A car paint color recognition and classification method combining hyperspectral and support vector

Abstract

A method for identifying and classifying automotive paint film colors that combines hyperspectral and support vector imaging technology relates to the fields of computer vision and machine learning. This method utilizes hyperspectral imaging technology to acquire detailed spectral information about automotive paint films. Advanced image processing algorithms extract spectral features of various paint film colors to form label vectors. These vectors are then fed into support vector machines and single-class support vector machine models for training and optimization. This constructs an efficient color classification model that accurately classifies automotive paint film colors into multiple preset categories and effectively screens out anomalous color samples. This method boasts rapid recognition, high accuracy, and strong adaptability. It is widely applicable to the automotive manufacturing, maintenance, insurance, and used car appraisal industries, providing a novel solution for the automated identification and classification of automotive colors.

Description

Technical Field

[0001] The present invention relates to the technical field of computer vision and machine learning, and in particular to a method for identifying and classifying automobile paint film colors by combining hyperspectral and support vectors. Background Art

[0002] Automotive paint films are a crucial factor influencing a vehicle's exterior quality. They protect the vehicle's body, enhance its aesthetics, and aid in the reflection and identification of vehicle information. Every year, automakers experience countless instances of material waste, increased costs, and customer loss due to paint coating errors. Therefore, accurate identification and classification of paint film colors is a critical step in automotive manufacturing and evaluation, crucial for improving production efficiency, reducing material waste, and enhancing product quality. Furthermore, accurate paint film color recognition can provide objective and consistent color information for applications such as automotive repair, insurance, and used car appraisals, offering standardized and automated solutions for related industries.

[0003] Currently, spectrophotometry (also known as spectral photometry) is the most widely used high-precision color measurement method. This method calculates tristimulus values ​​by measuring the spectral power of a sample, thereby determining the sample's chromaticity coordinates and other color parameters. Spectrophotometers offer high measurement accuracy and wide applicability, but they are expensive, capable of only performing single-point measurements on small areas, and have extremely strict requirements for surface smoothness, color distribution uniformity, and other characteristics of the sample being measured, as well as the lighting conditions during measurement. The measurement process is cumbersome and complex, resulting in low measurement efficiency.

[0004] Given that the materials inspected on automotive paint film color inspection lines are typically large, have varying curvatures, and vary in shape, maintaining consistent lighting conditions in the workshop makes it difficult for spectrophotometers to achieve the various color measurement conditions required for high-precision measurement, resulting in significant limitations. Furthermore, in recent years, the shortcomings of various traditional color measurement methods, including spectrophotometers, have become increasingly apparent in many complex color measurement scenarios. With the rapid development of hyperspectral recognition technology, hyperspectral color measurement technology has begun to emerge in the field of color measurement.

[0005] Compared with traditional color measurement methods, hyperspectral imaging technology can achieve "image and spectrum integration". Most hyperspectral cameras use "push-broom" imaging, which can obtain two-dimensional array information of the sample and spectral information of each pixel point, which is conducive to more comprehensive data analysis, making it easier to eliminate local errors. The acquired spectral information can be processed through various algorithms to greatly reduce the impact of factors such as ambient light or the complex characteristics of the material itself, thereby reducing the requirements for measurement conditions. In recent years, many scholars in related fields at home and abroad have proposed the application of hyperspectral color measurement methods to industries such as textiles, archaeology, and jewelry. However, their research results on the color characterization of experimental materials are mostly limited to the three-stimulus value colorimetric representation method under the CIE system, and have not completely overcome the shortcomings of traditional color measurement methods.

[0006] Through the above analysis, the problems and defects of the existing technology are as follows:

[0007] Good measurement accuracy can only be achieved when measuring the color of samples with a flat surface and uniform color distribution (such as textiles), which has great limitations in the workplace;

[0008] The working environment requirements for color measurement are relatively strict, and the measured data is often only applicable to the same working environment. Once the working environment changes, the previously obtained data will not be of much significance.

