Detection device and detection method for double-sided optical imaging film

Abstract

The present invention relates to the field of optical film inspection technology, and provides an inspection device and method for double-sided optical imaging films. The method comprises obtaining first and second optical reflection data from the double-sided optical imaging film, comparing them, obtaining global reflection difference data, analyzing them, obtaining optical reflection performance data and transmission performance data, inputting the optical reflection performance data and transmission performance data into a preset analysis model, and outputting an optical performance evaluation report. By obtaining the first and second optical reflection data from the double-sided optical imaging film, comparing and statistically analyzing them, accurate global reflection difference data is obtained, and then outputting an optical performance evaluation report based on the preset analysis model. This method provides a more comprehensive performance evaluation, suitable for quality control and performance analysis of a variety of high-precision optical devices, and improves the difficulty in comprehensively evaluating both optical uniformity and reflection characteristics in high-precision application scenarios.

Description

Technical Field

[0001] The present application relates to the technical field of optical film detection, and in particular to a detection device and method for a double-sided optical imaging film. Background Art

[0002] Optical imaging films play a vital role in display devices, imaging equipment, and optical instruments. With the rapid development of science and technology, the demand for high resolution, low reflectivity, and high optical uniformity continues to increase, driving continuous innovation and advancement in optical imaging film technology. Double-sided optical imaging films, due to their excellent transmission and reflection properties, are widely used in various high-precision optical devices.

[0003] Among the relevant technical means, the detection method of double-sided optical imaging film is mainly through separate optical detection, which obtains optical reflection and transmission data by separately detecting the two surfaces of the double-sided optical imaging film. The double-sided film is detected and evaluated by using precise optical sensors and data processing software, and the double-sided optical performance of the optical imaging film is effectively evaluated.

[0004] Regarding the above technical solution, although the optical reflection and transmission data are obtained by separately detecting the two surfaces of the double-sided optical imaging film, the double-sided film can be detected and evaluated. However, in high-precision application scenarios, such as in medical imaging equipment, high-precision microscopes and scientific experimental instruments, it is difficult to comprehensively evaluate both optical uniformity and reflection characteristics. As a result, in some high-precision application scenarios, it is difficult to meet the comprehensive optical performance evaluation needs. Summary of the Invention

[0005] In order to improve the problem of difficulty in comprehensively evaluating both optical uniformity and reflective characteristics in high-precision application scenarios, the present application provides a detection device and a detection method for a double-sided optical imaging film.

[0006] The present invention provides a method for detecting a double-sided optical imaging film, comprising: obtaining first optical reflection data of a first surface and second optical reflection data of a second surface of the double-sided optical imaging film, comparing the first optical reflection data with the second optical reflection data to obtain global reflection difference data; performing statistical analysis on the global reflection difference data to obtain surface optical uniformity data, analyzing the optical uniformity of the double-sided optical imaging film using the surface optical uniformity data to obtain an optical uniformity evaluation value; performing comprehensive analysis on the optical uniformity of the first and second surfaces of the double-sided optical imaging film based on the optical uniformity evaluation value to obtain an optical uniformity analysis result; performing cluster analysis on the optical uniformity analysis result to generate an optical uniformity index and an optical deviation parameter, analyzing the optical reflection characteristics of the double-sided optical imaging film using the optical uniformity index to obtain optical reflection performance data, analyzing the transmission performance of the double-sided optical imaging film using the optical deviation parameter to obtain transmission performance data; inputting the optical reflection performance data and the transmission performance data into a preset analysis model to output a comprehensive optical performance score, and generating an optical performance evaluation report based on the comprehensive optical performance score.

[0007] As a preferred solution, the steps of obtaining first optical reflection data of the first surface and second optical reflection data of the second surface of the double-sided optical imaging film, comparing the first optical reflection data with the second optical reflection data, and obtaining global reflection difference data include: performing multi-point optical reflection tests on the first surface and the second surface of the double-sided optical imaging film using spectral reflection measurement equipment, and obtaining original optical reflection data of the first surface and the second surface by hyperspectral imaging technology; inputting the original optical reflection data of the first surface and the original optical reflection data of the second surface into a preset reflection comparison model to generate initial reflection difference data and a full-surface optical reflection difference distribution map; performing multi-scale decomposition of the full-surface optical reflection difference distribution map by discrete wavelet transform, and generating reflection difference spatial feature data based on the decomposition results; and fusing the initial reflection difference data with the reflection difference spatial feature data to obtain global reflection difference data of the double-sided optical imaging film.

[0008] As a preferred solution, the steps of performing statistical analysis on the global reflection difference data to obtain surface optical uniformity data, and using the surface optical uniformity data to analyze the optical uniformity of the double-sided optical imaging film to obtain an optical uniformity evaluation value include: clustering the global reflection difference data using a K-means clustering algorithm to generate an optical uniformity clustering graph; based on the optical uniformity clustering graph, calculating the overall deviation value of the film surface optical uniformity using a standard deviation method, and calculating the local deviation value using a local weighted regression method; and performing fast Fourier transform on the overall deviation value and the local deviation value. The deviation value is decomposed in the frequency domain to generate surface optical uniformity data; the surface optical uniformity data is subjected to frequency domain analysis using power spectral density analysis to obtain uniformity spectrum data; the uniformity spectrum data and the overall deviation value are subjected to dimensionality reduction analysis based on principal component analysis; and an optical uniformity characteristic index and an optical deviation distribution parameter are generated based on the analysis results; the optical uniformity characteristic index is subjected to spatial statistical analysis based on spatial autocorrelation to generate a global uniformity index; the global uniformity index and the optical deviation distribution parameter are subjected to regression analysis using a linear regression model to obtain an optical uniformity evaluation value.

