CN117969046B

CN117969046B - LED light source defect type detection method and system and electronic equipment

Info

Publication number: CN117969046B
Application number: CN202410382928.4A
Authority: CN
Inventors: 李锋; 叶胜寿; 邱光富
Original assignee: Shenzhen Guangmai Electronics Co ltd
Current assignee: Shenzhen Guangmai Electronics Co ltd
Priority date: 2024-04-01
Filing date: 2024-04-01
Publication date: 2024-08-20
Anticipated expiration: 2044-04-01
Also published as: CN117969046A

Abstract

The application provides a method, a system and electronic equipment for detecting defect types of an LED light source, and relates to the technical field of LED light source detection. Acquiring light source information of an LED light source to be detected, and determining configuration parameters of multispectral imaging equipment according to the light source information; configuring the multispectral imaging device based on the configuration parameters to obtain a target multispectral imaging device, and performing imaging acquisition on an LED light source to be detected through the target multispectral imaging device to obtain a light source image; analyzing and extracting the light source image to obtain the characteristic information of the light source image; and carrying out quantitative analysis on the light source image characteristic information, and determining the defect type of the LED light source defect to be detected. The application improves the efficiency and accuracy of the defect type detection of the LED light source.

Description

LED light source defect type detection method and system and electronic equipment

Technical Field

The application relates to the technical field of LED light source detection, in particular to a method, a system and electronic equipment for detecting defect types of an LED light source.

Background

As a new generation of high-efficiency electric light-emitting source, LED light sources are widely used, and besides being used for illumination, LED light sources are also used for manufacturing display screens, for example, high-definition display screens nowadays are mostly manufactured by using LED light sources as light-emitting sources. In order to improve the quality of the LED light source, it is necessary to detect defects of the LED light source and determine the type of the defects in the manufacturing process to improve the process. However, currently, the defect type is generally determined manually through visual inspection, so that in mass production detection, a large number of quality inspectors are required, and errors are easy to occur, which results in low detection efficiency.

Disclosure of Invention

The application provides a method, a system, electronic equipment and a storage medium for detecting the defect type of an LED light source, which can improve the efficiency and the accuracy of detecting the defect type of the LED light source.

The technical scheme of the embodiment of the application is as follows:

in a first aspect, an embodiment of the present application provides a method for detecting a defect type of an LED light source, where the method includes:

Acquiring light source information of an LED light source to be detected, and determining configuration parameters of the multispectral imaging device according to the light source information;

Configuring the multispectral imaging device based on the configuration parameters to obtain a target multispectral imaging device, and performing imaging acquisition on an LED light source to be detected through the target multispectral imaging device to obtain a light source image;

analyzing and extracting the light source image to obtain the characteristic information of the light source image;

And carrying out quantitative analysis on the light source image characteristic information, and determining the defect type of the LED light source defect to be detected.

In the above technical solution, firstly, light source information of an LED light source to be detected is obtained, where the light source information includes parameters such as peak wavelength, spectral bandwidth, and the like of the LED light source. From these spectral characteristic parameters, the configuration of the multispectral imaging device, including the selection of sensor parameters and filter parameters, may be determined. In this way, the multispectral imaging device can be configured to be a target imaging device for the specific LED light source.

The specially configured target multispectral imaging equipment is used for multispectral imaging acquisition of the LED light source, so that a light source image containing various spectral characteristic information of the light source can be acquired. And then, carrying out characteristic analysis and extraction on the light source image to obtain abundant characteristic information such as spectral characteristics, morphological characteristics, texture characteristics and the like. And finally, quantitatively analyzing according to the characteristic information to judge various defect types of the LED light source.

Compared with the traditional manual judgment method, the technical scheme realizes automatic detection of the defect type of the LED light source. By configuring the multispectral imaging equipment to acquire the light source image and then extracting the image characteristic information, various parameters of the LED light source can be accurately acquired, and different types of defects can be judged, so that the detection efficiency and accuracy are greatly improved, the detection cost is reduced, and the quality control of the LED light source is facilitated.

In some embodiments of the application, the light source information includes spectral characteristics, and determining configuration parameters of the multispectral imaging device from the light source information includes:

and determining sensor parameters and filter parameters of the multispectral imaging device according to the spectral characteristics, wherein the sensor parameters and the filter parameters are configuration parameters.

In the above technical solution, the spectral characteristic parameters of the LED light source, such as peak wavelength, half-peak width, etc. From these spectral characteristic parameters, a hardware configuration of the multispectral imaging device may be determined, including selection of sensor parameters and filter parameters.

For the sensor parameters, an appropriate sensor type may be selected according to the peak wavelength and spectral range of the LED light source, ensuring that its spectral response range covers all spectral components of the LED light source. For the parameters of the filter, the bandpass range of the filter can be precisely configured according to the half-peak width of the LED light source, so that the filter only passes the wave band light with diagnostic significance.

By configuring the sensor and filter parameters of the imaging device according to the spectral characteristics of the light source, the multispectral imaging device can be optimized for the LED light source to be detected, and all relevant spectral information can be captured. In this way, in the subsequent analysis of the light source image, various parameters of the light source can be accurately obtained, and different types of defects can be judged, so that the loss of spectrum information and detection errors caused by improper equipment configuration are avoided. The configuration method improves the flexibility and accuracy of detection, is beneficial to defect judgment of different types of LED light sources, and expands the application range of the technology.

In some embodiments of the present application, analyzing and extracting a light source image to obtain light source image feature information includes:

denoising the light source image through a filter to obtain a first light source image;

Correcting the first light source image through a correction algorithm to obtain a second light source image;

Normalizing the second light source image to obtain a target light source image;

Extracting features of the target light source image to obtain spectrum feature data, morphological feature data and texture feature data of the target light source image;

the spectral feature data, morphological feature data, and texture feature data are determined as light source image feature information.