[0009] In summary, the present invention provides a method for identifying and classifying automobile paint film colors by combining hyperspectral and support vector. Summary of the Invention

[0010] In order to solve the problems existing in the prior art, the present invention provides a method for identifying and classifying automobile paint film colors by combining hyperspectral and support vector.

[0011] A method for identifying and classifying automobile paint film color by combining hyperspectral and support vector is implemented by the following steps:

[0012] Step 1: Select a variety of standard paint film color cards and divide them into seven groups, with four color cards in each group having similar colors. Set the imaging conditions under an experimental light source with uniform illumination, use a hyperspectral camera to image each group of color cards to obtain hyperspectral images of each group of color cards, and preprocess the hyperspectral images to obtain spectral reflectance information;

[0013] Step 2: Use the continuous projection algorithm to perform dimension reduction processing on the spectral reflectance information of the visible light band of each color card by group, extract the characteristic wavelength of each group of color cards, and select the initial characteristic wavelength combination;

[0014] Step 3: Simulate complex imaging conditions and perform imaging measurements;

[0015] Simulating complex imaging conditions that are different from the imaging conditions described in step 1 to perform imaging, obtaining spectral reflectance information of each group of colors under the complex imaging conditions, and then repeating the operation of step 2 to obtain characteristic wavelength data;

[0016] Comparing the characteristic wavelength data with the preliminary characteristic wavelength combination selected in step 2, performing a secondary screening on the initial characteristic wavelengths, and using the screened characteristic wavelengths as label vectors of a support vector machine;

[0017] Step 4: Use the label vector described in step 3 as a training sample for the support vector machine, and train the support vector machine so that it can accurately identify and classify the paint film color; at the same time, use the training set to train the single-class support vector machine so that the single-class support vector machine can screen and identify abnormal colors; and combine the single-class support vector machine and the support vector machine to form a recognition and classification model for the color of the automobile paint film.

[0018] Beneficial effects of the present invention:

[0019] The automotive paint film color recognition and classification method described in the present invention obtains spectral reflectance information through a spectral preprocessing algorithm and a pixel point screening algorithm based on spectral matching angle theory, significantly eliminating recognition errors caused by changes in the surface curvature of the inspected material. It also extracts and integrates the paint film color spectral characteristics under various imaging conditions to construct an SVM prediction and classification model suitable for automotive paint film color assessment production lines. Combined with OC-SVM, this model screens out inspected materials with color spraying anomalies on the production line. The overall model not only has the ability to measure color under complex conditions, which is lacking in traditional color meters, but can also quickly and accurately determine the color type of automotive paint films. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of a method for identifying and classifying automobile paint film color by combining hyperspectral and support vector according to the present invention.

[0021] Figure 2 This is a flow chart of the present invention for screening all pixels in each sample ROI area. DETAILED DESCRIPTION

[0022] Combine Figure 1 and Figure 2This embodiment describes a method for automotive paint film color recognition and classification that combines hyperspectral and support vector imaging. This method identifies and classifies several different colored automotive exterior materials on a production line. This method uses a hyperspectral camera to image and analyze the target materials. In this embodiment, a hyperspectral camera is used to image the inspected materials. Its spectral range should cover the visible light band, i.e., 380-780nm, with a spectral resolution of ≤10nm. The distance between the camera lens and the inspected materials should be determined based on the actual situation, ensuring that all inspected materials are clearly imaged. Lighting conditions should be stable to ensure that the surfaces of the inspected materials are fully and evenly illuminated during measurement.