[0009] As a preferred embodiment, the step of comprehensively analyzing the optical uniformity of the first surface and the second surface of the double-sided optical imaging film based on the optical uniformity evaluation value to obtain an optical uniformity analysis result includes: decomposing the optical uniformity evaluation value into a regional uniformity index and a global uniformity index, and generating an optical uniformity heat map of the double-sided optical imaging film based on the regional uniformity index; performing trend analysis on the global uniformity index and the optical uniformity heat map using a least squares fitting method to obtain an optical uniformity change curve, and applying a Bezier curve fitting algorithm to extract optical characteristic trends from the optical uniformity change curve to obtain an optical uniformity analysis result.

[0010] As a preferred solution, the step of decomposing the optical uniformity evaluation value into a regional uniformity index and a global uniformity index includes: decomposing the optical uniformity evaluation value using a weighted average decomposition algorithm to obtain a global uniformity deviation value and a local uniformity change value; dividing the global uniformity deviation value into regions using a region growing method to generate a regional uniformity index; and fitting the local uniformity change value using a radial basis function interpolation method to generate a global uniformity index.

[0011] As a preferred solution, the steps of performing cluster analysis on the optical uniformity analysis results to generate an optical uniformity index and an optical deviation parameter, using the optical uniformity index to analyze the optical reflection characteristics of the double-sided optical imaging film to obtain optical reflection performance data, and using the optical deviation parameter to analyze the transmission performance of the double-sided optical imaging film to obtain transmission performance data include: clustering the optical uniformity analysis results using the DBSCAN algorithm to identify regions where optical characteristics of the film surface change, generating an optical uniformity region division map, and extracting the optical uniformity mean value of each characteristic change region based on the optical uniformity region division map. and maximum deviation value, generating an optical uniformity index through the optical uniformity mean and the maximum deviation value; performing classification analysis on the optical uniformity index using linear discriminant analysis to obtain an optical uniformity feature data set, performing regression analysis on the optical uniformity feature data set using a support vector machine regression model to obtain optical reflection characteristic-related parameters and optical deviation parameters; performing optical reflection performance fitting calculation on the optical reflection characteristic-related parameters according to a transfer matrix method to obtain optical reflection performance data of the double-sided optical imaging film; performing transmission performance calculation on the optical deviation parameters using a Fresnel equation to obtain transmission performance data of the double-sided optical imaging film.

[0012] As a preferred solution, the steps of inputting the optical reflection performance data and the transmission performance data into a preset analysis model, outputting a comprehensive optical performance score, and generating an optical performance evaluation report based on the comprehensive optical performance score include: weighting the optical reflection performance data and the transmission performance data by an entropy weight method to generate a comprehensive optical performance value, inputting the comprehensive optical performance value into a preset analysis model to obtain a comprehensive optical performance score; applying a fuzzy comprehensive evaluation method to classify and evaluate the comprehensive optical performance score, and generating an optical performance evaluation report including reflection performance, transmission performance and deviation trend based on the evaluation results.

[0013] The present application also provides a detection device for a double-sided optical imaging film, comprising: a comparison module for obtaining first optical reflection data of a first surface and second optical reflection data of a second surface of the double-sided optical imaging film, comparing the first optical reflection data with the second optical reflection data to obtain global reflection difference data; a first analysis module for performing statistical analysis on the global reflection difference data to obtain surface optical uniformity data, and analyzing the optical uniformity of the double-sided optical imaging film using the surface optical uniformity data to obtain an optical uniformity evaluation value; a second analysis module for analyzing the first surface of the double-sided optical imaging film according to the optical uniformity evaluation value. and performing a comprehensive analysis on the optical uniformity of the first surface and the second surface to obtain an optical uniformity analysis result; a third analysis module, used to perform a cluster analysis on the optical uniformity analysis result, generate an optical uniformity index and an optical deviation parameter, use the optical uniformity index to analyze the optical reflection characteristics of the double-sided optical imaging film to obtain optical reflection performance data, and use the optical deviation parameter to analyze the transmission performance of the double-sided optical imaging film to obtain transmission performance data; an evaluation module, used to input the optical reflection performance data and the transmission performance data into a preset analysis model, output a comprehensive optical performance score, and generate an optical performance evaluation report based on the comprehensive optical performance score.

[0014] Compared with the existing technology, the present application has the following beneficial effects: high detection accuracy and comprehensive evaluation. By acquiring the first optical reflection data and the second optical reflection data of the double-sided optical imaging film, comparing and statistically analyzing them, accurate global reflection difference data is obtained, thereby effectively evaluating the surface optical uniformity of the double-sided optical imaging film. Based on the optical uniformity evaluation value, a comprehensive analysis of the two surfaces is performed to obtain an optical uniformity analysis result. Cluster analysis is used to generate optical uniformity indicators and optical deviation parameters based on the optical uniformity analysis result. The optical reflection performance and transmission performance are analyzed separately to obtain comprehensive optical performance data. Then, a preset analysis model is used to comprehensively evaluate the optical reflection performance data and transmission performance data. After outputting the comprehensive optical performance score, an optical performance evaluation report is generated. This provides a more comprehensive and accurate performance evaluation of the double-sided optical imaging film, which is suitable for quality control and performance analysis of a variety of high-precision optical equipment, and improves the problem of difficulty in comprehensively evaluating both optical uniformity and reflection characteristics in high-precision application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] The structures, proportions, sizes, etc. depicted in the drawings of this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not intended to limit the conditions under which the present invention can be implemented and therefore have no substantive technical significance. Any structural modifications, changes in proportional relationships, or adjustments in size should still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and objectives that can be achieved by the present invention.

