Image processing-based PMOLED screen defect detection system
By constructing a multi-dimensional collaborative detection mechanism that combines brightness decay characteristics and driving response state, continuous tracking and anomaly classification of PMOLED screen defects are achieved, solving the problem of defect judgment deviation in existing technologies and improving detection accuracy and stability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GUANGXI DAYUAN TECHNOLOGY CO LTD
- Filing Date
- 2026-04-27
- Publication Date
- 2026-07-21
AI Technical Summary
Existing technologies lack a continuous judgment link for the defect evolution process of PMOLED screens, which makes it easy for the judgment results of different types of defects to be biased, affecting the accuracy of anomaly classification.
By constructing an image processing-based PMOLED screen defect detection system, a multi-dimensional collaborative detection mechanism is formed by using a grayscale acquisition module, an attenuation recognition module, a boundary driving module, and an anomaly judgment module, combined with brightness attenuation characteristics, boundary pixel changes, and driving response status, to achieve continuous tracking and state characterization of the defect evolution process.
It improves the accuracy of defect location and anomaly classification, enhances the ability to distinguish different anomaly types, and improves the consistency and stability of detection results.
Smart Images
Figure CN122434867A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of defect detection technology, and more specifically, to a PMOLED screen defect detection system based on image processing. Background Technology
[0002] As a self-emissive display device, the light emission characteristics of each display area of a PMOLED screen will vary with driving conditions and usage status during long-term operation. During the testing process, the brightness distribution of the area is usually analyzed by loading a test pattern and acquiring display images, and the display status is evaluated in combination with the driving side information.
[0003] The existing technology has the following shortcomings: Current detection methods lack a unified mechanism for characterizing the relationship between the historical defect change boundary expansion process and the driving response state during the analysis process. This makes it difficult to form a continuous judgment link for the defect evolution process, which can lead to deviations in the judgment results when different types of defects exhibit similar characteristics and affect the accuracy of anomaly classification. Therefore, an image processing-based PMOLED screen defect detection system is proposed.
[0004] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention
[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a PMOLED screen defect detection system based on image processing. This system constructs a brightness attenuation characterization mechanism by fusing regional grayscale acquisition with historical defect records, analyzes the boundary expansion trend by combining boundary pixel changes within the observation period, introduces driving scan line current to characterize the driving response state, and extracts emission shutdown delay features under multiple test pattern switching conditions to form a timing fluctuation judgment link, thereby solving the problems mentioned in the background art.
[0006] To achieve the above objectives, the present invention provides the following technical solution: a PMOLED screen defect detection system based on image processing, comprising a grayscale acquisition module, an attenuation recognition module, a boundary driving module, and an anomaly determination module, the functions of each module being as follows: The grayscale acquisition module is used to divide the PMOLED screen under test into regions, detect the grayscale value of the pixels in each region and calculate the average grayscale of the region, access the historical record database to obtain historical defect records of the divided regions and count the number of defect markings, and pass the average grayscale of the region and the number of defect markings to the attenuation recognition module. The attenuation recognition module is used to evaluate the brightness attenuation characteristics of the divided region by combining the average gray level of the region and the number of defect markings. Based on the brightness attenuation characteristics, the divided regions are filtered and marked. An observation and evaluation period is set. Within the observation period, the boundary pixel data of the marked divided regions are detected and transmitted to the boundary driving module. The boundary driving module uses boundary pixel data to analyze the boundary expansion trend, reads the driving scan line current of the marked area, analyzes the driving response status based on the driving scan line current, and evaluates the light decay level of the marked area in combination with the boundary expansion trend and passes it to the anomaly judgment module. The anomaly detection module performs test pattern switching processing on the marked area, collects the light emission shutdown delay time of the marked area under different test patterns, generates a timing fluctuation index based on the light emission shutdown delay time, analyzes the display anomaly type of the marked area in combination with the light emission decay level, and outputs the corresponding detection prompt.
[0007] In a preferred embodiment, in the grayscale acquisition module, the number of horizontal and vertical pixels of the display area is obtained through the driving interface, and the display area is divided into regular grids according to the preset horizontal and vertical scales of the division area to obtain the division area. The display driver control unit loads a preset test pattern onto the PMOLED screen under test, and the optical acquisition unit set at the detection end synchronously acquires the grayscale value of the pixel in each divided area. The average grayscale value of the pixels within a defined region is calculated to obtain the region's average grayscale value. Historical defect records for each region are obtained from the historical record database, and the number of defect markers is obtained by counting the historical defect records.
