavelength channel.

2. The method according to claim 1, characterized in that Step S20 specifically includes: S201: Initializing and calibrating the parameters of the multispectral imaging system, including setting the wavelength range of the light source module, adjusting the intensity of the multi-wavelength light source, confirming the accuracy of the incident angle adjustment mechanism, calibrating the focal length and field of view of the imaging optical component, detecting the spectral decomposition accuracy of the spectrometer, and calibrating the sensitivity and signal-to-noise ratio of the image sensor; S202: Positioning and fixing the pretreated eggshell sample in the center of the sample stage, using a sample fixing fixture to compress and limit the eggshell sample, ensuring that the surface of the eggshell sample is flat and without shaking, and the surface of the eggshell sample is perpendicular to the optical axis of the imaging optical component, and by adjusting the height and tilt angle of the sample stage, the surface of the eggshell sample is geometrically aligned with the incident light of the light source module and the optical axis of the imaging optical component; S203: adjusting the incident angle of the light source module in sequence according to a plurality of preset incident angles, emitting light of a specified wavelength, including blue light, green light, and red light, toward the eggshell surface through the multi-wavelength light source at each incident angle, with the light source module maintaining a preset distance from the eggshell surface; S204: When the light of the specified wavelength emitted by the light source module illuminates the eggshell surface, the zoom lens built into the imaging optical assembly collects and focuses the composite spectrum reflected from the eggshell surface, and the zoom lens achieves imaging of the spectral reflection characteristics of the eggshell surface by adjusting the focal length and field of view parameters; wherein the imaging optical assembly and the light source module are opposite to each other, forming a preset angle; S205: Processing the collected composite spectrum through a spectrometer installed between the imaging optical assembly and the image sensor. The spectrometer decomposes the composite spectrum into independent monochromatic spectra including blue light, green light, and red light based on the principle of prism or grating. The image sensor converts the optical signals corresponding to the decomposed monochromatic spectra into digital image data for recording the reflected spectrum intensity information at each incident angle and wavelength channel. S206: Integrate the reflection spectrum intensity data at each incident angle and each wavelength channel to construct a three-dimensional spectrum data matrix including the incident angle, wavelength channel and reflection spectrum intensity value. The three-dimensional spectrum data matrix is a standardized representation of the eggshell surface spectral reflectance data.

3. The method according to claim 2, characterized in that Include at least one of the following: The light source module is arranged at an angle of 45° to the imaging optical component, and the optical axis of the imaging optical component forms an angle of 45° with the incident light; The wavelength range of the light source module is 400-700nm; The multiple incident angles of the light source module include: 0°, 15°, 30°, 45°, 60°, and 75°; The distance between the light source module and the eggshell surface is maintained at 5-10 cm; The image sensor includes: a CCD image sensor or a CMOS image sensor; The three-dimensional spectrum data matrix includes: incident angle information, wavelength channel information, and corresponding reflection spectrum intensity values.

4. The method according to claim 1, wherein Step S30 specifically includes: S301: Preprocessing original spectral reflectance data of multiple incident angles and multiple wavelengths to obtain a three-dimensional spectral reflectance data matrix that has undergone denoising and normalization transformation, wherein the preprocessing includes denoising and normalization transformation; S302: performing discrete wavelet transform multi-scale decomposition on the three-dimensional spectral reflectance data matrix to obtain a wavelet coefficient matrix; S303: performing principal component analysis on the wavelet coefficient matrix after the discrete wavelet transform, identifying and retaining the principal component with the largest explained variance through a cumulative variance contribution rate threshold; S304: reconstructing a spectral reflectance curve using a spline interpolation method, and calculating target spectral parameters based on the reconstructed spectral reflectance curve; the target spectral parameters include at least one of the following: average reflectance, reflectance standard deviation, peak reflectance, spectral curve entropy, and spectral asymmetry index; S305: Combining the wavelet coefficient matrix, the principal components, and the target spectral parameters, constructing a multi-dimensional eggshell color feature vector; step S305 specifically includes: normalizing the wavelet coefficient matrix, the principal components, and the target spectral parameters, and integrating the normalized wavelet coefficient matrix, the principal components, and the target spectral parameters into a 20-30 dimensional eggshell color feature vector through a weighted fusion method, wherein the weighted fusion determines the weight coefficient based on the information entropy and discrimination corresponding to the wavelet coefficient matrix, the principal components, and the target spectral parameters, respectively.

5. The method according to claim 4, characterized in that The standardized transformation includes normalization or Z-score transformation; The principal component analysis compresses high-dimensional spectral data to 20-30 dimensions.