According to the technical scheme, according to the LED light source defect type detection method, after an original light source image is acquired, the image needs to be preprocessed so as to improve the effect of subsequent feature extraction. Firstly, the original image is subjected to denoising treatment through a filter, so that noise points in the image acquisition process can be eliminated, and the image quality is improved. Then, an image correction algorithm is used for carrying out geometric distortion correction on the denoised image, and the possible image distortion problem is corrected. And then, carrying out normalization processing on the corrected image, and eliminating the integral brightness fluctuation caused by different shooting conditions to obtain a target light source image. And finally, extracting features of the target image to obtain three types of information, namely spectral features, morphological features and texture features, and jointly forming the feature expression of the image. Compared with the simple process of directly extracting the features of the original image, the preprocessing flow can improve the reliability and accuracy of the feature extraction. The denoising process can weaken interference of uncorrelated noise on the characteristics; the correction process can reduce the influence of optical distortion on feature extraction; the normalization process can reduce the influence of the change in the photographing condition on the feature value. Therefore, the characteristic data obtained through pretreatment can truly reflect the characteristics of the light source rather than being interfered by external environments, is favorable for subsequent defect type judgment, and improves the detection robustness. The preprocessing method expands the applicable scene of the technology and enhances the practicability.

In some embodiments of the present application, performing quantitative analysis on the light source image feature information to determine a defect type of the LED light source defect to be detected includes:

determining the peak intensity, the peak wavelength, the width of a spectrum peak and spectrum integration of an LED light source to be detected based on the spectrum characteristic data, and determining the defect type of the defect of the LED light source to be detected based on the peak intensity, the peak wavelength, the width of the spectrum peak and the spectrum integration;

Determining wavelet coefficients of the light source image based on the texture feature data, and determining defect types of defects of the LED light source to be detected based on the wavelet coefficients;

and determining edge characteristics of the light source image based on the morphological characteristic data, and determining the defect type of the LED light source defect to be detected based on the edge characteristics of the light source image.

In the above technical solution, after the feature information of the light source image is obtained, three types of defects existing in the LED light source can be determined according to different types of feature data. First, parameters such as peak wavelength, peak intensity, spectral bandwidth, and integrated intensity of the light source can be calculated based on the spectral feature data. By analyzing the spectrum parameters, whether defects exist in the brightness, the color temperature, the color stability and the luminous flux of the LED light source, namely, whether performance defects exist or not can be judged. Second, based on the texture feature data, wavelet coefficients of the light source image may be extracted. The wavelet coefficients reflect detailed information at different scales of the image. By analyzing the wavelet coefficients, whether the LED light source has deformation defects can be judged. Finally, edge profile information of the light source image may be extracted based on the morphological feature data. By judging whether the outline is complete, whether the appearance of the LED light source is defective or not can be deduced.

In some embodiments of the present application, determining a defect type of an LED light source defect to be detected based on a peak intensity, a peak wavelength, a width of a spectral peak, and a spectral integral, includes:

Determining whether the defect type is a brightness defect according to the peak intensity and a preset intensity threshold, and determining the defect type as the brightness defect when the peak intensity is lower than the preset intensity threshold;

Determining whether the defect type is a color temperature defect according to the peak wavelength and a preset wavelength threshold, and determining the defect type as the color temperature defect when the peak wavelength deviation exceeds the preset wavelength threshold;

Determining whether the defect type is a color stability defect according to the width of the spectrum peak and a preset width threshold value, and determining the defect type as the color stability defect when the width of the spectrum peak exceeds the preset width threshold value;

And determining whether the defect type is a luminous flux defect according to the spectrum integral and a preset integral threshold value, and determining the defect type as the luminous flux defect when the spectrum integral exceeds the preset integral threshold value.

According to the technical scheme, according to the method for detecting the defect type of the LED light source, when judging the performance defect of the LED light source, the spectral characteristic parameters including peak intensity, peak wavelength, spectral peak width, integral intensity and the like are mainly utilized. The peak intensity reflects the brightness level of the LED, and whether brightness defects exist can be judged according to comparison between the peak intensity and a preset intensity threshold. The peak wavelength reflects the color temperature parameter of the LED, and whether the color temperature has defects can be judged by analyzing the deviation of the peak wavelength from the standard wavelength. The spectral peak width reflects the stability and monochromaticity of the luminous color of the LED, and whether the color stability has a problem can be judged according to the comparison between the spectral peak width and a preset width threshold value. The integral intensity reflects the luminous flux of the LED, and according to the comparison between the integral intensity and the standard threshold value, whether the luminous flux has defects or not can be judged

In some embodiments of the present application, determining a defect type of an LED light source defect to be detected based on edge features of a light source image includes:

and determining the light source outline of the LED based on the edge characteristics, and determining that the defect type is the appearance defect of the LED light source when the matching degree of the light source outline and a preset light source outline template is lower than the preset matching degree.

According to the technical scheme, according to the method for detecting the defect type of the LED light source, when the appearance defect of the LED light source is judged, the detection is mainly realized based on the edge characteristics of the light source image. First, the edge contour of the light source image is extracted, and the outline information of the light source is reflected. And then, matching and comparing the extracted actual edge profile with a preset standard light source profile template. If the matching degree of the two is high enough, the appearance of the light source is basically good; if the matching degree is too low, it can be judged that there is an outline defect.

In some embodiments of the present application, determining a defect type of the LED light source defect to be detected based on the wavelet coefficients includes:

performing preset coefficient threshold processing on the wavelet coefficient to obtain a target wavelet coefficient;

And determining a target difference value based on the target wavelet coefficient and a preset contrast coefficient, wherein when the target difference value exceeds the preset contrast difference value, the defect type is the deformation defect of the LED light source.