[0008] In a preferred embodiment, in the attenuation recognition module, the average gray level of each divided region and the number of defect markings are standardized to obtain the gray level factor and the defect factor. The brightness attenuation characteristic value of each divided region is calculated by combining the grayscale factor and the defect factor. If the brightness attenuation characteristic value of each divided region is greater than or equal to the preset first threshold of brightness attenuation characteristic, then the brightness attenuation characteristic of the divided region is determined to be a severe attenuation characteristic. If the brightness attenuation characteristic value of each divided region is less than the preset first threshold of brightness attenuation characteristic and greater than or equal to the preset second threshold of brightness attenuation characteristic, then the brightness attenuation characteristic of the divided region is determined to be a moderate attenuation characteristic. If the brightness attenuation characteristic value of each divided region is less than the preset second threshold of brightness attenuation characteristic, then the brightness attenuation characteristic of the divided region is determined to be a mild attenuation characteristic. If the brightness attenuation characteristics of the divided region are severe or moderate, then the divided region is marked.
[0009] In a preferred embodiment, in the attenuation recognition module, the boundary pixel data of the marked division region includes the average gray value of the boundary of each marked division region and the boundary gray value change rate. Using a vertex of the marked region as the origin and the width of the pixel as the coordinate scale, construct the coordinate axis of the marked region. In the coordinate axis, the pixel with the same X-axis or Y-axis coordinate as the origin is taken as the boundary pixel of the marked region. The observation and evaluation period is preset and multiple acquisition times are divided. The gray values of each boundary pixel in each marked area are obtained through the optical acquisition unit and combined into a set of boundary pixel gray values.
[0010] In a preferred embodiment, in the attenuation recognition module, the gray values of each boundary pixel of a marked region are accumulated to obtain the total gray value of the boundary pixels of the marked region. Divide the total gray value of the boundary pixels of the marked region by the number of acquisition times to obtain the average gray value of the boundary. The gray values of the boundary pixels of the same marked area at the same acquisition time are added together to obtain the boundary gray value of the marked area at that acquisition time. The difference between the boundary gray values of adjacent acquisition times is calculated and the absolute value is divided by the acquisition time interval to obtain the boundary gray change rate of the marked area at that acquisition time. The boundary gray-scale change rate of the marked area is calculated by averaging the boundary gray-scale change rate at each acquisition time.
[0011] In a preferred embodiment, in the boundary driving module, if the average gray value of the boundary of each marked region is less than or equal to a preset average gray value threshold, and the gray value change rate is greater than or equal to a preset gray value change rate threshold, then it is determined that the marked region has a tendency to expand outward. If the average gray value of the boundary of each marked region is greater than the preset average gray value threshold, or the gray value change rate is less than the preset gray value change rate threshold, then it is determined that the marked region does not have a significant tendency to expand outward.
[0012] In a preferred embodiment, in the boundary driving module, the driving scan line current of each marked division region is obtained by a current acquisition unit disposed at the driving end; If the current of the drive scan line of each marked region is greater than or equal to the preset drive scan line current threshold, the drive response state of that marked region is determined to be a high load response state. Conversely, the driving response state of the marked region is determined to be a normal response state; For each marked region, a joint judgment is performed based on the boundary expansion trend and the driving response status. When the boundary has an expansion trend and the driving response status is a high load response status, it is judged as a severe degradation level. When there is an outward expansion trend at the boundary and the driving response is in a normal response state, it is judged as a moderate decay level; when there is no outward expansion trend at the boundary, it is judged as a mild decay level.
[0013] In a preferred embodiment, in the anomaly determination module, a pattern control command is sent to the PMOLED screen through the display driver control unit to call up a variety of test patterns in the test pattern database; The target emission off time of each marked area under the test pattern condition is obtained through the time recording unit; The grayscale values of each pixel in each marked region under different test pattern conditions are collected by an optical acquisition unit set at the detection end. Under different test pattern conditions, based on the comparison results between the gray values of pixels in each marked area and the preset gray values of pixels to be turned off, the actual light emission turn-off time of each marked area is determined, and the corresponding light emission turn-off delay time is obtained according to the absolute value of the difference between the target light emission turn-off time and the actual light emission turn-off time.
[0014] In a preferred embodiment, in the anomaly determination module, the standard deviation of the light emission shutdown delay time of the same marked division region under different test pattern conditions is calculated to obtain the temporal fluctuation index of the marked division region. The time-series fluctuation index is compared with the preset time-series fluctuation index threshold, and a graded judgment is performed in combination with the luminous decay level to distinguish between severe unstable decay anomalies, enhanced fluctuation decay anomalies, stable decay anomalies, mild stable decay anomalies, and normal display status. Based on the judgment result, the corresponding level of warning prompts or status prompts are output.
[0015] A method for detecting defects in PMOLED screens based on image processing, used to implement a PMOLED screen defect detection system based on image processing, includes the following steps: Step S1: When processing the PMOLED screen under test, the display area is first divided, the gray value of the pixels in each divided area is detected and the average gray value of the area is calculated, the historical record database is accessed to obtain the historical defect records of the corresponding divided area and the number of defect markings is counted. The average gray value of the area and the number of defect markings are used as the basis for subsequent analysis. Step S2: After obtaining the average gray level of the region and the number of defect markings, they are comprehensively processed to evaluate the brightness decay characteristics of each region. Based on the brightness decay characteristics, the regions are screened and marked. At the same time, an observation and evaluation period is set. During the observation period, the boundary pixel data of the marked regions are detected to provide data support for subsequent boundary change analysis. Step S3: After acquiring the boundary pixel data, analyze it to determine the boundary expansion trend. At the same time, read the driving scan line current of the marked area, analyze the driving response state based on the driving scan line current, and evaluate the luminous decay level of the marked area in combination with the boundary expansion trend. Step S4: After obtaining the luminescence decay level, perform test pattern switching processing on the marked area. Under different test pattern conditions, collect the luminescence shutdown delay time of the marked area, generate a timing fluctuation index based on the luminescence shutdown delay time, and analyze the display abnormality type of the marked area in combination with the luminescence decay level. Finally, output the corresponding detection prompt information.
