A method and system for pixel positioning of OLED mobile phone screen based on region growing
Through the method based on region growth, texture and grayscale features are calculated, the first-place area seeds are selected and the positioning network is built, which solves the problem of low pixel positioning efficiency of existing OLED mobile phone screens, and achieves fast and accurate pixel-level fault positioning and efficient Quality control.
Patent Information
- Application Number
- CN202411073892.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-08-07
AI Technical Summary
The existing OLED mobile phone screen pixel positioning methods are inefficient, especially in complex backgrounds or high-resolution images. The matching process takes a long time and makes it difficult to quickly and accurately locate pixel-level faults.
Using a region-based growth method, by obtaining the standard features of screen pixel points, segmenting the screen into multiple regions, calculating texture feature coefficients and grayscale feature coefficients, filtering out the first-order area seeds of the starting growth area, and performing the area based on the comparison model Positioning, quickly identify other regions that are consistent with the seed characteristics of the first-order region, and build a positioning network.
It improves the efficiency of pixel positioning of OLED mobile phone screens, can quickly and accurately locate pixel-level faults under different background conditions, reduces false alarm rates, and ensures the accuracy of screen quality control.
Smart Images

Figure CN118587291B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of mobile phone screen technology, and in particular to an OLED mobile phone screen pixel positioning method and system based on regional growth. Background Art
[0002] OLED (Organic Light Emitting Diode) screens are widely used in high-end smartphones and tablets due to their self-luminous properties, high contrast, thin design and bendable potential. Pixel positioning of OLED screens is an important task in the production, quality control, calibration and repair processes.
[0003] When a pixel-level fault occurs on the screen, such as a "dead pixel" or a "bright spot", pixel positioning technology can help accurately locate the fault location. However, the existing OLED mobile phone screen pixel positioning usually compares a known small image with a larger target image to obtain the pixel positioning of the mobile phone screen. This comparison method is relatively inefficient, and the matching process may become very time-consuming in complex backgrounds or high-resolution images. Therefore, a method and system for OLED mobile phone screen pixel positioning based on region growing is needed to solve the above problems. Summary of the invention
[0004] The purpose of the present invention is to provide an OLED mobile phone screen pixel positioning system based on region growing to solve the technical problems raised in the above background technology.
[0005] To achieve the above object, the present invention provides the following technical solutions:
[0006] A pixel positioning method for an OLED mobile phone screen based on region growing, comprising:
[0007] Obtaining the screen pixels of the entire OLED mobile phone screen and obtaining standard features of the screen pixels, wherein the standard features include multiple pixel brightness and multiple tone contrasts within a preset time;
[0008] The screen pixels of the entire OLED mobile phone screen are divided according to the preset area to obtain a plurality of regional pixel areas, and any one of the regional pixel areas is selected as the starting growth area;
[0009] Calculating a texture feature coefficient according to the plurality of pixel brightnesses, calculating a grayscale feature coefficient according to the plurality of hue contrasts, and calculating an RGB standard feature value according to the texture feature coefficient and the grayscale feature coefficient, and defining the RGB standard feature value as a first preset condition;
[0010] Acquire a plurality of first screen pixel points in the starting growth area, acquire a plurality of corresponding RGB feature values according to the plurality of first screen pixel points, and determine in turn whether the plurality of RGB feature values are equal to a first preset condition; if they are equal, use the screen pixel points corresponding to the plurality of RGB feature values equal to the first preset condition as standard pixel seeds;
[0011] Obtain the center coordinates of the starting growth area, and use the one of the multiple standard pixel seeds closest to the center coordinates as the first area seed;
[0012] The first regional seed is used as a reference object to obtain multiple second regional seeds corresponding to the remaining multiple regional pixel areas, and the screen pixel points within the multiple regional pixel areas are regionally positioned according to the first regional seed and the multiple second regional seeds.
[0013] Preferably, the step of using the first regional seed as a reference object to obtain a plurality of second regional seeds corresponding to the remaining plurality of regional pixel areas, and performing regional positioning of screen pixel points within the plurality of regional pixel areas according to the first regional seed and the plurality of second regional seeds comprises:
[0014] Obtain multiple second screen pixel points corresponding to the remaining multiple regional pixel areas, obtain multiple corresponding first RGB feature values according to the multiple second screen pixel points, obtain the first standard RGB feature value corresponding to the first regional seed, input the multiple first RGB feature values and the first standard RGB feature value into the comparison model in sequence for training, and output multiple comparison values;
[0015] sequentially determining whether the plurality of comparison values are equal to a preset comparison value;
[0016] If they are equal, then the multiple second screen pixel points corresponding to the regional pixel area corresponding to the first RGB feature value equal to the preset contrast value are used as second regional seeds, the first regional seed is used as the origin, and the multiple second regional seeds are used as base points of the corresponding region, and the screen pixel points within the multiple regional pixel areas are regionally positioned based on the origin of the corresponding region and the multiple base points.