[0023] The method for identifying and classifying the color of automobile paint films described in this embodiment is implemented by the following steps:

[0024] Step 1: Select a corresponding color card set and color number based on the specific paint film color type to be identified in the actual project; select 28 commonly used automotive paint film colors from the GSB05-1426-2001 standard paint film color card set and divide them into 7 groups, with 4 colors in each group being similar colors. Under a uniform experimental light source, the color cards are laid flat on the laboratory table, and a hyperspectral camera is used to obtain its hyperspectral image (spectral image under ideal conditions). Preprocessing operations and pixel point screening are performed to obtain spectral reflectance information (ideal condition sample data); the 7 groups are:

[0025] Group 1: B06-light sky blue, B07-egg blue, B08-childish blue, BG05-light lake green;

[0026] Group 2: Y11-Ivory, Y02-Pearl, Y03-Cream, Y04-Ivory;

[0027] Group 3: B04-silver gray, B05-sea gray, G10-aircraft gray, BG01-medium green gray;

[0028] Group 4: GY02-spinning green, GY04-grass green, GY05-brown green, GY06-olive green;

[0029] Group 5: G01-apple green, G08-light apple green, GY01-bean green, GY08-fruit green;

[0030] Group 6: YR04-orange, R02-vermilion, R03-scarlet, R05-orange;

[0031] Group 7: YR09-iron yellow, YR06-brown yellow, YR01-light brown, YR07-dark brown yellow;

[0032] In this embodiment, under an experimental light source, each set of standard paint film color charts is laid flat on the camera imaging area. To obtain sufficient data and reduce accidental errors, multiple hyperspectral images of each set of color charts are acquired while ensuring uniform illumination. A region of interest (ROI) is extracted from each image, and raw spectral information within this region is obtained. Preprocessing is also performed simultaneously. This raw spectral information is contaminated with data noise such as the light source, camera dark current, ambient stray light, and shadows. When preprocessing the spectral information of the ROI region, a black and white plate correction formula is first applied to eliminate the effects of the light source, ambient light, and camera dark current, thereby obtaining an initial reflectance data curve. SG smoothing is then applied to remove some random noise and improve signal accuracy. A multivariate scatter correction (MSC) algorithm is then used to eliminate scattering and spectral differences caused by changes in material surface curvature. Finally, a spectral similarity test is performed on all pixels in the acquired area based on the spectral matching angle formula. Finally, a subset of pixels within the ROI region closest to the actual value is selected, and their spectral reflectance information is extracted.

[0033] In this embodiment, any medium with hyperspectral image processing capabilities is used to extract the ROI region. In this embodiment, MATLAB and ENVI software are used. The specific process of preprocessing the ROI region is as follows:

[0034] Step 1-1: Use the black and white plate correction formula to perform black and white balance and dark current correction, and calculate the initial spectral reflectance:

[0035]

[0036] Where, DN raw is the original spectral image response value, DN white Calibrate the image response value for the standard white plate, DN dc is the blackboard calibration image response value, R ref The spectral reflectance value obtained after calibration is obtained by imaging the standard whiteboard using a hyperspectral camera to obtain the standard whiteboard calibration image response value DN white ; Cover the camera lens with a lens cap to image and obtain the blackboard calibration image response value DN dc ;

[0037] Step 1-2: Use SG smoothing to process some random noise in the spectral curve; assume that the smoothing window width is n = 2m + 1, and the expected number of fitting curves is k, then use a k-1 degree polynomial to fit the data points in the window:

[0038] y=a0+a1x+a2x 2 +…+a k-1 x k-1

[0039] Solve the least squares problem to obtain the fitting parameters a0 to a k :

[0040]

[0041] In matrix form:

[0042] Y (2m+1)×1 =X (2m+1)×k ·A K×1 +E (2m+1)×1

[0043] Among them, X is the fitting point matrix, Y is the actual value matrix, and A is the SG fitting parameter matrix; the least squares solution matrix of A can be obtained from the above formula for:

[0044]

[0045] Then we get the fitting parameter values ​​and the y prediction value matrix Y under the 2m+1 window width and k-order polynomial fitting conditions. SG :

[0046] Y SG =X·A=X·(X T ·X) -1 ·X T ·Y=B·Y

[0047] Where B = X·(X T ·X) -1 ·X T .

[0048] Steps 1-3: Use the MSC algorithm to eliminate scattering errors. When performing MSC correction on a certain ROI area, the average spectrum of all sample points in the area must be obtained first.