[0016] The technical effects and advantages of this invention are as follows: This invention achieves continuous tracking and state characterization of the defect evolution process in each display area of a PMOLED screen by constructing a multi-dimensional collaborative detection mechanism that integrates the boundary change characteristics of historical defect records with grayscale information of the fusion region, driving the scanning line current and the light emission shutdown delay. It can uniformly characterize the brightness decay development path boundary expansion trend and the driving response change relationship in the same detection link, effectively improving the defect location accuracy and enhancing the ability to distinguish different anomaly types. At the same time, it improves the consistency and stability of the anomaly judgment results, thus providing a reliable basis for graded detection prompts and subsequent maintenance decisions. Attached Figure Description
[0017] Figure 1 This is a schematic diagram of a PMOLED screen defect detection system based on image processing according to the present invention.
[0018] Figure 2 This is a flowchart illustrating the implementation of a PMOLED screen defect detection method based on image processing according to the present invention. Detailed Implementation
[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0020] This invention constructs a multi-dimensional collaborative detection mechanism that integrates the boundary change characteristics of grayscale historical defect records in the fusion region to drive the response state and the emission shutdown delay, thereby continuously characterizing the defect evolution process of PMOLED screens. This improves the defect location accuracy and the consistency of anomaly classification, while enhancing the ability to distinguish different decay modes, thus improving the reliability and stability of the overall detection results.
[0021] Example 1 Please see Figure 1 A PMOLED screen defect detection system based on image processing includes a grayscale acquisition module, an attenuation recognition module, a boundary driving module, and an anomaly detection module. The functions of each module are as follows: The grayscale acquisition module is used to divide the PMOLED screen under test into regions, detect the grayscale value of the pixels in each region and calculate the average grayscale of the region, access the historical record database to obtain historical defect records of the divided regions and count the number of defect markings, and pass the average grayscale of the region and the number of defect markings to the attenuation recognition module. The attenuation recognition module is used to evaluate the brightness attenuation characteristics of the divided region by combining the average gray level of the region and the number of defect markings. Based on the brightness attenuation characteristics, the divided regions are filtered and marked. An observation and evaluation period is set. Within the observation period, the boundary pixel data of the marked divided regions are detected and transmitted to the boundary driving module. The boundary driving module uses boundary pixel data to analyze the boundary expansion trend, reads the driving scan line current of the marked area, analyzes the driving response status based on the driving scan line current, and evaluates the light decay level of the marked area in combination with the boundary expansion trend and passes it to the anomaly judgment module. The anomaly detection module performs test pattern switching processing on the marked area, collects the light emission shutdown delay time of the marked area under different test patterns, generates a timing fluctuation index based on the light emission shutdown delay time, analyzes the display anomaly type of the marked area in combination with the light emission decay level, and outputs the corresponding detection prompt.
[0022] The specific implementation is as follows: In the grayscale acquisition module, during long-term use of PMOLED screens, the degree of brightness decay varies in different display areas, and a single overall grayscale detection is difficult to locate local defect areas; during defect detection, the display area is first divided, and the average grayscale of each divided area and historical defect mark records are obtained to provide basic data for subsequent targeted analysis. When processing the PMOLED screen under test, the display area is divided. The specific division process is as follows: First, the horizontal and vertical pixel counts of the display area are obtained through the driver interface. Then, the display area is divided into a regular grid according to the preset horizontal and vertical scales of the division area, which divides the display area into multiple rectangular sub-areas of the same size. Furthermore, each partitioned region is traversed and numbered in the order of left to right and top to bottom to obtain the unique identifier ID of each partitioned region; By loading a preset test pattern onto the PMOLED screen under test through the display driver control unit, the pixels in each divided area emit light under the same driving conditions. The display area is synchronously acquired by an optical acquisition unit set at the detection end to obtain the grayscale value of the pixel in each divided area; The average grayscale value of the pixels within a defined region is calculated to obtain the region's average grayscale value. Repeat the above steps to obtain the average gray level of each divided region. Match the unique identifier ID of each region with the historical record database to obtain the historical defect records of each region. Statistical analysis of historical defect records for a defined region yields the number of defect markers for that region. Repeat the above steps to obtain the number of defect markers for each divided region.