According to the technical scheme, when the deformation defect of the LED light source is judged according to the LED light source defect type detection method, the deformation defect is mainly realized by analyzing the wavelet coefficient of the light source image. Firstly, the extracted wavelet coefficients are subjected to threshold processing, and a plurality of high-frequency coefficients irrelevant to defect judgment are filtered out to obtain target wavelet coefficients reflecting deformation information. Then, the target wavelet coefficients are compared with the preset wavelet coefficients of the standard light source in a difference mode. If the difference value of the LED light source and the LED light source is too large and exceeds a preset threshold value, the LED light source can be judged to have deformation defects.

In a second aspect, an embodiment of the present application provides a system for detecting a defect type of an LED light source, including:

The data acquisition module is used for acquiring light source information of the LED light source to be detected and determining configuration parameters of the multispectral imaging device according to the light source information;

The light source image acquisition module is used for configuring the multispectral imaging equipment based on the configuration parameters to obtain target multispectral imaging equipment, and carrying out imaging acquisition on the LED light source to be detected through the target multispectral imaging equipment to obtain a light source image;

The characteristic information extraction module is used for analyzing and extracting the light source image to obtain the characteristic information of the light source image;

The defect type determining module is used for carrying out quantitative analysis on the light source image characteristic information and determining the defect type of the LED light source defect to be detected.

In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a memory, a user interface, and a network interface, where the memory is configured to store instructions, the user interface and the network interface are configured to communicate with other devices, and the processor is configured to execute the instructions stored in the memory, so that the electronic device performs any one of the methods provided in the first aspect.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing instructions that, when executed, perform the method of any one of the first aspects provided above.

In summary, one or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:

1. Firstly, light source information of an LED light source to be detected is obtained, wherein the light source information comprises parameters such as peak wavelength, spectral bandwidth and the like of the LED light source. From these spectral characteristic parameters, the configuration of the multispectral imaging device, including the selection of sensor parameters and filter parameters, may be determined. In this way, the multispectral imaging device can be configured to be a target imaging device for the specific LED light source.

2. Spectral characteristics parameters of the LED light source, such as peak wavelength, half-width, etc. From these spectral characteristic parameters, a hardware configuration of the multispectral imaging device may be determined, including selection of sensor parameters and filter parameters.

3. According to the LED light source defect type detection method, after an original light source image is acquired, the image needs to be preprocessed so as to improve the effect of subsequent feature extraction. Firstly, the original image is subjected to denoising treatment through a filter, so that noise points in the image acquisition process can be eliminated, and the image quality is improved. Then, an image correction algorithm is used for carrying out geometric distortion correction on the denoised image, and the possible image distortion problem is corrected. And then, carrying out normalization processing on the corrected image, and eliminating the integral brightness fluctuation caused by different shooting conditions to obtain a target light source image. And finally, extracting features of the target image to obtain three types of information, namely spectral features, morphological features and texture features, and jointly forming the feature expression of the image.

Compared with the simple process of directly extracting the features of the original image, the preprocessing flow can improve the reliability and accuracy of the feature extraction. The denoising process can weaken interference of uncorrelated noise on the characteristics; the correction process can reduce the influence of optical distortion on feature extraction; the normalization process can reduce the influence of the change in the photographing condition on the feature value. Therefore, the characteristic data obtained through pretreatment can truly reflect the characteristics of the light source rather than being interfered by external environments, is favorable for subsequent defect type judgment, and improves the detection robustness. The preprocessing method expands the applicable scene of the technology and enhances the practicability.

Drawings

FIG. 1 is a schematic flow chart of a method for detecting defect types of an LED light source according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a system for detecting defect types of LED light sources according to an embodiment of the present application;

fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order that those skilled in the art will better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments.

In describing embodiments of the present application, words such as "for example" or "for example" are used to mean serving as examples, illustrations, or descriptions. Any embodiment or design described herein as "such as" or "for example" in embodiments of the application should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "or" for example "is intended to present related concepts in a concrete fashion.

In the description of embodiments of the application, the term "plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating an indicated technical feature. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

The embodiment of the application provides a method, a system, electronic equipment and a storage medium for detecting the defect type of an LED light source, wherein the LED light source is used as a new-generation high-efficiency environment-friendly illuminant, is rapidly replacing a traditional illumination light source, and is widely applied in the illumination field. Meanwhile, the LED light source is widely applied to manufacturing of displays, and most of the current mainstream high-definition display screens adopt LEDs as backlight sources. With the rapid development of the LED industry, the quality control of the LED light source is particularly important. In the process of producing and manufacturing the LED, the manufactured LED needs to be subjected to defect detection, and the specific type of the defect is further judged, so that the production process is improved in a targeted manner, and the product qualification rate is improved.

However, at present, the judgment of the defect type of the LED mainly depends on manual visual inspection, and a worker needs to check the luminous condition of the LED by naked eyes to judge what type of defect exists. This method is inefficient in mass production and cannot meet the speed requirements of the test. Meanwhile, the manual judgment is easily subjectively influenced, the accuracy is low, and the situation of misjudgment of the defect type possibly occurs. This results in a failure to purposefully optimize the process flow and a failure to thoroughly improve the optical performance and quality stability of the LED. Therefore, there is a need to develop a new method for automatically and efficiently judging various defect types of LEDs to meet the requirements of quality detection on speed and accuracy and ensure high reliability of LED products.

The technical scheme provided by the embodiment of the application is further described below with reference to the accompanying drawings.

Referring to fig. 1, fig. 1 is a flowchart of a method for detecting a defect type of an LED light source according to an embodiment of the present application. An LED light source defect type detection method, which is performed by a processor in an electronic device or a readable storage medium, includes steps S100, S200, S300, and S400.

Step S100, light source information of the LED light source to be detected is obtained, and configuration parameters of the multispectral imaging device are determined according to the light source information.