[0049]

[0050] Among them, x ij is the spectral reflectance value of the i-th sample in the j-th band, and n is the total number of samples. Then, the spectrum of each sample point is subjected to a univariate linear regression relative to the average spectrum, and the least squares fitting formula for each sample is obtained as follows:

[0051]

[0052] Among them, x i represents the i-th sample, k i with b iare the offset and translation of each sample spectral curve compared to the baseline, respectively. Solving the least squares problem can obtain the corresponding values. Finally, the obtained baseline offset and translation are used to perform spectral correction:

[0053]

[0054] Where x MSC This is the spectral information after MSC correction. It should be noted that the experimental materials used in actual projects are often pure colors with uniform color distribution. If the original spectral curve of some materials does not have obvious scattering noise, the MSC correction step can be omitted to prevent overfitting.

[0055] In steps 1-4, the spectral reflectance curve obtained after the above preprocessing is used to filter out the pixels with the highest similarity within the ROI region based on the spectral matching angle theory to ensure that the data reflects the true value of the ROI region as much as possible. The spectral matching angle formula of the two spectral curves is as follows:

[0056]

[0057] Among them, X k 、Y k are the spectral reflectance values ​​of the two spectral curves in the kth band, θ SAM is the SAM angle of the two; θ SAM The smaller the value, the higher the similarity of the two spectral lines. According to the actual imaging situation, when θ SAM When the value is less than a certain threshold, the two spectral lines can be considered to come from the same color.

[0058] like Figure 2 As shown in the figure, the average spectrum of all pixels in the ROI area of ​​a certain type of paint film color image is taken and regarded as the "ideal spectrum". Based on the spectral matching, a screening threshold is set. Among the spectral reflectance curves of all pixels in the ROI area, the part with the highest similarity to the ideal spectrum is screened out as the spectral reflectance information of the paint film color in the ROI area. The specific process is as follows:

[0059] Step A: Calculate the average spectrum of the ROI area and initialize the number of cycles to I = 1;

[0060] Step B, calculating the SAM angle between the spectrum of the 1st pixel point in the ROI area and the average spectrum;

[0061] Step C: Determine whether the SAM angle calculated in step B exceeds a preset threshold. If so, remove the point and execute step D; otherwise, retain the point and execute step D;

[0062] Step D: Loop number + 1, determine whether the loop number reaches the total number of pixels N in the ROI area. If yes, end; otherwise, return to step B.

[0063] Step 2: Based on the Successive Projection Algorithm (SPA), dimensionality reduction processing is performed on the spectral reflectance information of the visible light band of each color card by group, and the initial characteristic wavelength of the color cards of each color group under the imaging conditions described in step 1 is preliminarily extracted. The four color cards in each group have the same characteristic wavelength;

[0064] In this embodiment, the SPA method is used to extract the characteristic wavelengths of various paint film materials. According to the principle of the SPA method, the hyperspectral camera and all wavelengths in the visible light band are sequentially used as initial bands to perform feature extraction operations to obtain multiple groups of characteristic wavelengths. Combined with cross-validation and multivariate regression models, statistical tests and judgments are performed using judgment criteria such as the square of the prediction error and the PRESS regression judgment criterion. The initial characteristic wavelength group (characteristic wavelength) is selected based on the judgment results.

[0065] Step 3: Simulate complex imaging conditions and perform imaging measurements for typical conditions that may occur in actual automotive paint film color recognition and affect the final recognition results. In this embodiment, three types of complex imaging conditions that may occur in actual engineering are simulated: changes in light source type, changes in illumination angle, and changes in material surface curvature. An experimental environment that meets these three conditions is established, and imaging operations are performed on the corresponding experimental materials. The operation process in steps 1 and 2 is repeated for its hyperspectral data to obtain characteristic wavelength data again. At this point, the characteristic wavelength extraction results of the standard paint film color under all imaging conditions are integrated and analyzed to screen out more representative feature variables and form the label vector of the support vector machine. The specific operations are as follows:

[0066] Perform multiple imaging operations by changing the illumination angle of the experimental light source in step 1; perform multiple imaging operations by replacing various common working light sources different from the experimental light source in step 1; perform multiple imaging operations using various automobile shell molds having the same color as the paint film color card in step 1 and having a surface with varying curvature; and perform data processing again according to the operation sequence in step 1 using a large number of imaging results under the above three types of complex imaging conditions (spectral images under complex conditions) to obtain spectral reflectance information for each group of colors under the three types of conditions (complex condition sample data).