[0023] It should be explained that the driving interface refers to the software or hardware interface that interacts with the PMOLED screen driving control unit to obtain the horizontal and vertical pixel counts of the display area; the preset horizontal and vertical scales of the division area can be set according to the display resolution of the PMOLED screen, the resolution accuracy of the optical acquisition unit, and the minimum spatial granularity of defect location; the display driving control unit refers to the hardware or logic module in the detection system responsible for sending control commands to the PMOLED screen under test, loading test patterns, and controlling its display state, and is used to load preset test patterns onto the PMOLED screen under test; the optical acquisition unit refers to the hardware device set at the detection end that performs real-time, synchronous image acquisition of the display area of the PMOLED screen under test, and is used to obtain the grayscale values of pixels in each division area; the historical record database refers to the data set used to store past defect detection records of each division area of the PMOLED screen, which includes historical defect marking information for each area, which can be accessed and matched by the detection system in subsequent detection processes.
[0024] By dividing the display area and fusing the average gray level of the area with the number of historical defect markers, potential defect areas can be accurately located, avoiding the omission of local anomalies by overall detection.
[0025] In the attenuation identification module, the average gray level of each divided region and the number of historical defect markings reflect the degree of brightness attenuation and the frequency of historical anomalies in that region. However, it is difficult to accurately judge the severity of attenuation when using either of them alone. After obtaining the above data, it is processed in a comprehensive manner to evaluate the brightness attenuation characteristics and to select the marking regions that need to be focused on. At the same time, its boundary pixel data is obtained for subsequent change analysis. The average gray level and the number of defect markers in each divided region are standardized to obtain the gray level factor and the defect factor. The brightness attenuation characteristic value of each divided region is calculated by combining the grayscale factor and the defect factor. The calculation formula is as follows: ,in, Gray factor As a defect factor, and To preset the weighting coefficients, These are the brightness attenuation characteristic values for each divided region; The brightness decay characteristic value reflects the degree of brightness decay in each segmented area under the preset test pattern conditions and its relative decay level in the overall display area. The larger the brightness decay characteristic value, the more severe the brightness drop in the segmented area, and the higher the decay level in the overall display area. The smaller the brightness decay characteristic value, the better the brightness retention ability of the segmented area, and the relatively slight decay. It should be noted that the preset weighting coefficients can be set according to the importance of the display area of the PMOLED screen, the confidence level of the number of historical defect markings, and the sensitivity requirements of brightness decay characteristics.
[0026] The brightness attenuation characteristic value of each divided region is compared with the preset first threshold and the preset second threshold for brightness attenuation characteristics to determine the result. It should be noted that the first threshold of the preset brightness attenuation feature is greater than the second threshold of the preset brightness attenuation feature. If the brightness attenuation characteristic value of each divided region is greater than or equal to the preset first threshold of brightness attenuation characteristic, then the brightness attenuation characteristic of the divided region is determined to be a severe attenuation characteristic. If the brightness attenuation characteristic value of each divided region is less than the preset first threshold of brightness attenuation characteristic and greater than or equal to the preset second threshold of brightness attenuation characteristic, then the brightness attenuation characteristic of the divided region is determined to be a moderate attenuation characteristic. If the brightness attenuation characteristic value of each divided region is less than the preset second threshold of brightness attenuation characteristic, then the brightness attenuation characteristic of the divided region is determined to be a mild attenuation characteristic. Regions are filtered and labeled based on brightness attenuation characteristics: If the brightness attenuation characteristics of the divided region are severe or moderate attenuation characteristics, then the divided region is marked. If the brightness attenuation feature of the divided region is a slight attenuation feature, then it is determined that the divided region will not be marked. The boundary pixel data of each marked region refers to the grayscale information and corresponding spatial location information of the pixels located at the boundary of the region during the detection process, including the average grayscale value and the grayscale change rate of each marked region. Using a vertex of the marked region as the origin and the width of the pixel as the coordinate scale, construct the coordinate axis of the marked region. In this coordinate axis, the pixel with the same X-axis or Y-axis coordinate as the origin is taken as the boundary pixel of the marked region. Repeat the above steps to obtain the boundary pixels of each marked region; The observation and evaluation cycle is preset and multiple acquisition times are divided. The gray values of each boundary pixel of each marked area are obtained through the optical acquisition unit set at the detection end, and then integrated into a set of gray values of each boundary pixel of each marked area according to the acquisition order. The total gray value of the boundary pixels of a marked region is obtained by summing the set of gray values of each boundary pixel of the marked region. Divide the total gray value of the boundary pixels of the marked region by the number of acquisition times to obtain the average gray value of the boundary pixels of the marked region. Repeat the above steps to obtain the average gray value of the boundary of each marked region; The gray values of the boundary pixels of the same marked area at the same acquisition time are added together to obtain the boundary gray value of the marked area at that acquisition time. Repeat the above steps to obtain the boundary grayscale values of the marked area at each acquisition time; The difference between the boundary gray values of adjacent acquisition times is calculated and the absolute value is divided by the acquisition time interval to obtain the boundary gray change rate of the marked area at that acquisition time. Repeat the above steps to obtain the boundary grayscale change rate of the marked area at each acquisition time; The boundary gray-scale change rate of the marked area is calculated by averaging the boundary gray-scale change rate at each acquisition time. Repeat the above steps to obtain the boundary grayscale change rate of each marked region.