6. The method according to claim 1, characterized in that Also includes: S50: Obtaining a description of the eggshell color characteristics through a spectral analysis algorithm based on the spectral reflectance data of the eggshell surface; S60: Generate an eggshell surface color quality assessment report based on the eggshell surface color quality grade and the eggshell color feature description; wherein the eggshell surface color quality assessment report includes the following contents: a basic information module, which records the egg batch, detection time and detection equipment parameters; a spectral feature analysis module, which presents the quantitative analysis results of the eggshell color feature vector; a quality grade assessment module, which maps the spectral features to predefined quality grades based on a pretrained machine learning model; and an anomaly detection module, which marks and explains spectral features that deviate from the normal range.

7. The method according to claim 1, characterized in that The method further comprises the steps of: S71: collecting spectral reflectance data of cleaned eggshell surfaces of multiple varieties, multiple breeding environments, and multiple growth stages through a multispectral imaging system, and establishing an eggshell color quality standard database including eggshell color feature vectors and corresponding eggshell surface color quality grade labels; S72: Preprocessing the feature vectors in the eggshell color quality standard database, wherein the preprocessing includes missing value processing, outlier detection processing, feature standardization processing, and feature dimensionality reduction processing to obtain a normalized feature matrix; S73: Using the normalized feature matrix as training data, selecting a radial basis kernel function, and constructing and tuning an eggshell color quality assessment model through a grid search and cross-validation method to ensure that the model can be directly applied to the spectral reflectance data of the eggshell surface after cleaning.

8. A system for evaluating eggshell surface color quality based on color reflection, characterized in that: include: An eggshell surface multimodal collaborative cleaning system is used to clean the eggshell surface to obtain a cleaned eggshell surface; A multispectral imaging system is used to capture spectral characteristics of the cleaned eggshell surface and obtain spectral reflectance data of the cleaned eggshell surface; A computer device is used to perform feature extraction and dimensionality reduction on the spectral reflectance data of the eggshell surface to obtain a multi-dimensional eggshell color feature vector; and obtain an eggshell surface color quality grade based on the multi-dimensional eggshell color feature vector and a trained eggshell color quality assessment model; The eggshell surface multimodal collaborative cleaning system specifically includes: A directional airflow cleaning module having adjustable airflow parameters, including an airflow injection angle and airflow pressure; the directional airflow cleaning module comprises an air pump, an adjustable nozzle, and a pressure sensor; the air pump is used to generate an airflow with controllable airflow pressure; the pressure sensor is used to monitor the airflow pressure in real time; and the airflow injection angle of the adjustable nozzle can be adjusted; An electrostatic adsorption cleaning module, comprising an electrostatic fiber cloth mounted on the end of a robotic arm, which adsorbs particles within a target size range from the eggshell surface using a preset electrostatic field strength; An optical detection feedback module includes an industrial camera and an image processing module. The industrial camera is used to capture images of the clean area on the eggshell surface in real time. The image processing module is used to quantify the cleaning effect based on the clean area images to obtain real-time feedback data. The real-time feedback data includes the percentage of residual particle area, particle size distribution, surface dust density, and cleaning uniformity index. a control module, configured to adjust the airflow parameters of the directional airflow cleaning module and the electrostatic intensity of the electrostatic adsorption cleaning module according to the real-time feedback data of the optical detection feedback module; The multispectral imaging system comprises: A light source module includes a multi-wavelength light source and an incident angle adjustment mechanism. The light source module is installed above the sample stage and maintains a preset fixed distance from the eggshell surface. The multi-wavelength light source adjusts the incident angle through the incident angle adjustment mechanism to ensure that the emitted light of the specified wavelength can evenly cover the eggshell surface. The multi-wavelength light source includes light sources of three wavelength channels: blue light, green light, and red light. Imaging optical components, using a zoom lens to adjust focal length and field of view parameters; The spectrometer is configured to decompose the composite spectrum reflected from the eggshell surface into monochromatic spectra of different wavelength channels corresponding to a blue light channel, a green light channel, and a red light channel based on a prism or grating principle; the reflected composite spectrum is a spectral characteristic of the incident spectrum after being reflected from the eggshell surface; The image sensor is specifically used to receive the monochromatic spectrum decomposed by the spectrometer, convert the optical signal corresponding to the monochromatic spectrum into digital image data, and record the spectral reflectance data of the cleaned eggshell surface at each incident angle and each wavelength channel.

Images