[0017] Preferably, the step of sequentially inputting the plurality of first RGB feature values and the first standard RGB feature value into a comparison model for training and outputting a plurality of comparison values comprises:
[0018] The plurality of the first RGB feature values and the first standard RGB feature values are sequentially input into a comparison model for training, and a plurality of comparison values are output, wherein the function formula of the comparison model is:
[0019] ;
[0020] in, represents the comparison value from the fth to the tth, represents the fth first standard RGB eigenvalue, represents the fth first RGB eigenvalue, represents the tth first standard RGB eigenvalue, Represents the tth first RGB eigenvalue.
[0021] Preferably, the step of performing regional positioning of screen pixel points within a plurality of pixel areas of the region based on the origin of the corresponding region and the plurality of base points comprises:
[0022] Obtaining the origin coordinates of the origin, and establishing a two-dimensional coordinate system of screen pixel points according to the origin coordinates;
[0023] Acquire multiple distances from the origin coordinates to the multiple base points based on the two-dimensional coordinate system;
[0024] Based on the two-dimensional coordinate system, multiple direction angles corresponding to the multiple base points in the two-dimensional coordinate system are obtained, and multiple base point coordinates are calculated in sequence according to the multiple distances, the origin coordinates and the multiple direction angles, wherein the calculation formula is:
[0025] ;
[0026] in, represents the coordinates of the oth to kth base points, Represents the coordinate value of the origin at the X-axis. Represents the coordinate value of the origin on the y-axis. represents the oth distance, represents the kth distance, Indicates the direction angle corresponding to the oth base point in the two-dimensional coordinate system, Indicates the direction angle corresponding to the kth base point in the two-dimensional coordinate system;
[0027] Corresponding pixel coordinates are assigned to the region pixels of the corresponding region according to the origin coordinates and the plurality of base point coordinates, until the plurality of region pixels correspond to one pixel coordinate.
[0028] Preferably, the step of calculating the texture feature coefficient according to the brightness of the plurality of pixels comprises:
[0029] The average pixel brightness is obtained according to the plurality of pixel brightnesses, and the standard pixel brightness difference is calculated according to the plurality of pixel brightnesses and the average pixel brightness, wherein the calculation formula is:
[0030] ;
[0031] in, Represents the standard pixel brightness difference, represents the brightness of the first pixel, N represents the number of pixel brightness, The serial number representing the brightness of the pixel, represents the average pixel brightness;
[0032] The texture feature coefficient is calculated according to the standard pixel brightness difference and the average pixel brightness, wherein the calculation formula is:
[0033] ;
[0034] in, represents the texture feature coefficient, represents the average pixel brightness, Indicates the standard pixel brightness difference.
[0035] Preferably, the step of calculating the grayscale characteristic coefficient according to the plurality of hue contrasts comprises:
[0036] An average hue contrast is obtained according to the multiple hue contrasts, and a standard hue contrast difference is calculated according to the multiple hue contrasts and the average hue contrast, wherein the calculation formula is:
[0037] ;
[0038] in, Indicates the standard hue contrast difference, represents the i-th hue contrast, N represents the number of hue contrasts, i represents the sequence number of hue contrasts, represents the average tonal contrast;
[0039] The grayscale characteristic coefficient is calculated according to the standard hue contrast difference and the average hue contrast, wherein the calculation formula is:
[0040] ;
[0041] in, represents the grayscale characteristic coefficient, represents the average hue contrast, Indicates the standard tonal contrast difference.
[0042] Preferably, the step of calculating the RGB standard feature value according to the texture feature coefficient and the grayscale feature coefficient comprises:
[0043] Obtaining weight factors of texture feature coefficients;
[0044] The RGB standard feature value is calculated according to the texture feature coefficient, the weight factor of the texture feature coefficient and the grayscale feature coefficient, wherein the calculation formula is:
[0045] ;
[0046] in, Represents the RGB standard feature value, represents the texture feature coefficient, a represents the weight factor of the texture feature coefficient, Represents the grayscale characteristic coefficient.