[0017] Figure 1 1 is a flow chart of a method for detecting a double-sided optical imaging film provided by an embodiment of the present invention;

[0018] Figure 2 It is a schematic block diagram of the structure of a detection device for a double-sided optical imaging film provided by an embodiment of the present invention.

[0019] Description of reference numerals:

[0020] 10. Detection device for double-sided optical imaging film; 11. Comparison module; 12. First analysis module; 13. Second analysis module; 14. Third analysis module; 15. Evaluation module. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0023] It should also be understood that the terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0024] It should be further understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0025] The technical solution of the present invention will be further described below with reference to the accompanying drawings and through specific implementation methods.

[0026] Example 1:

[0027] like Figure 1 As shown, the present application provides a method for detecting a double-sided optical imaging film, including steps S100 to S500.

[0028] Step S100 : obtaining first optical reflection data of the first surface and second optical reflection data of the second surface of the double-sided optical imaging film, and comparing the first optical reflection data with the second optical reflection data to obtain global reflection difference data.

[0029] In this step, a high-precision optical sensor is used to obtain first optical reflection data from the first surface and second optical reflection data from the second surface of the double-sided optical imaging film. Specifically, reflectance spectroscopy analysis technology is used to measure the reflection spectra of both surfaces and record the reflection data. The first and second optical reflection data are then compared to calculate global reflection difference data, which is used to characterize the reflectance difference between the two surfaces.

[0030] For example, the reflection spectrum data of two surfaces are measured simultaneously on a high-precision optical detection instrument, and compared and analyzed through data processing software to obtain global reflection difference data.

[0031] Step S200 : Statistically analyzing the global reflection difference data to obtain surface optical uniformity data, and analyzing the optical uniformity of the double-sided optical imaging film using the surface optical uniformity data to obtain an optical uniformity evaluation value.

[0032] In this step, a statistical analysis tool is used to analyze the global reflection difference data to obtain the surface optical uniformity data of the double-sided optical imaging film. Specifically, a statistical method is used to perform statistical analysis such as mean and variance on the reflection difference data to quantify the surface optical uniformity.

[0033] For example, statistical analysis software can be used to process global reflection difference data to obtain surface optical uniformity data. This data can then be used for further analysis to evaluate the optical uniformity of double-sided optical imaging films and obtain an optical uniformity evaluation value.

[0034] Step S300 : performing a comprehensive analysis on the optical uniformity of the first surface and the second surface of the double-sided optical imaging film according to the optical uniformity evaluation value to obtain an optical uniformity analysis result.

[0035] In this step, a comprehensive analysis of the optical uniformity of the first and second surfaces of the double-sided optical imaging film is performed based on the optical uniformity evaluation values. Specifically, the optical uniformity and consistency of the two surfaces are evaluated by comparing and comprehensively analyzing the evaluation values.

[0036] For example, the optical uniformity evaluation value can be visualized using a chart tool to intuitively evaluate the overall optical uniformity of a double-sided optical imaging film and obtain optical uniformity analysis results.

[0037] Step S400: Perform cluster analysis on the optical uniformity analysis results to generate optical uniformity indices and optical deviation parameters. Use the optical uniformity indices to analyze the optical reflection characteristics of the double-sided optical imaging film to obtain optical reflection performance data. Use the optical deviation parameters to analyze the transmission performance of the double-sided optical imaging film to obtain transmission performance data.

[0038] In this step, cluster analysis is used to group and categorize the optical uniformity analysis results, generating specific optical uniformity indices and optical deviation parameters. Specifically, a K-means clustering algorithm is used to classify the analysis results and identify regions with different optical properties. The generated optical uniformity indices are then used to conduct a detailed analysis of the optical reflectance characteristics of the double-sided optical imaging film, generating optical reflectance performance data. The optical deviation parameters are then used to analyze the transmittance performance of the film, generating transmittance performance data.

[0039] For example, the K-means clustering algorithm is used to process the optical uniformity analysis results to generate an optical uniformity index, and the optical characteristic analysis is performed in combination with the optical parameter database.

[0040] Step S500: Input the optical reflection performance data and the transmission performance data into a preset analysis model, output an optical performance comprehensive score, and generate an optical performance evaluation report based on the optical performance comprehensive score.

[0041] In this step, a pre-defined analysis model is used to comprehensively evaluate the optical reflectance and transmission performance data, outputting a comprehensive optical performance score. Specifically, the aforementioned optical reflectance and transmission performance data are input into an AI-based analysis model for a multi-dimensional comprehensive score. A detailed optical performance evaluation report is generated based on the comprehensive score results.

[0042] For example, a deep learning model is used to process input data to obtain a comprehensive score of optical performance and automatically generate an optical performance evaluation report containing multiple evaluation indicators.