[0027] It should be explained that the standardization processing methods include, but are not limited to, standard linear transformation based on interval scaling, Z-Score standardization based on statistics, or normalization based on nonlinear mapping functions. The application methods of standardization processing will not be elaborated here. The preset first threshold and the preset second threshold of brightness attenuation characteristics can be set according to the brightness attenuation tolerance of the display area of the PMOLED screen, the statistical distribution characteristics of historical defects, and the detection sensitivity requirements. The preset observation and evaluation cycle can be set according to the brightness attenuation rate of the PMOLED screen, the sampling frequency requirements of the boundary pixel data, and the real-time requirements of defect detection.
[0028] The regions are screened and marked based on brightness attenuation characteristics, and combined with the collection of boundary pixel data within the observation period, reliable data support is provided for subsequent boundary change analysis.
[0029] In the boundary driving module, the brightness decay of the marked division area is often accompanied by grayscale changes of boundary pixels and abnormal driving scan line current. Single-dimensional detection is difficult to distinguish different degrees of light decay. After acquiring boundary pixel data, the boundary expansion trend is analyzed, and the driving scan line current is read to evaluate the driving response state. The two are combined to determine the light decay level of the marked division area. The average gray level and the rate of change of gray level of each marked region are compared with the preset average gray level threshold and the preset rate of change of gray level threshold for judgment. If the average gray value of the boundary of each marked region is less than or equal to the preset average gray value threshold, and the gray value change rate of the boundary is greater than or equal to the preset gray value change rate threshold, then it is determined that the marked region has a tendency to expand outward. If the average gray value of the boundary of each marked region is greater than the preset average gray value threshold, or the gray value change rate is less than the preset gray value change rate threshold, then it is determined that the marked region does not have an obvious tendency to expand outward. The current of the drive scan line of each marked area is obtained by the current acquisition unit set at the drive end; The driving scan line current of each marked region is compared with the preset driving scan line current threshold for determination: If the current of the drive scan line of each marked region is greater than or equal to the preset drive scan line current threshold, the drive response state of that marked region is determined to be a high load response state. If the driving scan line current of each marked region is less than the preset driving scan line current threshold, then the driving response state of that marked region is determined to be a normal response state. The judgment is made by combining the boundary expansion trend of each marked region with the driving response status: If the boundary expansion trend of each marked area is present and the driving response state of the marked area is a high load response state, then the luminous decay level of the marked area is determined to be a severe decay level. If the boundary expansion trend of each marked area is present and the driving response state of the marked area is normal, then the luminous decay level of the marked area is determined to be moderate decay level. If the boundary expansion trend of each marked area is not present, then the luminous decay level of the marked area is determined to be mild decay.
[0030] It should be explained that the preset boundary grayscale average threshold can be set based on the grayscale statistics of the normal display area boundary of the PMOLED screen, the resolution accuracy of the optical acquisition unit, and the sensitivity requirements for boundary expansion detection; the preset boundary grayscale change rate threshold can be set based on the statistical values of the boundary grayscale change rate during the normal aging process of the PMOLED screen, the sampling time interval within the observation and evaluation period, and the sensitivity requirements for boundary expansion trend detection; the current acquisition unit refers to the hardware detection unit set at the driver end that reads the driving scan line current corresponding to each marked area in real time, and is used to obtain the driving scan line current of each marked area; the preset driving scan line current threshold can be set based on the statistical reference value of the scan line current under normal display conditions of the PMOLED screen, the rated current operating range of the driver chip, and the sensitivity requirements for load anomaly detection.
[0031] By combining the boundary expansion trend with the driving scan line current to analyze the driving response state, the luminous decay level of the marked and divided regions is quantitatively evaluated, thereby improving the accuracy of the decay degree judgment.