Specifically, in order to enable automatic defect detection of the LED light source, the first step needs to obtain light source information of the LED light source to be detected. The light source information includes various optical characteristic parameters of the LED light source, such as peak wavelength, spectral bandwidth, color temperature, etc. of the LED. The purpose of these parameters is to select the appropriate multispectral imaging device and to determine the relevant configuration parameters based on the characteristics of the LEDs.

Specifically, the light emission spectrum curve of the LED to be detected can be measured in advance, and parameters such as the peak wavelength and the half-peak width of the LED can be obtained. The optical configuration of the multispectral imaging device is then determined from these spectral characteristic parameters, including selecting the appropriate filter type and sensor type to have a response range matching the emission range of the LED light source. In addition, the parameter settings such as the exposure time of the imaging device may also be calculated from the light source parameters. Through such configuration optimization, a multispectral imaging device specifically configured for the specific LED light source can be obtained.

The advantage of this configuration is that an optimal configuration of the imaging device can be determined for each LED based on the characteristics of the different types of LEDs, thereby performing optimal defect detection. Therefore, the method can ensure that all necessary spectrum information is contained when the light source image is acquired, improve the subsequent detection accuracy and realize the comprehensive automatic detection of various LED light source defects.

On the basis of the above embodiment, as an alternative embodiment, the light source information includes a spectral characteristic, and determining the configuration parameter of the multispectral imaging device according to the light source information includes:

Specifically, after the light source information of the LED light source to be detected is obtained, since the information includes the spectral characteristic parameters of the LED, the configuration parameters of the multispectral imaging device can be determined according to the spectral characteristics, and the key is the selection of the sensor parameters and the filter parameters. The purpose of this configuration of the imaging device parameters is to ensure that the device's optical response range covers the full spectral distribution range of the LED light source. Only if the light source characteristics and the imaging device characteristics are correctly matched, an LED image containing the entire spectral information can be obtained later.

Specifically, the appropriate sensor type may be selected based on the peak wavelength of the LED, ensuring that the peak wavelength range of the response of the sensor coincides with the peak wavelength range of the LED. Meanwhile, a bandpass filter with proper wave band width can be selected according to the spectral bandwidth of the LED light source, and light rays of irrelevant wave bands are filtered. By such a targeted configuration, an imaging device with an optimal response to the particular LED light source can be obtained. When the LED light source image is acquired subsequently, all the representative spectrum components can be acquired correctly, so that the accurate analysis of the light source performance parameters is facilitated, and the defect detection accuracy is improved. The parameter configuration method enables the detection system to have good universal adaptability.

Step S200, configuring the multispectral imaging device based on the configuration parameters to obtain a target multispectral imaging device, and performing imaging acquisition on an LED light source to be detected through the target multispectral imaging device to obtain a light source image.

Specifically, after acquiring the light source information of the LED light source to be detected and determining the parameter configuration scheme of the imaging device, the multispectral imaging device is actually adjusted and optimized according to the configuration parameters. Thus, a target imaging device which is specially configured for the current LED light source to be detected can be obtained.

Specifically, according to the predetermined parameter specifications such as the type of the optical filter and the type of the sensor, the hardware composition of the multispectral imaging device is adjusted and combined, and a proper optical filter is installed to be connected with a matched image sensor. And then, according to the calculated optimal exposure time, gain coefficient and other parameter settings, the working mode of the imaging equipment is configured. By such adjustment, the optical response characteristics of the imaging device can be optimally matched with the characteristics of the LED light source to be detected. The LED light source is imaged and acquired by using the target imaging equipment which is accurately configured, and a light source image containing all necessary spectrum information can be acquired. Thus, a foundation is laid for subsequent processing analysis of the image. The proposal has the advantages of realizing personalized imaging of different LED light sources, ensuring the quality of the acquired image, avoiding acquisition distortion caused by improper configuration and improving the flexibility and accuracy of detection.

And step S300, analyzing and extracting the light source image to obtain the characteristic information of the light source image.

Specifically, after the target imaging device is adopted to obtain the image of the LED light source to be detected, the next step is to perform feature analysis and extraction on the obtained light source image so as to obtain the image feature information required by detection. The image feature extraction is required because the problem of the light source is difficult to directly see from the original image, and the parameters reflecting the performance of the light source are required to be extracted through analysis to perform subsequent defect judgment.

Specifically, a series of pre-processing, including denoising, correction, etc., may be performed on the original light source image to improve the image quality. And then, carrying out image segmentation on the preprocessed image, and extracting an image area of the single LED chip. And then, spectral characteristic analysis can be carried out on the segmented image to obtain parameters such as a light-emitting spectrum curve, peak wavelength and the like of the LED. Meanwhile, shape and texture feature analysis can be performed to obtain feature data reflecting the appearance and surface information of the LED.

By combining these spectral features, shape features and texture features, a light source image feature vector containing rich information can be constructed. These features reflect various aspects of the performance, shape quality, etc. of the LED. By carrying out the feature extraction, a reliable basis can be provided for the subsequent defect type judgment, and the analysis accuracy is improved.

On the basis of the above embodiment, as an optional embodiment, analyzing and extracting the light source image to obtain the light source image feature information, including:

step S310, denoising the light source image through a filter to obtain a first light source image;

Specifically, after an original LED light source image is obtained, denoising the image is needed in the first step, and a first light source image is obtained. The denoising process is performed to remove various noise components in the original image, which are introduced by the imaging device noise and interfere with subsequent feature extraction and analysis. Specifically, different types of low-pass filters or median filters can be designed to filter the original light source image, smooth the image and suppress the influence of noise points. Common filters include gaussian filters, mean filters, etc. This process results in a first light source image in which the noise effects are suppressed. The denoising processing has the effects of effectively reducing various noises in the original image, improving the image quality and providing high-quality input images for the subsequent picture analysis algorithm. This helps to improve the accuracy of feature extraction and the robustness of image analysis, and avoid noise from interfering with the determination result. By adopting the denoising pretreatment step, the performance of the whole detection and identification system can be improved.