[0043] In this embodiment, global reflection difference data is obtained by acquiring first optical reflection data from the first surface and second optical reflection data from the second surface of a double-sided optical imaging film. The first and second optical reflection data are then compared to obtain global reflection difference data. Statistical analysis is then performed on the global reflection difference data to obtain surface optical uniformity data. This surface optical uniformity data is then used to analyze the optical uniformity of the double-sided optical imaging film, obtaining an optical uniformity evaluation value. Subsequently, a comprehensive analysis of the optical uniformity of both the first and second surfaces of the double-sided optical imaging film is performed based on the optical uniformity evaluation value to obtain an optical uniformity analysis result. Finally, cluster analysis is performed on the optical uniformity analysis results to generate optical uniformity indices and optical deviation parameters. The optical uniformity indices are then used to analyze the optical reflectance characteristics of the double-sided optical imaging film, obtaining optical reflectance performance data. The optical deviation parameters are then used to analyze the transmittance performance of the double-sided optical imaging film, obtaining transmittance performance data. These reflectance and transmittance performance data are then fed into a pre-set analysis model, which outputs a comprehensive optical performance score. An optical performance evaluation report is generated based on the comprehensive optical performance score, enabling comprehensive and accurate testing and evaluation of double-sided optical imaging films. This overcomes the shortcomings of existing technologies, which struggle to balance optical uniformity and reflectance characteristics in high-precision applications. This not only improves testing accuracy and consistency, but also provides more comprehensive optical performance data, providing reliable data support and evaluation basis for the use of double-sided optical imaging films in high-precision applications.

[0044] Example 2:

[0045] In step S100, a multi-point optical reflection test is performed on the first surface and the second surface of the double-sided optical imaging film using a spectral reflection measurement device, and raw optical reflection data of the first surface and the second surface are obtained using hyperspectral imaging technology.

[0046] By performing multiple measurements at different locations, the acquired data is ensured to be representative and highly accurate. Specifically, high-precision spectral reflectance measurement equipment is used to perform reflection tests at multiple predetermined locations on the double-sided optical imaging film to obtain optical reflection data at different locations. Hyperspectral imaging technology is then used to obtain more comprehensive optical information, including reflectance at various wavelengths.

[0047] For example, at least 25 measurement points are selected on a double-sided optical imaging film with a diameter of 10 cm, and the optical reflection data of each measurement point at different wavelengths is recorded by a hyperspectral imaging device to ensure that the data covers the entire surface and has sufficient details.

[0048] The original optical reflection data of the first surface and the original optical reflection data of the second surface are input into a preset reflection comparison model to generate initial reflection difference data and a full-surface optical reflection difference distribution map.

[0049] The raw optical reflection data is preprocessed to remove noise and outliers. Specifically, the preprocessed data is compared point by point using a reflection comparison model to calculate the reflection difference at each measurement point, generate initial reflection difference data, and generate a full-surface optical reflection difference distribution map using an interpolation algorithm.

[0050] For example, the optical reflection data is preprocessed using the data processing tools in Matlab. After removing the noise, each measurement point is compared and analyzed by writing a comparison algorithm to generate the initial reflection difference data, and the optical reflection difference distribution map is generated using the interpolation method.

[0051] The full-surface optical reflection difference distribution map is decomposed at multiple scales by discrete wavelet transform, and the reflection difference spatial feature data is generated based on the decomposition results.

[0052] The optical reflectance difference distribution map is decomposed into components of different scales by applying discrete wavelet transform to capture the features at different scales. Specifically, appropriate wavelet basis functions and decomposition levels are selected to perform multi-scale decomposition on the distribution map and extract the spatial feature data at each scale.

[0053] For example, the Haar wavelet basis function is used to decompose the optical reflection difference distribution map into three layers to obtain high-frequency and low-frequency components, and the image features after each layer of decomposition are analyzed to obtain the reflection difference spatial feature data at different scales.

[0054] The initial reflection difference data and the reflection difference spatial feature data are fused to obtain the global reflection difference data of the double-sided optical imaging film.

[0055] By weightedly fusing the spatial feature data obtained by multi-scale decomposition with the initial reflection difference data, more comprehensive reflection difference information is obtained; specifically, a weighted average algorithm is used to weight the feature data of each scale and combine them with the initial reflection difference data to generate global reflection difference data.

[0056] For example, the weighted average function in Python is used to perform weighted fusion on the initial reflection difference data and the feature data obtained by three-layer wavelet decomposition to generate reflection difference data containing more details and global information.

[0057] In step S200, the global reflection difference data is clustered using the K-means clustering algorithm to generate an optical uniformity cluster map. Based on the optical uniformity cluster map, the overall deviation value of the optical uniformity of the film surface is calculated using the standard deviation method, and the local deviation value is calculated using the local weighted regression method.

[0058] The global reflection difference data is unsupervisedly classified using the K-means clustering algorithm to identify different clusters in the data. Specifically, an appropriate K value (e.g., 3 to 5) is selected to cluster the global reflection difference data to generate an optical uniformity cluster map. The overall and local optical uniformity deviation values ​​of the film surface are further calculated using the standard deviation method and local weighted regression method.

[0059] For example, the K-means clustering function in R language is used to perform cluster analysis on the reflection difference data, K=4 is selected for classification, and an optical uniformity cluster map is generated. The overall deviation value is calculated using the standard deviation formula, and the loess function is used for local weighted regression to calculate the local deviation value.

[0060] Fast Fourier transform is used to perform frequency domain decomposition of the global deviation value and the local deviation value to generate surface optical uniformity data.