[0047] The present application also provides an OLED mobile phone screen pixel positioning system based on regional growth, comprising:
[0048] The first acquisition module is used to acquire screen pixels of the entire OLED mobile phone screen and acquire standard features of the screen pixels, wherein the standard features include a plurality of pixel brightnesses and a plurality of hue contrasts within a preset time;
[0049] A first segmentation module is used to segment the screen pixels of the entire OLED mobile phone screen according to a preset area to obtain a plurality of regional pixel areas, and select any one of the regional pixel areas as a starting growth area;
[0050] A first calculation module, used for calculating a texture feature coefficient according to the plurality of pixel brightnesses, calculating a grayscale feature coefficient according to the plurality of hue contrasts, and calculating an RGB standard feature value according to the texture feature coefficient and the grayscale feature coefficient, and defining the RGB standard feature value as a first preset condition;
[0051] a second acquisition module, used to acquire a plurality of first screen pixel points in the starting growth area, acquire a plurality of corresponding RGB feature values according to the plurality of first screen pixel points, and sequentially determine whether the plurality of RGB feature values are equal to a first preset condition; if they are equal, the screen pixel points corresponding to the plurality of RGB feature values equal to the first preset condition are used as standard pixel seeds;
[0052] The third acquisition module is used to obtain the center coordinates of the starting growth area and use the one of the multiple standard pixel seeds closest to the center coordinates as the first area seed;
[0053] a fourth acquisition module, used to acquire a plurality of second screen pixel points corresponding to the remaining plurality of regional pixel areas, acquire a plurality of corresponding first RGB feature values according to the plurality of second screen pixel points, acquire a first standard RGB feature value corresponding to a first regional seed, input the plurality of first RGB feature values and the first standard RGB feature value into a comparison model in sequence for training, and output a plurality of comparison values;
[0054] A first judging module, used for judging in sequence whether the plurality of comparison values are equal to a preset comparison value;
[0055] If they are equal, then the multiple second screen pixel points corresponding to the regional pixel area corresponding to the first RGB feature value equal to the preset contrast value are used as second regional seeds, the first regional seed is used as the origin, and the multiple second regional seeds are used as base points of the corresponding region, and the screen pixel points within the multiple regional pixel areas are regionally positioned based on the origin of the corresponding region and the multiple base points.
[0056] The present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.
[0057] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.
[0058] The beneficial effects of the present application are as follows: the present invention first obtains the screen pixel points of the entire OLED mobile phone screen, and obtains the standard features of the screen pixel points, wherein the standard features include multiple pixel brightnesses and multiple hue contrasts within a preset time, and then divides the screen pixel points of the entire OLED mobile phone screen according to the preset regional area to obtain multiple regional pixel areas, and selects any one of the regional pixel areas as the starting growth area, and screens out the first regional seed of the starting growth area through the standard features, and then inputs the first standard RGB feature value corresponding to the first regional seed and the multiple first RGB feature values into the comparison model for training, outputs multiple comparison values, and judges in turn whether the multiple comparison values are equal to the preset comparison value, if they are equal, then the multiple second screen pixel points corresponding to the regional pixel area corresponding to the first RGB feature value equal to the preset comparison value are used as the second regional seeds, and the first regional seed is used as the origin, and the multiple second regional seeds are used as the base points of the corresponding area, and the screen pixel points within the multiple regional pixel areas are regionally positioned based on the origin and the multiple base points of the corresponding area, so that it can not only meet the needs of quickly positioning pixels under different background conditions, but also make the positioning efficiency of the screen pixel points of the entire OLED mobile phone screen higher on the basis of simultaneous positioning. BRIEF DESCRIPTION OF THE DRAWINGS
[0059] Figure 1 A schematic diagram of a method flow chart of an embodiment of the present application.
[0060] Figure 2 A schematic diagram of the system structure of an embodiment of the present application.
[0061] Figure 3A schematic diagram of the internal structure of a computer device according to an embodiment of the present application.
[0062] Figure 4 It is a schematic diagram of the structure between coordinates and pixels according to an embodiment of the present application.
[0063] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0064] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0065] like Figure 1-4 As shown, the present application provides an OLED mobile phone screen pixel positioning method based on region growing, comprising:
[0066] S1. Obtaining screen pixels of the entire OLED mobile phone screen and obtaining standard features of the screen pixels, wherein the standard features include a plurality of pixel brightnesses and a plurality of hue contrasts within a preset time;
[0067] S2, dividing the screen pixels of the entire OLED mobile phone screen according to the preset area to obtain a plurality of regional pixel areas, and selecting any one of the regional pixel areas as the starting growth area;
[0068] S3, calculating a texture feature coefficient according to the plurality of pixel brightnesses, calculating a grayscale feature coefficient according to the plurality of hue contrasts, and calculating an RGB standard feature value according to the texture feature coefficient and the grayscale feature coefficient, and defining the RGB standard feature value as a first preset condition;
[0069] S4, obtaining a plurality of first screen pixel points in the starting growth area, obtaining a plurality of corresponding RGB feature values according to the plurality of first screen pixel points, and determining in turn whether the plurality of RGB feature values are equal to a first preset condition, and if they are equal, taking the screen pixel points corresponding to the plurality of RGB feature values equal to the first preset condition as standard pixel seeds;
[0070] S5, obtaining the center coordinates of the starting growth area, and taking the one of the multiple standard pixel seeds closest to the center coordinates as the first area seed;
[0071] S6. Using the first region seed as a reference object, obtain a plurality of second region seeds corresponding to the remaining plurality of region pixel areas, and perform region positioning on screen pixel points within the plurality of region pixel areas according to the first region seed and the plurality of second region seeds.