Step S320, correcting the first light source image through a correction algorithm to obtain a second light source image;

Specifically, after denoising the original light source image, geometric distortion correction is required to be performed on the denoised first light source image in the next step, so as to obtain a second light source image. The purpose of image correction is to eliminate various distortions possibly generated in the acquisition process of the light source image, and mainly comprises image distortion, rotation and the like. These distortions can adversely affect subsequent image analysis and feature extraction.

Step S330, carrying out normalization processing on the second light source image to obtain a target light source image;

Specifically, after denoising and correcting the light source image, the second light source image needs to be normalized in the next step to eliminate the overall brightness change caused by different shooting conditions, so as to obtain the target light source image. The normalization is performed to reduce the effect of the overall brightness variation of the light source image under different imaging conditions on subsequent analysis. Different imaging conditions such as exposure time, light intensity and the like can cause the overall brightness of the image to fluctuate. Specifically, an image equalization algorithm may be designed to automatically adjust the contrast and brightness of the second light source image, eliminating the overall contrast differences resulting from imaging condition variations. Thus, a target light source image with uniform brightness can be obtained. The effect of image normalization is that the influence of imaging condition change on the integral image characteristic can be effectively eliminated. During subsequent parameter analysis based on image content, errors caused by imaging environment changes can be greatly reduced, and consistency and reliability of results are improved. The normalization processing can reduce the dependence of the external environment on the detection performance, and enhance the application range of the system.

Step S340, determining the spectral feature data, the morphological feature data and the texture feature data as light source image feature information;

specifically, after preprocessing a light source image, the next step is to perform feature extraction on the preprocessed target light source image, and obtain three types of data including spectral features, morphological features and texture features.

The purpose of the feature extraction is to extract parameters which can effectively represent the performance of the light source from the image as a judgment basis. The direct analysis from the image pixel data is not intuitive, and the quantized judgment index is not easy to establish.

Specifically, a spectrum analysis algorithm can be designed for the light source image to obtain spectrum characteristic data such as a light emission spectrum curve, a peak wavelength and the like of the light source. Meanwhile, a morphological analysis algorithm can be designed, and the outline of the light source can be obtained as morphological feature data through means such as edge detection. An image processing method can be also adopted to obtain parameters of the image surface texture as texture feature data. Through such feature extraction, three types of feature data representing the light source performance, the external shape, and the surface quality can be obtained. The characteristic data can be directly related to various defects of the light source to establish a quantitative judgment index. The feature extraction can provide information support for subsequent intelligent judgment, and the accuracy of detection and identification is improved.

On the basis of the above embodiment, as an optional embodiment, performing quantization analysis on the light source image feature information to determine a defect type of the LED light source defect to be detected, including:

Step S341, determining the peak intensity, the peak wavelength, the width of the spectrum peak and the spectrum integral of the LED light source to be detected based on the spectrum characteristic data, and determining the defect type of the defect of the LED light source to be detected based on the peak intensity, the peak wavelength, the width of the spectrum peak and the spectrum integral;

Specifically, after the spectral feature data of the LED light source image is obtained, parameters such as the peak intensity, the peak wavelength, the spectral peak width, the integral intensity and the like of the light source can be determined according to the obtained spectral feature data, and whether the light source has a performance defect can be judged based on the spectral feature parameters. The purpose of extracting the spectral characteristic parameters is to obtain a quantization index reflecting the luminous performance of the LED. These parameters may directly correspond to performance items of the light source such as brightness, color temperature, color purity, luminous flux, etc. Only these quantization parameters are obtained, and quantitative defect determination can be performed.

Specifically, the spectral curve may be analyzed to determine the intensity peak, the wavelength at which the peak is located, the width at half maximum, and the integrated area. And comparing the parameter value with a threshold value set by a standard to check whether the parameter value is within a tolerance range, and judging whether the corresponding performance has defects. The acquisition of the spectral characteristic parameters can realize the accurate quantitative analysis of each index of the LED performance, is favorable for establishing an automatic quantitative judgment mechanism, replaces the traditional empirical judgment, improves the objectivity and consistency of the result, and reduces the probability of manual misjudgment. By adopting the technical scheme, the LED defect detection can be promoted to develop towards the direction of intellectualization and precision.

On the basis of the above embodiment, as an alternative embodiment, the method for determining the peak intensity, the peak wavelength, the width of the spectrum peak and the spectrum integral of the LED light source to be detected based on the spectrum characteristic data, and determining the defect type of the defect of the LED light source to be detected based on the peak intensity, the peak wavelength, the width of the spectrum peak and the spectrum integral includes the following steps:

Step S3411, determining whether the defect type is a brightness defect according to the peak intensity and a preset intensity threshold, and determining the defect type as the brightness defect when the peak intensity is lower than the preset intensity threshold;

Specifically, after the spectral characteristic parameters of the LED light source image are obtained, whether the light source has brightness defects can be judged according to the comparison condition of the peak intensity and the preset intensity threshold. The purpose of the peak intensity determination is to obtain a quantified parameter reflecting the brightness performance of the light source. The peak intensity corresponds directly to the luminous intensity level of the LED. Specifically, the extracted peak intensity value of the light source is compared with an intensity threshold value set in advance according to a standard. If the peak intensity of the light source is below this threshold, it may be determined that the light source has a brightness defect. Through quantitative analysis of peak intensity, accurate identification of LED brightness defects can be realized, and the LED brightness defects are converted into an automatic judging process, so that the traditional manual visual inspection method is replaced. By adopting the technical scheme, whether the brightness of the light source meets the standard can be effectively judged, and the objectivity and consistency of judgment are improved.