[0061] By performing fast Fourier transform analysis on the deviation values, the deviation information in the spatial domain is converted into frequency domain information. Specifically, an appropriate sampling frequency is selected, and Fourier transform is performed on the overall and local deviation values ​​to generate optical uniformity data in the frequency domain.

[0062] For example, the fft function in Matlab is used to perform Fourier transform on the overall and local deviation values ​​to generate a spectrum diagram, and the contribution of different frequency components to the optical uniformity is analyzed to obtain the surface optical uniformity data.

[0063] Power spectral density analysis is applied to perform frequency domain analysis on the surface optical uniformity data to obtain uniformity spectrum data. Dimensionality reduction analysis is performed on the uniformity spectrum data and the overall deviation value based on principal component analysis. Optical uniformity characteristic indicators and optical deviation distribution parameters are generated based on the analysis results.

[0064] The main components and features in the frequency domain are identified through power spectral density analysis. Specifically, the power spectral density of the optical uniformity data is calculated, the main spectral features are extracted, and the data is reduced in dimension through principal component analysis to generate optical uniformity characteristic indicators and optical deviation distribution parameters.

[0065] For example, the power spectral density of optical uniformity data is calculated using the Welch method in Python, the first two main components are extracted through principal component analysis, the characteristic indicators after dimensionality reduction are obtained, and the optical deviation distribution parameters are generated based on the analysis results.

[0066] The optical uniformity characteristic indicators are spatially statistically analyzed based on spatial autocorrelation to generate a global uniformity index. The global uniformity index and optical deviation distribution parameters are then regressed using a linear regression model to obtain an optical uniformity evaluation value.

[0067] The spatial distribution characteristics of the optical uniformity characteristic indicators are evaluated by applying the spatial autocorrelation analysis method. Specifically, the global and local spatial autocorrelation indicators are calculated to generate a global uniformity index. The uniformity index and the optical deviation distribution parameters are then regressed and analyzed using a linear regression model to obtain the optical uniformity evaluation value.

[0068] For example, the Moran's I method in GeoDa software was used to calculate the spatial autocorrelation of the optical uniformity characteristic index to generate a global uniformity index. The regression analysis function in SPSS was then used to perform regression analysis on the uniformity index and deviation parameters to obtain the optical uniformity evaluation value.

[0069] In step S300 , the optical uniformity evaluation value is decomposed into a regional uniformity index and a global uniformity index, and an optical uniformity heat map of the double-sided optical imaging film is generated based on the regional uniformity index.

[0070] The optical uniformity evaluation value is decomposed to identify the optical uniformity of different regions. Specifically, the evaluation value is decomposed into a regional uniformity index and a global uniformity index using a weighted average algorithm to generate a heat map reflecting the regional uniformity.

[0071] For example, the pivot table function in Excel is used to perform weighted decomposition of the optical uniformity evaluation value to generate uniformity indicators for different areas, and a heat map plug-in is used to generate an optical uniformity heat map of the double-sided optical imaging film.

[0072] The least squares fitting method was used to perform trend analysis on the global uniformity index and the optical uniformity heat map to obtain the optical uniformity change curve. The Bessel curve fitting algorithm was applied to extract the optical characteristic trend of the optical uniformity change curve to obtain the optical uniformity analysis result.

[0073] The global uniformity index and thermal map data are fitted by the least squares fitting method to identify the uniformity change trend. Specifically, an appropriate fitting function is selected to perform fitting analysis on the optical uniformity change curve, and the Bezier curve is applied to extract the optical characteristic trend to obtain the analysis result.

[0074] For example, the least squares fitting tool in the Origin software is used to perform fitting analysis on the optical uniformity index, draw a change curve, and use the Bezier curve algorithm to smooth the change curve, extract the optical characteristic trend, and obtain the uniformity analysis results.

[0075] The step of decomposing the optical uniformity evaluation value into a regional uniformity index and a global uniformity index includes: decomposing the optical uniformity evaluation value using a weighted average decomposition algorithm to obtain a global uniformity deviation value and a local uniformity change value.

[0076] The correlation between the indicators of each region and the overall indicator is ensured by performing weighted average decomposition on the optical uniformity evaluation values ​​of each region. Specifically, the optical uniformity evaluation values ​​of each region are weighted using the weighted average decomposition algorithm to calculate the global uniformity deviation value and the local uniformity change value.

[0077] For example, a formula is written in Excel to decompose the optical uniformity data using a weighted average algorithm to generate uniformity deviation and change values ​​for each area, ensuring the consistency and accuracy of data processing.

[0078] The global uniformity deviation value is divided into regions using the region growing method to generate regional uniformity indicators.

[0079] The global uniformity deviation value is divided into regions by applying the region growing algorithm to identify regions with different optical properties. Specifically, an appropriate region growing initial point is selected, and the deviation value is regionally expanded by a recursive algorithm to generate a regional uniformity index.

[0080] For example, the region growing algorithm in the scikit-image library in Python is used to process the optical uniformity data, set the initial growth point and threshold, automatically identify regions with similar optical properties, and generate regional uniformity indicators.

[0081] The local uniformity change value is fitted by radial basis function interpolation method to generate the global uniformity index.

[0082] The local uniformity variation values ​​are smoothly fitted by applying the radial basis function interpolation method to generate a continuous global uniformity index. Specifically, appropriate radial basis functions and control parameters are selected to interpolate the local uniformity variation values ​​to generate a smooth global uniformity index.