[0032] In the anomaly detection module, the marked areas of different light decay levels may exhibit different light-off delay characteristics under test pattern switching conditions. The decay level alone cannot further distinguish the anomaly type. After obtaining the light decay level, the test pattern switching process is performed to collect the light-off delay time and generate the timing fluctuation index. Combined with the decay level analysis, the anomaly type is displayed, and finally the corresponding detection prompt information is output. The display driver control unit sends pattern control commands to the PMOLED screen, calls up various test patterns in the test pattern database, and loads each marked area according to the preset switching order; The time recording unit is used to obtain the target light emission off time of each marked area under different test pattern conditions; The grayscale values of each pixel in each marked region under different test pattern conditions are collected by an optical acquisition unit set at the detection end. If, under different test pattern conditions, one or more pixels in each marked area have a gray value greater than or equal to the preset pixel turn-off gray value, it is determined that the marked area has not yet completed the light emission shutdown under the current test pattern condition, and gray value acquisition continues. If the grayscale value of all pixels in each marked area is less than the preset grayscale value for turning off pixels under different test pattern conditions, it is determined that the marked area has completed the light emission shutdown under the current test pattern condition, and the corresponding time is taken as the actual light emission shutdown time. The target light emission shutdown time of each marked area under the same test pattern is subtracted from the corresponding actual light emission shutdown time, and the absolute value is taken to obtain the light emission shutdown delay time of each marked area under the same test pattern. Repeat the above steps to obtain the light emission shutdown delay time of each marked region under different test pattern conditions; The standard deviation of the light emission shutdown delay time of the same marked region under different test pattern conditions is calculated to obtain the temporal fluctuation index of the marked region. Repeat the above steps to obtain the temporal fluctuation index of each marked region; It should be noted that the test pattern database refers to a collection of various standard test patterns pre-stored in the testing system. These patterns are used to load and switch the marked areas of the PMOLED screen at different testing stages to evaluate abnormal performance of the screen under different display conditions. The preset switching order can be set according to the grayscale progression of the test patterns, the comparative analysis requirements of the light emission shutdown delay time under different pattern conditions, and the timing logic requirements of the testing process. The time recording unit is a timing unit used to record the target light emission shutdown time and the actual light emission shutdown time of each marked area under different test pattern conditions. The preset pixel shutdown grayscale value can be set according to the background noise grayscale statistics of the PMOLED screen in the non-light emission state, the signal-to-noise ratio characteristics of the optical acquisition unit, and the sensitivity requirements of light emission shutdown state detection.
[0033] The temporal fluctuation index of each marked region is compared with the preset temporal fluctuation index threshold, and a judgment is made in conjunction with the luminous decay level: If the temporal fluctuation index of each marked area is greater than or equal to the preset temporal fluctuation index threshold, and the light decay level is severe decay level, then the display anomaly type of the marked area is determined to be a severe unstable decay anomaly, and a first-level warning message is output. If the temporal fluctuation index of each marked area is greater than or equal to the preset temporal fluctuation index threshold, and the light decay level is moderate decay level, then the display anomaly type of the marked area is determined to be a fluctuation-enhanced decay anomaly and a level 2 warning message is output. If the temporal fluctuation index of each marked area is less than the preset temporal fluctuation index threshold, and the light decay level is severe decay level, then the display anomaly type of the marked area is determined to be a stable decay anomaly, and a level three warning message is output. If the temporal fluctuation index of each marked area is less than the preset temporal fluctuation index threshold, and the light decay level is moderate decay level, then the display abnormality type of the marked area is determined to be mild stable decay abnormality, and a prompt monitoring information is output. If the light decay level of each marked area is mild, the display abnormality type of that marked area is determined to be normal display state, and a normal state prompt message is output.
[0034] It should be explained that the preset timing fluctuation index threshold can be set based on the statistical benchmark value of timing fluctuation during the switching process of different test patterns in the normal display state of the PMOLED screen, the allowable fluctuation range of the light emission shutdown delay time, and the sensitivity requirements of anomaly detection; the first-level warning message refers to the highest level alarm message output by the detection system when it determines that the display anomaly type is a severe unstable degradation anomaly, used to indicate that there is a serious display quality problem in this area, which requires immediate attention or handling; the second-level warning message refers to the medium-level alarm message output by the detection system when it determines that the display anomaly type is a fluctuation enhancement degradation anomaly, used to indicate that there is a downward trend in display quality in this area, which requires further attention or handling. Intensive monitoring or maintenance arrangements are required. Level 3 early warning information refers to a lower-level warning message output by the detection system when it determines the display anomaly type is stable attenuation, indicating a continuous but relatively stable brightness attenuation in the area and suggesting inclusion in the observation plan. Monitoring warning information refers to a low-level warning message output by the detection system when it determines the display anomaly type is mild stable decay, informing the user that there are slight signs of attenuation in the area and suggesting continuous monitoring without immediate intervention. Normal status warning information refers to a confirmatory warning message output by the detection system when it determines the display anomaly type is normal display status, informing the user that all detection indicators in the area are within the normal range and no action is required.
[0035] The temporal fluctuation index is obtained by testing pattern switching processing, and the abnormality type is displayed by combining the luminescence decay level analysis. Different types of decay anomalies are distinguished, and targeted detection prompts are output.
[0036] Example 2, as Figure 2 As shown, an image processing-based PMOLED screen defect detection method is used to implement an image processing-based PMOLED screen defect detection system, including the following steps: Step S1: When processing the PMOLED screen under test, the display area is first divided, the gray value of the pixels in each divided area is detected and the average gray value of the area is calculated, the historical record database is accessed to obtain the historical defect records of the corresponding divided area and the number of defect markings is counted. The average gray value of the area and the number of defect markings are used as the basis for subsequent analysis. Step S2: After obtaining the average gray level of the region and the number of defect markings, they are comprehensively processed to evaluate the brightness decay characteristics of each region. Based on the brightness decay characteristics, the regions are screened and marked. At the same time, an observation and evaluation period is set. During the observation period, the boundary pixel data of the marked regions are detected to provide data support for subsequent boundary change analysis. Step S3: After acquiring the boundary pixel data, analyze it to determine the boundary expansion trend. At the same time, read the driving scan line current of the marked area, analyze the driving response state based on the driving scan line current, and evaluate the luminous decay level of the marked area in combination with the boundary expansion trend. Step S4: After obtaining the luminescence decay level, perform test pattern switching processing on the marked area. Under different test pattern conditions, collect the luminescence shutdown delay time of the marked area, generate a timing fluctuation index based on the luminescence shutdown delay time, and analyze the display abnormality type of the marked area in combination with the luminescence decay level. Finally, output the corresponding detection prompt information.