Step S3412, determining whether the defect type is a color temperature defect according to the peak wavelength and a preset wavelength threshold, and determining the defect type as the color temperature defect when the peak wavelength deviation exceeds the preset wavelength threshold;

Specifically, after the spectral characteristic parameters of the LED light source image are obtained, whether the light source has a color temperature defect or not can be judged according to the comparison condition of the peak wavelength and the preset wavelength threshold. The purpose of the peak wavelength determination is to obtain a quantified parameter reflecting the color temperature performance of the light source. The peak wavelength corresponds directly to the emission color temperature of the LED. Specifically, the extracted peak wavelength value of the light source is compared with a wavelength threshold preset according to a standard. If the peak wavelength deviation of the light source exceeds the threshold range, the light source can be judged to have color temperature defects. Through quantitative analysis of peak wavelength, accurate identification of LED color temperature deviation defects can be realized, and the LED color temperature deviation defects are converted into an automatic judging process, so that the traditional manual visual inspection method is replaced. By adopting the technical scheme, whether the color temperature of the light source is stable and reaches the standard can be effectively judged, and the objectivity and consistency of judgment are improved.

Step S3413, determining whether the defect type is a color stability defect according to the width of the spectrum peak and a preset width threshold, and determining the defect type as the color stability defect when the width of the spectrum peak exceeds the preset width threshold;

Specifically, after the spectral characteristic parameters of the LED light source image are obtained, whether the light source has color stability defects can be judged according to the comparison condition of the spectral peak width and the preset width threshold. The purpose of the peak width determination is to obtain a quantified parameter reflecting the color stability of the light source. The peak width directly corresponds to the luminous color purity of the LED. Specifically, the extracted light source peak width value is compared with a width threshold value preset according to a standard. If the peak width of the light source exceeds the threshold range, the light source can be judged to have color stability defects. Through quantitative analysis of peak width, accurate identification of the color stability defect of the LED can be realized, and the LED color stability defect is converted into an automatic judging process, so that the traditional manual visual inspection method is replaced. By adopting the technical scheme, whether the color purity of the light source is stable and reaches the standard can be effectively judged, and the objectivity and consistency of judgment are improved.

Step S3414 determines whether the defect type is a light flux defect according to the spectrum integration and the preset integration threshold, and determines the defect type as the light flux defect when the spectrum integration exceeds the preset integration threshold.

Specifically, after the spectral characteristic parameters of the LED light source image are obtained, whether the light source has a luminous flux defect can be judged according to the comparison condition of spectral integral and a preset integral threshold. The purpose of the integration calculation is to obtain a quantized parameter reflecting the luminous flux performance of the light source. The integration area corresponds directly to the luminous flux of the LED. Specifically, the extracted integrated area value of the light source is compared with an integrated threshold value preset according to a standard. If the integrated area of the light source exceeds the threshold range, it can be judged that the light source has a luminous flux defect. Through quantitative analysis of the integral area, the LED luminous flux defect can be accurately identified, and the LED luminous flux defect is converted into an automatic judging process, so that the traditional manual visual inspection method is replaced. By adopting the technical scheme, whether the luminous flux of the light source meets the standard can be effectively judged, and the objectivity and consistency of judgment are improved.

Step S342, determining wavelet coefficients of the light source image based on the texture feature data, and determining defect types of the LED light source defects to be detected based on the wavelet coefficients;

specifically, after texture feature data of the LED light source image is acquired, a wavelet coefficient of the light source image may be determined based on the data, and wavelet analysis may be used to determine whether the light source has a deformation defect. The purpose of extracting wavelet coefficients is to obtain feature parameters reflecting local details and abrupt change information of the image. Wavelet transforms are sensitive to local anomalies, which can be used to detect deformation defects. Specifically, a wavelet transform may be performed on the light source image to extract a series of wavelet coefficients that represent the level of detail of the image. And then analyzing the difference degree of the wavelet coefficient and the wavelet coefficient of the standard light source, and judging the deformation defect if obvious deviation exists. By wavelet analysis, it is possible to effectively detect whether or not there is a minute distortion in the shape of the light source. The wavelet coefficients more reflect shape deformation information than if the image data were analyzed directly. By adopting the technical scheme, the automatic identification of the LED deformation defects can be realized, the omission of detection is avoided, and the detection effect is improved.

On the basis of the above embodiment, as an alternative embodiment, determining the defect type of the LED light source defect to be detected based on the wavelet coefficient includes:

Step S3421, performing preset coefficient threshold processing on the wavelet coefficients to obtain target wavelet coefficients;

Specifically, after the wavelet coefficient of the LED light source image is obtained, in order to effectively determine the deformation defect, the wavelet coefficient needs to be subjected to preset threshold processing to obtain a target wavelet coefficient. The thresholding is performed to filter out wavelet coefficients that are not relevant to the deformation determination. Only the target coefficient reflecting the deformation information is reserved, so that the accuracy of subsequent judgment can be improved. Specifically, wavelet scale and direction subbands sensitive to deformation can be selected based on a priori experience, and a retention threshold for the corresponding subbands can be set. Then, invalid coefficients with wavelet coefficients absolute values lower than a threshold value are filtered out, and target wavelet coefficients higher than the threshold value are reserved. Therefore, effective information related to deformation discrimination in wavelet analysis can be extracted, irrelevant noise is removed, and subsequent discrimination is more accurate. By adopting the technical scheme, the target distinguishing characteristics can be effectively extracted, and the deformation defect recognition effect is improved.

In step S3422, a target difference is determined based on the target wavelet coefficient and a preset contrast coefficient, and when the target difference exceeds the preset contrast difference, the defect type is a deformation defect of the LED light source.

Specifically, after the target wavelet coefficients are obtained, whether the deformation defect exists in the LED light source can be judged based on the difference value condition of the coefficients and the standard contrast coefficient. The purpose of the difference judgment is to judge the presence of deformation by quantitative contrast analysis. Only a means for establishing quantifiable discrimination can automatic identification be achieved.