[0072] As described in the above steps S1-S6, when a pixel-level fault occurs on the screen, such as a "dead pixel" or a "bright spot", the pixel positioning technology can help accurately locate the fault location, while the existing OLED mobile phone screen pixel positioning usually compares a known small image with a larger target image to obtain the pixel positioning of the mobile phone screen, and this comparison method to find the positioning is relatively inefficient, and in complex backgrounds or high-resolution images, the matching process may become very time-consuming. Among them, the formation of OLED pixels is based on the organic light-emitting diodes emitting light of different colors (RGB three colors), and the RGB three colors are called a light-emitting unit, and then RGB is combined into the color displayed on the screen. In the present invention, the pixels generated by the light-emitting unit are positioned. When it is necessary to position the screen pixel points, this solution selects the corresponding features as the benchmark according to the characteristics of the OLED mobile phone screen. Among them, since each OLED pixel point They are all independent light-emitting units and do not require an additional backlight source. In this way, when the light-emitting units produce a brightness difference, a specific light spot will be formed, and the light spot will produce a texture. Therefore, the texture feature can be used as a standard feature when the screen is bright. At the same time, due to the characteristics of OLED display: when the pixel is not emitting light, the light-emitting unit is actually turned off and does not emit any light. This means that the OLED screen can provide a very deep tone contrast when displaying dark tones. Because the grayscale value refers to the pixel intensity in the grayscale image, the higher the grayscale value, the brighter the pixel in the image looks. Therefore, the difference between the tone contrast of the light-emitting unit at the brightest and the tone contrast at the darkest can be reflected by the grayscale value. On this basis, the screen pixel points of the entire OLED mobile phone screen are first divided according to the preset area to obtain multiple regional pixel areas, and any one of the regional pixel areas is selected as the starting growth area (regional pixel, such as Figure 4As shown), by dividing the screen pixel points of the entire OLED mobile phone screen, the pixel areas of multiple regions can be located at the same time, so that the efficiency of mobile phone screen pixel positioning is higher, and then the texture feature coefficient is calculated according to the brightness of the multiple pixels, the grayscale feature coefficient is calculated according to the multiple hue contrasts, and the RGB standard feature value is calculated according to the texture feature coefficient and the grayscale feature coefficient, and the RGB standard feature value is defined as the first preset condition, so that the RGB standard feature value calculated can simultaneously meet the OLED screen in the light and dark modes to screen seeds at the same time, on this basis, a plurality of first screen pixel points in the starting growth area are obtained, and then the corresponding plurality of RGB feature values are obtained according to the plurality of first screen pixel points, and it is judged in turn whether the plurality of RGB feature values are equal to the first preset condition, if they are equal, the screen pixel points corresponding to the plurality of RGB feature values equal to the first preset condition are used as standard pixel seeds, and the center coordinates of the starting growth area are obtained at the same time, and The pixel seed closest to the center coordinate among multiple standard pixel seeds is used as the first regional seed. The first regional seed selected in this way can provide a base point for the positioning of the screen pixel points of the entire OLED mobile phone screen. Then, the first regional seed is used as a reference object to obtain multiple second regional seeds corresponding to the remaining multiple regional pixel areas. The screen pixel points within the multiple regional pixel areas are regionally positioned according to the first regional seed and the multiple second regional seeds. This can not only meet the needs of quickly positioning pixels under different background conditions, but also make the positioning efficiency of the screen pixel points of the entire OLED mobile phone screen higher on the basis of simultaneous positioning. A practical application example: During pixel-level fault detection on an OLED screen production line, the OLED screen to be detected is divided into multiple small areas (for example, an area of 16x16 pixels), each area is used as an independent detection unit, and the area in the upper left corner of the screen is selected as the starting growth area, and then feature extraction and seed selection are started in the area in the upper left corner. By comparing the models, the system can quickly identify other areas that are consistent with the characteristics of the first area seed, mark the center points of these areas as the second area seeds, and thus build a positioning network covering the entire screen. Using this network, the system can quickly and accurately detect any pixel-level faults on the screen, such as "dead pixels" or "bright spots", and record their specific locations. This method not only improves detection efficiency, but also reduces the false alarm rate, ensuring the quality control of OLED screens before leaving the factory. The above examples are only for understanding and are not the only limitation.