[0037] Finally, it should be noted that in this paper, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.
[0038] Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0039] In this document, the singular forms “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that terms such as “comprising / including” or “having” specify the presence of the stated features, integrals, steps, operations, components, parts, or combinations thereof, but do not preclude the possibility of the presence or addition of one or more other features, integrals, steps, operations, components, parts, or combinations thereof. Meanwhile, the term “and / or” as used in this specification includes any and all combinations of the associated listed items.
[0040] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.
[0041] The above description of the disclosed embodiments will enable those skilled in the art to make or use various modifications to these embodiments. It will be readily apparent to those skilled in the art that the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A PMOLED screen defect detection system based on image processing, characterized in that: It includes a grayscale acquisition module, an attenuation recognition module, a boundary driving module, and an anomaly detection module. The functions of each module are as follows: It includes a grayscale acquisition module, an attenuation recognition module, a boundary driving module, and an anomaly detection module. The functions of each module are as follows: The grayscale acquisition module is used to divide the PMOLED screen under test into regions, detect the grayscale value of the pixels in each region and calculate the average grayscale of the region, access the historical record database to obtain historical defect records of the divided regions and count the number of defect markings, and then pass the average grayscale of the region and the number of defect markings to the attenuation recognition module. The attenuation recognition module is used to evaluate the brightness attenuation characteristics of the divided region by combining the average gray level of the region and the number of defect markings. Based on the brightness attenuation characteristics, the divided regions are filtered and marked. An observation and evaluation period is set. Within the observation period, the boundary pixel data of the marked divided regions are detected and transmitted to the boundary driving module. The boundary driving module uses boundary pixel data to analyze the boundary expansion trend, reads the driving scan line current of the marked area, analyzes the driving response status based on the driving scan line current, and evaluates the light decay level of the marked area in combination with the boundary expansion trend and passes it to the anomaly judgment module. The anomaly detection module performs test pattern switching processing on the marked area, collects the light emission shutdown delay time of the marked area under different test patterns, generates a timing fluctuation index based on the light emission shutdown delay time, analyzes the display anomaly type of the marked area in combination with the light emission decay level, and outputs the corresponding detection prompt.
2. The PMOLED screen defect detection system based on image processing according to claim 1, characterized in that: In the grayscale acquisition module, the number of horizontal and vertical pixels of the display area is obtained through the driver interface, and the display area is divided into regular grids according to the preset horizontal and vertical scales of the division area to obtain the division area; The display driver control unit loads a preset test pattern onto the PMOLED screen under test, and the optical acquisition unit set at the detection end synchronously acquires the grayscale value of the pixel in each divided area. The average grayscale value of the pixels within a defined region is calculated to obtain the region's average grayscale value. Historical defect records for each region are obtained from the historical record database, and the number of defect markers is obtained by counting the historical defect records.
3. The PMOLED screen defect detection system based on image processing according to claim 1, characterized in that: In the attenuation recognition module, the average gray level of each divided region and the number of defect markings are standardized to obtain the gray level factor and the defect factor. The brightness attenuation characteristic value of each divided region is calculated by combining the grayscale factor and the defect factor. If the brightness attenuation characteristic value of each divided region is greater than or equal to the preset first threshold of brightness attenuation characteristic, then the brightness attenuation characteristic of the divided region is determined to be a severe attenuation characteristic. If the brightness attenuation characteristic value of each divided region is less than the preset first threshold of brightness attenuation characteristic and greater than or equal to the preset second threshold of brightness attenuation characteristic, then the brightness attenuation characteristic of the divided region is determined to be a moderate attenuation characteristic. If the brightness attenuation characteristic value of each divided region is less than the preset second threshold of brightness attenuation characteristic, then the brightness attenuation characteristic of the divided region is determined to be a mild attenuation characteristic. If the brightness attenuation characteristics of the divided region are severe or moderate, then the divided region is marked.
4. The PMOLED screen defect detection system based on image processing according to claim 1, characterized in that: In the attenuation recognition module, the boundary pixel data of the marked division region includes the average gray value of the boundary of each marked division region and the boundary gray value change rate; Using a vertex of the marked region as the origin and the width of the pixel as the coordinate scale, construct the coordinate axis of the marked region. In the coordinate axis, the pixel with the same X-axis or Y-axis coordinate as the origin is taken as the boundary pixel of the marked region. The observation and evaluation period is preset and multiple acquisition times are divided. The gray values of each boundary pixel in each marked area are obtained through the optical acquisition unit and combined into a set of boundary pixel gray values.