[0083] For example, the radial basis function interpolation tool in Matlab is used to fit the local uniformity data, and appropriate functions and parameters are selected to generate a global uniformity index with high fitting accuracy.

[0084] In step S400, the optical uniformity analysis results are clustered using the DBSCAN algorithm to identify areas of optical property change on the film surface, generate an optical uniformity area division map, extract the optical uniformity mean and maximum deviation value of each property change area based on the optical uniformity area division map, and generate an optical uniformity index based on the optical uniformity mean and maximum deviation values.

[0085] The DBSCAN algorithm is used to perform density cluster analysis on the optical uniformity data to identify areas with changes in optical properties. Specifically, an appropriate ε value and minimum number of sample points are selected, and the optical uniformity analysis results are clustered to generate an optical uniformity region partition map. The mean optical uniformity value and maximum deviation value of each region are extracted.

[0086] For example, the DBSCAN function in the R language is used to perform density cluster analysis on the optical uniformity data, selecting ε=0.5 and the minimum number of sample points as 5 to generate an optical uniformity region division map, and extracting the mean and maximum deviation value of each region to generate the optical uniformity index.

[0087] The optical uniformity indicators were classified and analyzed using linear discriminant analysis to obtain an optical uniformity feature data set. The optical uniformity feature data set was then regressed using a support vector machine regression model to obtain optical reflection characteristic related parameters and optical deviation parameters.

[0088] The optical uniformity indicators are classified through linear discriminant analysis to form an optical uniformity feature data set. Specifically, the regional uniformity indicators are classified into different categories using the linear discriminant analysis method to generate a feature data set. The data set is then subjected to regression analysis using a support vector machine regression model to obtain optical reflection characteristic-related parameters and optical deviation parameters.

[0089] For example, the LinearDiscriminantAnalysis and SVR modules in Python are used to perform classification and regression analysis on optical uniformity data, extract relevant parameters, and generate optical reflection characteristics and deviation parameters.

[0090] The optical reflection performance data of the double-sided optical imaging film were obtained by fitting and calculating the optical reflection performance of the optical reflection characteristic-related parameters according to the transfer matrix method.

[0091] The optical reflection performance data of the double-sided optical imaging film are obtained by fitting and calculating the relevant parameters of the optical reflection characteristics using the transfer matrix method.

[0092] For example, the transfer matrix calculation tool in Matlab is used to perform fitting calculations on the acquired optical reflection characteristic parameters to obtain specific optical reflection performance data of the double-sided optical imaging film.

[0093] The transmission performance data of the double-sided optical imaging film was obtained by calculating the transmission performance of the optical deviation parameters using the Fresnel equation.

[0094] The optical deviation parameters are calculated using the Fresnel equation to obtain transmission performance data. Specifically, the transmission performance is calculated using the Fresnel equation in combination with the deviation parameters to generate transmission performance data for the double-sided optical imaging film.

[0095] For example, the Fresnel equation calculation function in Python is used to substitute the optical deviation parameters into the equation to calculate the transmittance performance of the film and obtain the transmittance performance data of the double-sided optical imaging film.

[0096] In step S500, the optical reflection performance data and the transmission performance data are weighted by the entropy weight method to generate a comprehensive optical performance value, which is then input into a preset analysis model to obtain a comprehensive optical performance score.

[0097] By applying the entropy weight method to weight different types of optical performance data, a comprehensive performance value is generated; specifically, the entropy weight method is used to weight the reflection performance data and the transmission performance data to calculate the comprehensive optical performance value, which is then input into the preset analysis model to obtain a comprehensive optical performance score.

[0098] For example, the entropy weight calculation tool in Excel is used to perform weighted calculations on the optical reflection performance and transmission performance data to generate a comprehensive optical performance value, which is then input into the machine learning model to obtain a detailed comprehensive optical performance score.

[0099] The fuzzy comprehensive evaluation method is used to classify and evaluate the comprehensive score of optical performance, and an optical performance evaluation report including reflection performance, transmission performance and deviation trend is generated based on the evaluation results.

[0100] The fuzzy comprehensive evaluation method is used to conduct detailed classification evaluation of the comprehensive score of optical performance and generate a comprehensive report; specifically, the fuzzy comprehensive evaluation method is used to perform layered processing on the scoring results, evaluate the optical performance, and generate a detailed evaluation report containing multiple indicators.

[0101] For example, the fuzzy logic library in Python is used to perform fuzzy comprehensive evaluation on the comprehensive score of optical performance, classify it according to predetermined rules, and generate a detailed optical performance evaluation report containing information such as reflection performance, transmission performance, and optical deviation trends.

[0102] In this example, multi-point optical reflectance testing of double-sided optical imaging films was performed using spectral reflectance measurement equipment. Hyperspectral imaging technology was used to obtain raw data. Global reflectance difference data was then generated using a preset reflectance comparison model and discrete wavelet transform. Subsequently, K-means clustering and fast Fourier transform analysis were used to obtain surface optical uniformity data and generate optical uniformity characteristic indices. The DBSCAN algorithm was used to identify areas of optical property variation. Optical performance was calculated using a support vector machine regression model, the transfer matrix method, and the Fresnel equation to obtain a comprehensive score. Finally, a detailed optical performance evaluation report was generated, providing a comprehensive and accurate means of testing and evaluation.