[0073] In one embodiment, the step S6 of using the first region seed as a reference object to obtain a plurality of second region seeds corresponding to the remaining plurality of region pixel areas, and performing region positioning on screen pixel points within the plurality of region pixel areas according to the first region seed and the plurality of second region seeds comprises:
[0074] S601, obtaining a plurality of second screen pixel points corresponding to the remaining plurality of regional pixel areas, obtaining a plurality of corresponding first RGB feature values according to the plurality of second screen pixel points, obtaining a first standard RGB feature value corresponding to a first regional seed, inputting the plurality of first RGB feature values and the first standard RGB feature value into a comparison model in sequence for training, and outputting a plurality of comparison values;
[0075] S602, determining in sequence whether a plurality of the comparison values are equal to a preset comparison value;
[0076] If they are equal, then the multiple second screen pixel points corresponding to the regional pixel area corresponding to the first RGB feature value equal to the preset contrast value are used as second regional seeds, the first regional seed is used as the origin, and the multiple second regional seeds are used as base points of the corresponding region, and the screen pixel points within the multiple regional pixel areas are regionally positioned based on the origin of the corresponding region and the multiple base points.
[0077] As described in the above steps S601-S602, the present application obtains multiple second screen pixel points corresponding to the remaining multiple regional pixel areas, obtains multiple corresponding first RGB feature values according to the multiple second screen pixel points, obtains the first standard RGB feature value corresponding to the first regional seed, and sequentially inputs the multiple first RGB feature values and the first standard RGB feature value into the comparison model for training, outputs multiple comparison values, and sequentially determines whether the multiple comparison values are equal to 1. If they are equal to 1, the multiple second screen pixel points corresponding to the regional pixel area corresponding to the first RGB feature value equal to the preset comparison value are used as the second regional seeds, the first regional seed is used as the origin, and the multiple second regional seeds are used as the base points of the corresponding region, and the screen pixel points within the multiple regional pixel areas are regionally positioned based on the origin and the multiple base points of the corresponding region. In this way, the origin and the base points are provided in the multiple regional pixel areas, and then the screen pixel points of the entire OLED mobile phone screen are simultaneously positioned through the origin and the base points, so that it can not only meet the needs of quickly positioning pixels under different background conditions, but also make the positioning efficiency of the screen pixel points of the entire OLED mobile phone screen higher on the basis of simultaneous positioning.
[0078] In one embodiment, the step S601 of sequentially inputting the plurality of first RGB feature values and the first standard RGB feature values into a comparison model for training and outputting a plurality of comparison values includes:
[0079] S6011. Input the plurality of the first RGB feature values and the first standard RGB feature values into a comparison model in sequence for training, and output a plurality of comparison values, wherein the function formula of the comparison model is:
[0080] ;
[0081] in, represents the comparison value from the fth to the tth, represents the fth first standard RGB eigenvalue, represents the fth first RGB eigenvalue, represents the tth first standard RGB eigenvalue, Represents the tth first RGB eigenvalue.
[0082] As described in the above step S6011, the present application sequentially inputs the multiple first RGB feature values and the first standard RGB feature values into the comparison model for training, and outputs multiple comparison values. The multiple comparison values calculated in this way can provide an important basis for comparison with the preset comparison values, and thus can conveniently and quickly screen out the regional seeds corresponding to the pixel areas of the multiple regions.
[0083] In one embodiment, the step S602 of performing regional positioning on the screen pixel points within the pixel areas of the plurality of regions based on the origin of the corresponding region and the plurality of base points comprises:
[0084] S6021, obtaining the origin coordinates of the origin, and establishing a two-dimensional coordinate system of screen pixel points according to the origin coordinates;
[0085] S6022, obtaining a plurality of distances from the origin coordinate to the plurality of base points based on the two-dimensional coordinate system;
[0086] S6023, based on the two-dimensional coordinate system, obtaining multiple direction angles corresponding to the multiple base points in the two-dimensional coordinate system, and sequentially calculating multiple base point coordinates according to the multiple distances, the origin coordinates and the multiple direction angles, wherein the calculation formula is:
[0087] ;
[0088] in, represents the coordinates of the oth to kth base points, Represents the coordinate value of the origin at the X-axis. Represents the coordinate value of the origin on the y-axis. represents the oth distance, represents the kth distance, Indicates the direction angle corresponding to the oth base point in the two-dimensional coordinate system, Indicates the direction angle corresponding to the kth base point in the two-dimensional coordinate system;
[0089] S6024: assign corresponding pixel coordinates to the region pixels of the corresponding region according to the origin coordinates and the plurality of base point coordinates, until the plurality of region pixels correspond to one pixel coordinate.