[0067] SPA feature extraction is performed again on the spectral reflectance information obtained under the three types of complex imaging conditions, and the characteristic wavelengths extracted under the three types of complex conditions (characteristic wavelengths under complex conditions) are compared with the initial characteristic wavelength group obtained in step 2. The characteristic wavelengths of each color group are screened twice, and usually a part of the characteristic wavelengths in the initial characteristic wavelength group that are less representative and more sensitive to changes in light source and material surface are screened out; after screening, the final characteristic wavelength group for each color group is obtained.

[0068] At this point, the large amount of spectral reflectance information obtained for each set of paint film colors under all imaging conditions is integrated into a unified dataset. The dataset is then dimensionality reduced based on the final characteristic wavelength group of the color group. The reduced dataset serves as the label vector dataset for the color group.

[0069] Step 4: Use the label vector dataset as a training sample for a support vector machine to enable the support vector machine to accurately identify and classify paint film colors; at the same time, use the same dataset to train a single-class support vector machine to enable the single-class support vector machine to have the ability to screen and identify abnormal colors; a recognition and classification system for automobile paint film colors is formed by combining the single-class support vector machine and the support vector machine, which has both sample color classification and abnormal color screening functions.

[0070] In this embodiment, a large number of label vectors (training sets) for each paint film color are used to carry out SVM model training; first, a single-class support vector machine (OC-SVM) model is used to detect and screen samples with abnormal colors; the training set is input into the OC-SVM model, and by reasonably selecting the kernel function and related parameters, the entire data set is classified as a normal sample set; thereby, the model has the ability to identify and filter out abnormal samples; when a new color data is input into the model, it is first detected as an abnormality by the OC-SVM, and then the color recognition and classification is performed by the SVM. If the input data is determined to be an abnormal sample by the trained OC-SVM model, it is directly eliminated without subsequent recognition and classification operations;

[0071] In this embodiment, a support vector machine (SVM) is used to complete the recognition and classification of paint film colors; the label vector dataset of each group of paint film colors is used as the input feature, and the paint film color category is used as the output label; then, cross-validation and network search methods are used to optimize the hyperparameters of the SVM model, including the kernel function type, kernel function parameters, penalty coefficient, etc.; finally, the optimized SVM model is used to predict new paint film color samples, thereby realizing automatic recognition and classification of paint film colors.

[0072] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with this technical field within the technical scope disclosed by the present invention and within the spirit and principles of the present invention should be covered by the scope of protection of the present invention.

Claims

1. A method for identifying and classifying automobile paint film color by combining hyperspectral and support vector imaging, characterized by: The method is implemented by the following steps: Step 1: Select a variety of standard paint film color cards and divide them into seven groups, with four color cards in each group having similar colors. Set the imaging conditions under an experimental light source with uniform illumination, use a hyperspectral camera to image each group of color cards to obtain hyperspectral images of each group of color cards, and preprocess the hyperspectral images to obtain spectral reflectance information; Step 2: Use the continuous projection algorithm to perform dimension reduction processing on the spectral reflectance information of the visible light band of each color card by group, extract the characteristic wavelength of each group of color cards, and select the initial characteristic wavelength combination; Step 3: Simulate complex imaging conditions and perform imaging measurements; Simulating complex imaging conditions that are different from the imaging conditions described in step 1 to perform imaging, obtaining spectral reflectance information of each group of colors under the complex imaging conditions, and then repeating the operation of step 2 to obtain characteristic wavelength data; Comparing the characteristic wavelength data with the preliminary characteristic wavelength combination selected in step 2, performing a secondary screening on the initial characteristic wavelengths, and using the screened characteristic wavelengths as label vectors of a support vector machine; Step 4: Use the label vector described in step 3 as a training sample for the support vector machine, and train the support vector machine so that it can accurately identify and classify the paint film color; at the same time, use the training set to train the single-class support vector machine so that the single-class support vector machine can screen and identify abnormal colors; and combine the single-class support vector machine and the support vector machine to form a recognition and classification model for the color of the automobile paint film.