[0103] Example 3:

[0104] The present application also provides a detection device 10 for a double-sided optical imaging film, comprising a comparison module 11 , a first analysis module 12 , a second analysis module 13 , a third analysis module 14 and an evaluation module 15 .

[0105] The comparison module 11 is mainly used to obtain first optical reflection data of the first surface and second optical reflection data of the second surface of the double-sided optical imaging film, and compare the first optical reflection data with the second optical reflection data to obtain global reflection difference data.

[0106] The first analysis module 12 is mainly used to perform statistical analysis on the global reflection difference data to obtain surface optical uniformity data, and use the surface optical uniformity data to analyze the optical uniformity of the double-sided optical imaging film to obtain an optical uniformity evaluation value.

[0107] The second analysis module 13 is mainly used to perform a comprehensive analysis on the optical uniformity of the first surface and the second surface of the double-sided optical imaging film according to the optical uniformity evaluation value to obtain an optical uniformity analysis result.

[0108] The third analysis module 14 is mainly used to perform cluster analysis on the optical uniformity analysis results, generate optical uniformity indicators and optical deviation parameters, use the optical uniformity indicators to analyze the optical reflection characteristics of the double-sided optical imaging film to obtain optical reflection performance data, and use the optical deviation parameters to analyze the transmission performance of the double-sided optical imaging film to obtain transmission performance data.

[0109] The evaluation module 15 is mainly used to input the optical reflection performance data and the transmission performance data into a preset analysis model, output an optical performance comprehensive score, and generate an optical performance evaluation report based on the optical performance comprehensive score.

[0110] In this embodiment, the comparison module 11 obtains first optical reflection data from the first surface and second optical reflection data from the second surface of the double-sided optical imaging film and compares them to obtain global reflection difference data. The first analysis module 12 performs statistical analysis on the global reflection difference data to obtain surface optical uniformity data. This data is then used to analyze the optical uniformity of the double-sided optical imaging film and generate an optical uniformity evaluation value. The second analysis module 13 performs a comprehensive analysis of the optical uniformity of the first and second surfaces of the double-sided optical imaging film based on the optical uniformity evaluation value, generating an optical uniformity analysis result. The third analysis module 14 performs cluster analysis on the optical uniformity analysis result to generate an optical uniformity index and an optical deviation parameter. The third analysis module 14 analyzes the optical reflection characteristics and transmission performance of the double-sided optical imaging film, respectively, to obtain optical reflection performance data and transmission performance data. Finally, the evaluation module 15 inputs the optical reflection performance data and transmission performance data into a pre-set analysis model, outputs a comprehensive optical performance score, and generates an optical performance evaluation report. This detection device effectively improves the detection accuracy and data consistency of double-sided optical imaging films, providing a reliable basis for quality control and performance evaluation in high-precision application scenarios.

[0111] It should be noted that, those skilled in the art will clearly understand that, for the sake of convenience and brevity of description, the specific working processes of the above-described device and each module can refer to the corresponding processes in the aforementioned embodiment of the detection method for a double-sided optical imaging film, and will not be repeated here.

[0112] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting a double-sided optical imaging film, characterized in that: include: Acquire first optical reflection data of a first surface and second optical reflection data of a second surface of a double-sided optical imaging film, and compare the first optical reflection data with the second optical reflection data to obtain global reflection difference data; The global reflection difference data is clustered using a K-means clustering algorithm to generate an optical uniformity cluster map. Based on the optical uniformity cluster map, the global deviation value of the optical uniformity of the film surface is calculated using a standard deviation method, and the local deviation value is calculated using a local weighted regression method; the global deviation value and the local deviation value are decomposed in the frequency domain using a fast Fourier transform to generate surface optical uniformity data; the surface optical uniformity data is analyzed in the frequency domain using a power spectral density analysis to obtain uniformity spectrum data; the uniformity spectrum data and the global deviation value are subjected to a dimensionality reduction analysis using a principal component analysis, and an optical uniformity characteristic index and an optical deviation distribution parameter are generated based on the analysis results; the optical uniformity characteristic index is subjected to spatial statistical analysis based on spatial autocorrelation to generate a global uniformity index; the global uniformity index and the optical deviation distribution parameter are subjected to regression analysis using a linear regression model to obtain an optical uniformity evaluation value; performing a comprehensive analysis of the optical uniformity of the first surface and the second surface of the double-sided optical imaging film according to the optical uniformity evaluation value to obtain an optical uniformity analysis result; performing clustering processing on the optical uniformity analysis results using a DBSCAN algorithm to identify regions of optical property changes on the film surface, generating an optical uniformity region partition map, extracting an optical uniformity mean value and a maximum deviation value of each property change region based on the optical uniformity region partition map, and generating an optical uniformity index using the optical uniformity mean value and the maximum deviation value; Performing classification analysis on the optical uniformity index using linear discriminant analysis to obtain an optical uniformity feature data set, and performing regression analysis on the optical uniformity feature data set using a support vector machine regression model to obtain optical reflection characteristic related parameters and optical deviation parameters; Performing an optical reflection performance fitting calculation on the optical reflection characteristic-related parameters according to a transfer matrix method to obtain optical reflection performance data of the double-sided optical imaging film; performing a transmission performance calculation on the optical deviation parameters using a Fresnel equation to obtain transmission performance data of the double-sided optical imaging film; The optical reflection performance data and the transmission performance data are input into a preset analysis model, a comprehensive optical performance score is output, and an optical performance evaluation report is generated based on the comprehensive optical performance score.