[0090] As described in the above steps S6021-S6024, the present invention obtains the origin coordinates of the origin, and establishes a two-dimensional coordinate system of the screen pixel points according to the origin coordinates (such as Figure 4 As shown), then based on the two-dimensional coordinate system, multiple distances from the origin coordinate to the multiple base points are obtained, and then based on the two-dimensional coordinate system, multiple direction angles corresponding to the multiple base points in the two-dimensional coordinate system are obtained, and multiple base point coordinates are calculated in sequence according to the multiple distances, the origin coordinates and the multiple direction angles. For example, the coordinates of the origin are (0,0), the distance from the origin to one of the base points is 5 units (because the luminous pixels are evenly arranged when they leave the factory, and the units of a standard pixel are the same), and one of the base points is located at 45° north-east in the two-dimensional coordinate system, and then the angle is converted into radians. , , so that the coordinates of one of the base points P1 are (3.54, 3.54), and then the corresponding pixel coordinates are assigned to the regional pixels of the corresponding area according to the origin coordinates and the multiple base point coordinates, until the multiple regional pixels all correspond to one pixel coordinate. In this way, the origin and the base point are set in the area of the multiple regional pixels, and then the screen pixel points of the entire OLED mobile phone screen are positioned at the same time through the origin and the base point. This can not only meet the needs of fast pixel positioning under different background conditions, but also make the positioning efficiency of the screen pixel points of the entire OLED mobile phone screen higher on the basis of simultaneous positioning. The above-mentioned numbers are only used for example only and are not the only reference.
[0091] In one embodiment, the step S3 of calculating the texture feature coefficient according to the brightness of the plurality of pixels comprises:
[0092] S301, obtaining an average pixel brightness according to the plurality of pixel brightnesses, and calculating a standard pixel brightness difference according to the plurality of pixel brightnesses and the average pixel brightness, wherein the calculation formula is:
[0093] ;
[0094] in, Represents the standard pixel brightness difference, represents the brightness of the first pixel, N represents the number of pixel brightness, The serial number representing the brightness of the pixel, represents the average pixel brightness;
[0095] S302, calculating the texture feature coefficient according to the standard pixel brightness difference and the average pixel brightness, wherein the calculation formula is:
[0096] ;
[0097] in, represents the texture feature coefficient, represents the average pixel brightness, Indicates the standard pixel brightness difference.
[0098] As described in the above steps S301-S302, the present invention obtains the average pixel brightness through the brightness of multiple pixels, and calculates the standard pixel brightness difference according to the brightness of multiple pixels and the average pixel brightness, and then calculates the texture feature coefficient according to the standard pixel brightness difference and the average pixel brightness. For example, the brightness of multiple pixels is 20, 30, 40, 50, 60 respectively;
[0099] Average pixel brightness = (20+30+40+50+60) / 5 = 40;
[0100] The standard pixel brightness difference is calculated as follows:
[0101] ;
[0102] Then the texture feature coefficient is calculated as 14.14 / 40=0.35. The texture feature coefficient calculated in this way can provide an important basis for the selection of pixel seeds when the light-emitting unit is in a bright light state.
[0103] In one embodiment, the step S3 of calculating the grayscale characteristic coefficient according to the plurality of hue contrasts comprises:
[0104] S303, obtaining an average hue contrast according to the plurality of hue contrasts, and calculating a standard hue contrast difference according to the plurality of hue contrasts and the average hue contrast, wherein the calculation formula is:
[0105] ;
[0106] in, Indicates the standard hue contrast difference, represents the i-th hue contrast, N represents the number of hue contrasts, i represents the sequence number of hue contrasts, represents the average tonal contrast;
[0107] S304, calculating the grayscale characteristic coefficient according to the standard hue contrast difference and the average hue contrast, wherein the calculation formula is:
[0108] ;
[0109] in, represents the grayscale characteristic coefficient, represents the average hue contrast, Indicates the standard tonal contrast difference.
[0110] As described in the above steps S303-S304, the present invention obtains an average hue contrast according to a plurality of hue contrasts, calculates a standard hue contrast difference according to a plurality of hue contrasts and the average hue contrast, and calculates a grayscale characteristic coefficient according to the standard hue contrast difference and the average hue contrast, for example: a plurality of hue contrasts are 10, 9, 8, 7, 6;
[0111] Average pixel brightness = (10+9+8+7+6) / 5=8;
[0112] The standard hue contrast difference is calculated as follows:
[0113] ;
[0114] Then the grayscale characteristic coefficient is calculated = 1.414 / 8 = 5.66. The texture characteristic coefficient calculated in this way can provide an important basis for the screening of pixel seeds when the luminous unit is in a non-luminous state.