Specifically, the extracted target wavelet coefficient is subjected to point-by-point difference comparison with the standard comparison coefficient of the normal light source. If the difference value exceeds the range of the preset threshold value, the LED can be judged to have deformation defects. Through difference discrimination, the deformation defect can be automatically identified, and subjective judgment errors are avoided. By adopting the technical scheme, the deformation distinguishing characteristics can be effectively extracted, and the recognition effect and consistency are improved.

Step S343, determining the edge characteristics of the light source image based on the morphological characteristic data, and determining the defect type of the LED light source defect to be detected based on the edge characteristics of the light source image.

Specifically, after the morphological feature data of the LED light source image is obtained, the edge feature of the light source image may be extracted based on the data, and whether the appearance defect exists may be determined according to the edge information. The purpose of extracting the edge features is to obtain parameters reflecting the outline of the light source. The edges directly correspond to the outline of the light source. Only clear edge features are obtained for the appearance detection. Specifically, edge detection may be performed on the light source image, and edge features expressing the outline may be extracted. And then comparing the extracted edge with the standard light source outline, and analyzing the matching degree of the extracted edge and the standard light source outline. If the matching degree is low, it can be judged as an outline defect. By utilizing the edge characteristics, the appearance defect with abnormal shape can be effectively identified. Compared with the direct comparison image, the edge information can more accurately reflect the appearance difference. By adopting the technical scheme, the automatic detection of the appearance defects of the LEDs can be realized, the detection range is enlarged, and the effect is improved.

On the basis of the above embodiment, as an alternative embodiment, determining a defect type of the LED light source defect to be detected based on the edge feature of the light source image includes:

Specifically, after the edge features of the LED light source image are obtained, the outline of the light source can be determined based on the edge features and matched with a standard outline template, and whether appearance defects exist or not is judged according to the matching result. The purpose of the extraction of the profile is to obtain a feature that accurately characterizes the appearance of the light source. Only if contour information is acquired, contour comparison analysis can be performed. Specifically, a contour curve expressing the outline of the LED may be extracted by an edge detection algorithm. The extracted profile is then matched to a set standard profile template. If the matching degree of the two is lower than a preset threshold value, the LED can be judged to have appearance defects. By the contour matching method, the appearance defect detection can be converted into an automatically realized process, and errors in manual experience judgment are avoided. By adopting the technical scheme, the appearance defect can be accurately identified, and the detection effect is improved.

In step S350, the spectral feature data, morphological feature data, and texture feature data constitute light source image feature information.

Specifically, after spectral feature data, morphological feature data and texture feature data of the light source image are obtained, the three types of feature data are integrated to form feature information of the light source image. The purpose of such a representation by combining different types of characteristic data is to fully reflect information about various aspects of the light source image, including optical performance parameters, topographical features, and surface quality features. Only if the comprehensive information is collected, the light source can be comprehensively and accurately judged. Specifically, the spectral characteristics reflect mainly the light emission performance of the light source; the morphological characteristics reflect the shape of the outline; the texture features reflect the surface quality. The three types of features are combined according to a certain structure, so that a light source image feature vector or feature matrix containing rich information can be formed. The comprehensively constructed characteristic information can provide a richer judgment basis compared with single characteristic data. When the intelligent identification is carried out on different types of defects in the follow-up process, the information can be comprehensively utilized to carry out multi-angle analysis, and the judgment accuracy is improved. By adopting the comprehensive characteristic expression mode, the detection and recognition capability of the system can be enhanced.

And step S400, quantitatively analyzing the light source image characteristic information to determine the defect type of the LED light source defect to be detected.

Specifically, after the feature information of the LED light source image is obtained, quantitative analysis is required to be performed on the light source based on the features so as to determine the defect type of the LED light source image.

The purpose of quantitative analysis is to realize automatic intelligent judgment of the defect type of the LED instead of relying on manual experience judgment. Only establishing quantifiable judgment indexes and standards can truly realize the controllability and objectivity of the judgment result.

Specifically, a clear numerical determination threshold or range may be set according to spectral characteristic parameters of the light source, such as peak wavelength, half-width, and the like. And judging whether each parameter is in a normal range, and identifying performance defects such as brightness defects, color temperature defects and the like. Meanwhile, appearance defect detection can be performed based on the difference between the appearance of the light source and the standard template based on the shape feature comparison. The possibility of deformation defects can also be judged by means of wavelet analysis and the like.

By the quantitative analysis judging method, the specific defect type of the LED light source can be clearly judged, and compared with empirical judgment, the accuracy and reliability of the result can be greatly improved, and the artificial misjudgment probability is reduced. Meanwhile, quantitative statistics of results can be performed, and scientific basis is provided for quality control of the LED manufacturing process. By adopting the analysis method, the whole detection efficiency and the automation degree can be effectively improved.

As shown in fig. 2, an embodiment of the present application provides an LED light source defect type detection system 100, where the LED light source defect type detection system 100 obtains light source information of an LED light source to be detected through a data obtaining module 110, and determines configuration parameters of a multispectral imaging device according to the light source information; then, the light source image acquisition module 120 configures the multispectral imaging device based on the configuration parameters to obtain a target multispectral imaging device, and performs imaging acquisition on the LED light source to be detected through the target multispectral imaging device to obtain a light source image; secondly, analyzing and extracting the light source image through a characteristic information extraction module 130 to obtain the characteristic information of the light source image; and finally, quantitatively analyzing the light source image characteristic information through a defect type determining module 140 to determine the defect type of the LED light source defect to be detected.

It should be noted that, the data acquisition module 110 is connected to the light source image acquisition module 120, the light source image acquisition module 120 is connected to the feature information extraction module 130, and the feature information extraction module 130 is connected to the defect type determination module 140. The above-described LED light source defect type detection method is applied to the LED light source defect type detection system 100.