2. The method for automobile paint film color recognition and classification combining hyperspectral and support vector according to claim 1 is characterized in that: In step 1, each set of standard paint film color cards is laid out in the camera imaging area to collect a hyperspectral image, and the ROI area is extracted to obtain the original spectral information in the ROI area, and the original spectral information is preprocessed; the preprocessing process is as follows: First, the black and white plate correction formula is used to eliminate the influence of light source, ambient light and camera dark current to obtain the initial reflectivity data curve; Then, SG smoothing is used to remove some random noise; MSC algorithm is used to eliminate scattering and spectral differences caused by changes in material surface curvature; Finally, according to the spectral matching angle formula, a spectral similarity test is performed on all pixels in the collected area, and the pixel point closest to the actual value in the ROI area is finally selected to extract its spectral reflectance information.

3. The method for automobile paint film color recognition and classification combining hyperspectral and support vector according to claim 2, characterized in that: The specific process of extracting the spectral reflectance information of the pixel point closest to the actual value in the ROI area is as follows: Step A: Calculate the average spectrum of the ROI area and initialize the number of cycles to 0; Step B, calculating the SAM angle between the spectrum of the i-th pixel point in the ROI area and the average spectrum; Step C: Determine whether the SAM angle calculated in step B exceeds a preset threshold. If so, remove the point and execute step D; otherwise, retain the point and execute step D; Step D: add 1 to the number of loops and determine whether the number of loops reaches the total number of pixels N in the ROI area. If yes, end. Otherwise, return to step B.

4. The method for automobile paint film color recognition and classification combining hyperspectral and support vector according to claim 1, characterized in that: In step 2, according to the principle of the SPA algorithm, the hyperspectral camera and all wavelengths in the visible light band are used as initial bands to perform feature extraction operations in turn to obtain multiple sets of characteristic wavelengths; cross-validation and multivariate regression models are used to perform statistical tests and judgments on the characteristic wavelengths, and a preliminary characteristic wavelength combination is selected based on the judgment results.

5. The method for automobile paint film color recognition and classification combining hyperspectral and support vector according to claim 1, characterized in that: In step three, the complex imaging conditions are divided into three categories: changing the illumination angle of the experimental light source in step one for imaging; replacing a light source different from the experimental light source in step one for imaging; and using multiple automobile shell molds with the same color as the paint film color card in step one and with a surface curvature variation for imaging.

6. The method for automobile paint film color recognition and classification combining hyperspectral and support vector according to claim 1, characterized in that: In step 4, the training set is input into the single-class support vector machine, and the entire training set is classified as a normal sample set by selecting the kernel function and related parameters; the single-class support vector machine is enabled to identify and filter out abnormal samples; when new color data is input into the single-class support vector machine, the single-class support vector machine performs anomaly detection, and then the support vector machine performs color recognition and classification; if the input data is determined to be an abnormal sample by the trained single-class support vector machine, it is directly eliminated.

7. The method for automobile paint film color recognition and classification combining hyperspectral and support vector according to claim 1, characterized in that: In step four, a support vector machine is used to complete the recognition and classification of paint film color; the characteristic wavelength combination is used as the input feature, and the paint film color category is used as the output label; then, cross-validation and network search methods are used to optimize the hyperparameters of the SVM model, including the kernel function type, kernel function parameters, and penalty coefficient; finally, the optimized SVM model is used to predict new paint film color samples to achieve automatic recognition and classification of paint film color.

Images