[0115] In one embodiment, the step S3 of calculating the RGB standard feature value according to the texture feature coefficient and the grayscale feature coefficient comprises:
[0116] S305, obtaining a weight factor of a texture feature coefficient;
[0117] S306, calculating the RGB standard feature value according to the texture feature coefficient, the weight factor of the texture feature coefficient and the grayscale feature coefficient, wherein the calculation formula is:
[0118] ;
[0119] in, Represents the RGB standard feature value, represents the texture feature coefficient, a represents the weight factor of the texture feature coefficient, Represents the grayscale characteristic coefficient.
[0120] As described in the above steps S305-S306, the present invention first obtains the weight factor of the texture feature coefficient, and then calculates the RGB standard eigenvalue based on the texture feature coefficient, the weight factor of the texture feature coefficient and the grayscale feature coefficient. For example, the texture weight factor is 0.3, and the seed comprehensive feature coefficient = 0.35*0.3+5.66*(1-0.3)=4.067. The RGB standard eigenvalue calculated in this way can provide an important basis for seed screening of multiple pixels in the area.
[0121] The present invention also provides an OLED mobile phone screen pixel positioning system based on region growing, comprising:
[0122] The first acquisition module 1 is used to acquire the screen pixels of the entire OLED mobile phone screen and acquire the standard features of the screen pixels, wherein the standard features include a plurality of pixel brightnesses and a plurality of hue contrasts within a preset time;
[0123] The first segmentation module 2 is used to segment the screen pixels of the entire OLED mobile phone screen according to a preset area to obtain a plurality of regional pixel areas, and select any one of the regional pixel areas as a starting growth area;
[0124] A first calculation module 3, used for calculating a texture feature coefficient according to the plurality of pixel brightnesses, calculating a grayscale feature coefficient according to the plurality of hue contrasts, and calculating an RGB standard feature value according to the texture feature coefficient and the grayscale feature coefficient, and defining the RGB standard feature value as a first preset condition;
[0125] The second acquisition module 4 is used to acquire a plurality of first screen pixel points in the starting growth area, acquire a plurality of corresponding RGB feature values according to the plurality of first screen pixel points, and sequentially determine whether the plurality of RGB feature values are equal to a first preset condition, and if they are equal, use the screen pixel points corresponding to the plurality of RGB feature values equal to the first preset condition as standard pixel seeds;
[0126] The third acquisition module 5 is used to obtain the center coordinates of the starting growth area, and use the closest to the center coordinates of the multiple standard pixel seeds as the first area seed;
[0127] The fourth acquisition module 6 is used to obtain multiple second regional seeds corresponding to the remaining multiple regional pixel areas using the first regional seed as a reference object, and perform regional positioning of screen pixel points within the multiple regional pixel areas based on the first regional seed and the multiple second regional seeds.
[0128] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for pixel positioning of an OLED mobile phone screen based on region growth are implemented.
[0129] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0130] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.
[0131] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the scope of the present invention.
Claims
1. A pixel positioning method for OLED mobile phone screen based on region growing, It is characterized in that include: Obtaining the screen pixels of the entire OLED mobile phone screen and obtaining standard features of the screen pixels, wherein the standard features include multiple pixel brightness and multiple tone contrasts within a preset time; The screen pixels of the entire OLED mobile phone screen are divided according to the preset area to obtain a plurality of regional pixel areas, and any one of the regional pixel areas is selected as the starting growth area; Calculating a texture feature coefficient according to the plurality of pixel brightnesses, calculating a grayscale feature coefficient according to the plurality of hue contrasts, and calculating an RGB standard feature value according to the texture feature coefficient and the grayscale feature coefficient, and defining the RGB standard feature value as a first preset condition; The average pixel brightness is obtained according to the plurality of pixel brightnesses, and the standard pixel brightness difference is calculated according to the plurality of pixel brightnesses and the average pixel brightness, wherein the calculation formula is: ; in, Represents the standard pixel brightness difference, represents the brightness of the first pixel, N represents the number of pixel brightness, The serial number representing the brightness of the pixel, represents the average pixel brightness; The texture feature coefficient is calculated according to the standard pixel brightness difference and the average pixel brightness, wherein the calculation formula is: ; in, represents the texture feature coefficient, represents the average pixel brightness, Indicates the standard pixel brightness difference; An average hue contrast is obtained according to the multiple hue contrasts, and a standard hue contrast difference is calculated according to the multiple hue contrasts and the average hue contrast, wherein the calculation formula is: ; in, Indicates the standard hue contrast difference, represents the i-th hue contrast, N represents the number of hue contrasts, i represents the sequence number of hue contrasts, represents the average tonal contrast; The grayscale characteristic coefficient is calculated according to the standard hue contrast difference and the average hue contrast, wherein the calculation formula is: ; in, represents the grayscale characteristic coefficient, represents