Also to be described is: in the system provided in the above embodiment, when implementing the functions thereof, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be implemented by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the system and method embodiments provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the system and method embodiments are detailed in the method embodiments, which are not repeated herein.

The application also discloses electronic equipment. Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. The electronic device 500 may include: at least one processor 501, at least one network interface 504, a user interface 503, a memory 505, at least one communication bus 502.

Wherein a communication bus 502 is used to enable connected communications between these components.

The user interface 503 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 503 may further include a standard wired interface and a standard wireless interface.

The network interface 504 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.

Wherein the processor 501 may include one or more processing cores. The processor 501 connects various parts throughout the server using various interfaces and lines, performs various functions of the server and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 505, and invoking data stored in the memory 505. Alternatively, the processor 501 may be implemented in at least one hardware form of digital signal Processing (DIGITAL SIGNAL Processing, DSP), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 501 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 501 and may be implemented by a single chip.

The Memory 505 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 505 comprises a non-transitory computer readable medium (non-transitory computer-readable storage medium). Memory 505 may be used to store instructions, programs, code sets, or instruction sets. The memory 505 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-described various method embodiments, etc.; the storage data area may store data or the like involved in the above respective method embodiments. The memory 505 may also optionally be at least one storage system located remotely from the aforementioned processor 501. Referring to fig. 3, an operating system, a network communication module, a user interface module, and an application program of an LED light source defect type detection method may be included in a memory 505 as a computer storage medium.

In the electronic device 500 shown in fig. 3, the user interface 503 is mainly used for providing an input interface for a user, and acquiring data input by the user; and the processor 501 may be configured to invoke an application program in the memory 505 that stores a method of detecting a defect type of an LED light source, which when executed by the one or more processors 501, causes the electronic device 500 to perform the method as in one or more of the embodiments described above. It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all of the preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.

In the several embodiments provided by the present application, it should be understood that the disclosed system may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the partitioning of elements, merely a logical functional partitioning, and there may be additional partitioning in actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not implemented. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, system or unit indirect coupling or communication connection, electrical or otherwise.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in whole or in part in the form of a software product stored in a memory, comprising several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method of the various embodiments of the present application. And the aforementioned memory includes: various media capable of storing program codes, such as a U disk, a mobile hard disk, a magnetic disk or an optical disk.

The above are merely exemplary embodiments of the present disclosure and are not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure.

This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.

Claims

1. The method for detecting the defect type of the LED light source is characterized by comprising the following steps of:

acquiring light source information of an LED light source to be detected, wherein the light source information comprises spectral characteristics, and determining sensor parameters and filter parameters of multispectral imaging equipment according to the spectral characteristics, wherein the sensor parameters and the filter parameters are configuration parameters;

Configuring the multispectral imaging device based on the configuration parameters to obtain a target multispectral imaging device, and performing imaging acquisition on the LED light source to be detected through the target multispectral imaging device to obtain a light source image;

Extracting features of the target light source image to obtain spectral feature data, morphological feature data and texture feature data of the target light source image;

Determining the spectral feature data, the morphological feature data and the texture feature data as light source image feature information;

Determining the peak intensity, the peak wavelength, the width of a spectrum peak and spectrum integration of the LED light source to be detected based on the spectrum characteristic data, and determining the defect type of the defect of the LED light source to be detected based on the peak intensity, the peak wavelength, the width of the spectrum peak and the spectrum integration;

Determining a wavelet coefficient of the light source image based on the texture feature data, and determining a defect type of the LED light source defect to be detected based on the wavelet coefficient;

and determining the edge characteristics of the light source image based on the morphological characteristic data, and determining the defect type of the LED light source defect to be detected based on the edge characteristics of the light source image.

2. The method of claim 1, wherein the determining the defect type of the LED light source defect to be detected based on the peak intensity, the peak wavelength, the width of the spectral peak, and the spectral integral comprises:

And determining whether the defect type is a luminous flux defect according to the spectrum integral and a preset integral threshold, and determining the defect type as the luminous flux defect when the spectrum integral exceeds the preset integral threshold.

3. The method of claim 1, wherein the determining a defect type of the LED light source defect to be detected based on edge features of the light source image comprises:

and determining the light source outline of the LED based on the edge characteristics, and determining the defect type as the appearance defect of the LED light source when the matching degree of the light source outline and a preset light source outline template is lower than the preset matching degree.

4. The method of claim 1, wherein the determining the defect type of the LED light source defect to be detected based on the wavelet coefficients comprises:

5. An LED light source defect type detection system, the system comprising:

the data acquisition module is used for acquiring light source information of the LED light source to be detected, wherein the light source information comprises spectral characteristics, and determining sensor parameters and filter parameters of the multispectral imaging equipment according to the spectral characteristics, and the sensor parameters and the filter parameters are configuration parameters;

The characteristic information extraction module is used for denoising the light source image through a filter to obtain a first light source image;

The defect type determining module is used for determining the peak intensity, the peak wavelength, the width of a spectrum peak and the spectrum integral of the LED light source to be detected based on the spectrum characteristic data, and determining the defect type of the defect of the LED light source to be detected based on the peak intensity, the peak wavelength, the width of the spectrum peak and the spectrum integral;

6. An electronic device comprising a processor (501), a memory (505), a user interface (503), a communication bus (502) and a network interface (504), the processor (501), the memory (505), the user interface (503) and the network interface (504) being respectively connected to the communication bus (502), the memory (505) being adapted to store instructions, the user interface (503) and the network interface (504) being adapted to communicate to other devices, the processor (501) being adapted to execute the instructions stored in the memory (505) to cause the electronic device (500) to perform the method according to any of claims 1-4.

7. A computer readable storage medium storing instructions which, when executed, perform the method of any one of claims 1-4.