5. The PMOLED screen defect detection system based on image processing according to claim 4, characterized in that: In the attenuation recognition module, the gray values of each boundary pixel of a marked region are accumulated to obtain the total gray value of the boundary pixels of the marked region. Divide the total gray value of the boundary pixels of the marked region by the number of acquisition times to obtain the average gray value of the boundary. The gray values of the boundary pixels of the same marked area at the same acquisition time are added together to obtain the boundary gray value of the marked area at that acquisition time. The difference between the boundary gray values of adjacent acquisition times is calculated and the absolute value is divided by the acquisition time interval to obtain the boundary gray change rate of the marked area at that acquisition time. The boundary gray-scale change rate of the marked area is calculated by averaging the boundary gray-scale change rate at each acquisition time.
6. The PMOLED screen defect detection system based on image processing according to claim 5, characterized in that: In the boundary driving module, if the average gray value of the boundary of each marked region is less than or equal to the preset average gray value threshold, and the gray value change rate of the boundary is greater than or equal to the preset gray value change rate threshold, then it is determined that the marked region has a tendency to expand outward. If the average gray value of the boundary of each marked region is greater than the preset average gray value threshold, or the gray value change rate is less than the preset gray value change rate threshold, then it is determined that the marked region does not have a significant tendency to expand outward.
7. The PMOLED screen defect detection system based on image processing according to claim 6, characterized in that: In the boundary drive module, the drive scan line current of each marked division area is obtained by a current acquisition unit set at the drive end; If the current of the drive scan line of each marked region is greater than or equal to the preset drive scan line current threshold, the drive response state of that marked region is determined to be a high load response state. Conversely, the driving response state of the marked region is determined to be a normal response state; For each marked region, a joint judgment is performed based on the boundary expansion trend and the driving response status. When the boundary has an expansion trend and the driving response status is a high load response status, it is judged as a severe degradation level. When there is an outward expansion trend at the boundary and the driving response is in a normal response state, it is judged as a moderate decay level; when there is no outward expansion trend at the boundary, it is judged as a mild decay level.
8. The PMOLED screen defect detection system based on image processing according to claim 7, characterized in that: In the anomaly detection module, a pattern control command is sent to the PMOLED screen through the display driver control unit to call up a variety of test patterns in the test pattern database. The target emission off time of each marked area under the test pattern condition is obtained through the time recording unit; The grayscale values of each pixel in each marked region under different test pattern conditions are collected by an optical acquisition unit set at the detection end. Under different test pattern conditions, based on the comparison results between the gray values of pixels in each marked area and the preset gray values of pixels to be turned off, the actual light emission turn-off time of each marked area is determined, and the corresponding light emission turn-off delay time is obtained according to the absolute value of the difference between the target light emission turn-off time and the actual light emission turn-off time.
9. The PMOLED screen defect detection system based on image processing according to claim 8, characterized in that: In the anomaly detection module, the standard deviation of the light emission shutdown delay time of the same marked division area under different test pattern conditions is calculated to obtain the timing fluctuation index of the marked division area. The time-series fluctuation index is compared with the preset time-series fluctuation index threshold, and a graded judgment is performed in combination with the luminous decay level to distinguish between severe unstable decay anomalies, enhanced fluctuation decay anomalies, stable decay anomalies, mild stable decay anomalies, and normal display status. Based on the judgment result, the corresponding level of warning prompts or status prompts are output.
10. A PMOLED screen defect detection method based on image processing, based on the PMOLED screen defect detection system based on image processing according to any one of claims 1-9, characterized in that, Includes the following steps: Step S1: When processing the PMOLED screen under test, the display area is first divided, the gray value of the pixels in each divided area is detected and the average gray value of the area is calculated, the historical record database is accessed to obtain the historical defect records of the corresponding divided area and the number of defect markings is counted. The average gray value of the area and the number of defect markings are used as the basis for subsequent analysis. Step S2: After obtaining the average gray level of the region and the number of defect markings, they are comprehensively processed to evaluate the brightness decay characteristics of each region. Based on the brightness decay characteristics, the regions are screened and marked. At the same time, an observation and evaluation period is set. During the observation period, the boundary pixel data of the marked regions are detected to provide data support for subsequent boundary change analysis. Step S3: After acquiring the boundary pixel data, analyze it to determine the boundary expansion trend. At the same time, read the driving scan line current of the marked area, analyze the driving response state based on the driving scan line current, and evaluate the luminous decay level of the marked area in combination with the boundary expansion trend. Step S4: After obtaining the luminescence decay level, perform test pattern switching processing on the marked area. Under different test pattern conditions, collect the luminescence shutdown delay time of the marked area, generate a timing fluctuation index based on the luminescence shutdown delay time, and analyze the display abnormality type of the marked area in combination with the luminescence decay level. Finally, output the corresponding detection prompt information.