2. The method for detecting a double-sided optical imaging film according to claim 1, wherein: The step of acquiring first optical reflection data of the first surface and second optical reflection data of the second surface of the double-sided optical imaging film, and comparing the first optical reflection data with the second optical reflection data to obtain global reflection difference data comprises: Performing a multi-point optical reflection test on the first and second surfaces of the double-sided optical imaging film using a spectral reflection measurement device, and obtaining raw optical reflection data of the first and second surfaces using hyperspectral imaging technology; Inputting the original optical reflection data of the first surface and the original optical reflection data of the second surface into a preset reflection comparison model to generate initial reflection difference data and a full-surface optical reflection difference distribution map; Performing multi-scale decomposition on the full-surface optical reflection difference distribution map by discrete wavelet transform, and generating reflection difference spatial feature data based on the decomposition result; The initial reflection difference data is fused with the reflection difference spatial feature data to obtain global reflection difference data of the double-sided optical imaging film.

3. The method for detecting a double-sided optical imaging film according to claim 1, wherein: The step of comprehensively analyzing the optical uniformity of the first surface and the second surface of the double-sided optical imaging film according to the optical uniformity evaluation value to obtain an optical uniformity analysis result includes: Decomposing the optical uniformity evaluation value into a regional uniformity index and a global uniformity index, and generating an optical uniformity heat map of the double-sided optical imaging film based on the regional uniformity index; The global uniformity index and the optical uniformity heat map are trend analyzed using a least squares fitting method to obtain an optical uniformity change curve. The optical characteristic trend of the optical uniformity change curve is extracted using a Bessel curve fitting algorithm to obtain an optical uniformity analysis result.

4. The method for detecting a double-sided optical imaging film according to claim 3, wherein: The step of decomposing the optical uniformity evaluation value into a regional uniformity index and a global uniformity index comprises: Decomposing the optical uniformity evaluation value by using a weighted average decomposition algorithm to obtain a global uniformity deviation value and a local uniformity change value; Dividing the global uniformity deviation value into regions by a region growing method to generate a regional uniformity index; The local uniformity change value is fitted by radial basis function interpolation method to generate a global uniformity index.

5. The method for detecting a double-sided optical imaging film according to claim 1, wherein: The step of inputting the optical reflection performance data and the transmission performance data into a preset analysis model, outputting a comprehensive optical performance score, and generating an optical performance evaluation report based on the comprehensive optical performance score comprises: Performing weighted processing on the optical reflection performance data and the transmission performance data using an entropy weight method to generate a comprehensive optical performance value, and inputting the comprehensive optical performance value into a preset analysis model to obtain a comprehensive optical performance score; A fuzzy comprehensive evaluation method is applied to classify and evaluate the comprehensive score of the optical performance, and an optical performance evaluation report including reflection performance, transmission performance and deviation trend is generated based on the evaluation results.

6. A detection device for double-sided optical imaging film, characterized in that: include: A comparison module, configured to obtain first optical reflection data of a first surface and second optical reflection data of a second surface of the double-sided optical imaging film, and compare the first optical reflection data with the second optical reflection data to obtain global reflection difference data; a first analysis module, configured to perform clustering processing on the global reflection difference data using a K-means clustering algorithm to generate an optical uniformity cluster map; based on the optical uniformity cluster map, calculate an overall deviation value of the optical uniformity of the film surface using a standard deviation method, and calculate a local deviation value using a local weighted regression method; perform frequency domain decomposition on the overall deviation value and the local deviation value using a fast Fourier transform to generate surface optical uniformity data; perform frequency domain analysis on the surface optical uniformity data using a power spectral density analysis to obtain uniformity spectrum data; perform dimensionality reduction analysis on the uniformity spectrum data and the overall deviation value based on a principal component analysis; and generate an optical uniformity characteristic index and an optical deviation distribution parameter based on the analysis results; perform spatial statistical analysis on the optical uniformity characteristic index based on spatial autocorrelation to generate a global uniformity index; and perform regression analysis on the global uniformity index and the optical deviation distribution parameter using a linear regression model to obtain an optical uniformity evaluation value; a second analysis module, configured to comprehensively analyze the optical uniformity of the first surface and the second surface of the double-sided optical imaging film according to the optical uniformity evaluation value to obtain an optical uniformity analysis result; a third analysis module, configured to perform clustering processing on the optical uniformity analysis results using a DBSCAN algorithm, identify regions where optical properties of the film surface change, generate an optical uniformity region partition map, extract an optical uniformity mean and a maximum deviation value of each property change region based on the optical uniformity region partition map, and generate an optical uniformity index using the optical uniformity mean and the maximum deviation value; Performing classification analysis on the optical uniformity index using linear discriminant analysis to obtain an optical uniformity feature data set, and performing regression analysis on the optical uniformity feature data set using a support vector machine regression model to obtain optical reflection characteristic related parameters and optical deviation parameters; Performing an optical reflection performance fitting calculation on the optical reflection characteristic-related parameters according to a transfer matrix method to obtain optical reflection performance data of the double-sided optical imaging film; performing a transmission performance calculation on the optical deviation parameters using a Fresnel equation to obtain transmission performance data of the double-sided optical imaging film; An evaluation module is used to input the optical reflection performance data and the transmission performance data into a preset analysis model, output an optical performance comprehensive score, and generate an optical performance evaluation report based on the optical performance comprehensive score.

Images