the average hue contrast, Indicates the standard hue contrast difference; Obtaining weight factors of texture feature coefficients; The RGB standard feature value is calculated according to the texture feature coefficient, the weight factor of the texture feature coefficient and the grayscale feature coefficient, wherein the calculation formula is: ; in, Represents the RGB standard feature value, represents the texture feature coefficient, a represents the weight factor of the texture feature coefficient, Represents the grayscale characteristic coefficient; Acquire a plurality of first screen pixel points in the starting growth area, acquire a plurality of corresponding RGB feature values according to the plurality of first screen pixel points, and determine in turn whether the plurality of RGB feature values are equal to a first preset condition; if they are equal, use the screen pixel points corresponding to the plurality of RGB feature values equal to the first preset condition as standard pixel seeds; Obtain the center coordinates of the starting growth area, and use the one of the multiple standard pixel seeds closest to the center coordinates as the first area seed; Using the first regional seed as a reference object to obtain a plurality of second regional seeds corresponding to the remaining plurality of regional pixel areas, and performing regional positioning of screen pixel points within the plurality of regional pixel areas according to the first regional seed and the plurality of second regional seeds; Obtain multiple second screen pixel points corresponding to the remaining multiple regional pixel areas, obtain multiple corresponding first RGB feature values according to the multiple second screen pixel points, obtain the first standard RGB feature value corresponding to the first regional seed, input the multiple first RGB feature values and the first standard RGB feature value into the comparison model in sequence for training, and output multiple comparison values; sequentially determining whether the plurality of comparison values are equal to a preset comparison value; If they are equal, then the plurality of second screen pixel points corresponding to the regional pixel area corresponding to the first RGB feature value equal to the preset contrast value are used as second regional seeds, the first regional seed is used as the origin, the plurality of second regional seeds are used as base points of the corresponding region, and the screen pixel points within the plurality of regional pixel areas are regionally positioned based on the origin of the corresponding region and the plurality of base points; The plurality of the first RGB feature values and the first standard RGB feature values are sequentially input into a comparison model for training, and a plurality of comparison values are output, wherein the function formula of the comparison model is: ; in, represents the comparison value from the fth to the tth, represents the fth first standard RGB eigenvalue, represents the fth first RGB eigenvalue, represents the tth first standard RGB eigenvalue, Represents the tth first RGB eigenvalue.
2. The OLED mobile phone screen pixel positioning method based on region growing according to claim 1, It is characterized in that The step of performing regional positioning of screen pixel points within a plurality of pixel areas of the region based on the origin of the corresponding region and the plurality of base points comprises: Obtaining the origin coordinates of the origin, and establishing a two-dimensional coordinate system of screen pixel points according to the origin coordinates; Acquire multiple distances from the origin coordinates to the multiple base points based on the two-dimensional coordinate system; Based on the two-dimensional coordinate system, multiple direction angles corresponding to the multiple base points in the two-dimensional coordinate system are obtained, and multiple base point coordinates are calculated in sequence according to the multiple distances, the origin coordinates and the multiple direction angles, wherein the calculation formula is: ; in, represents the coordinates of the oth to kth base points, Represents the coordinate value of the origin at the X-axis. Represents the coordinate value of the origin on the y-axis. represents the oth distance, represents the kth distance, Indicates the direction angle corresponding to the oth base point in the two-dimensional coordinate system, Indicates the direction angle corresponding to the kth base point in the two-dimensional coordinate system; Corresponding pixel coordinates are assigned to the region pixels of the corresponding region according to the origin coordinates and the plurality of base point coordinates, until the plurality of region pixels correspond to one pixel coordinate.
3. An OLED mobile phone screen pixel positioning system based on region growing, It is characterized in that include: The first acquisition module is used to acquire screen pixels of the entire OLED mobile phone screen and acquire standard features of the screen pixels, wherein the standard features include a plurality of pixel brightnesses and a plurality of hue contrasts within a preset time; A first segmentation module is used to segment the screen pixels of the entire OLED mobile phone screen according to a preset area to obtain a plurality of regional pixel areas, and select any one of the regional pixel areas as a starting growth area; A first calculation module, used for calculating a texture feature coefficient according to the plurality of pixel brightnesses, calculating a grayscale feature coefficient according to the plurality of hue contrasts, and calculating an RGB standard feature value according to the texture feature coefficient and the grayscale feature coefficient, and defining the RGB standard feature value as a first preset condition; The average pixel brightness is obtained according to the plurality of pixel brightnesses, and the standard pixel brightness difference is calculated according to the plurality of pixel brightnesses and the average pixel brightness, wherein the calculation formula is: ; in, Represents the standard pixel brightness difference, represents the brightness of the first pixel, N represents the number of pixel brightness, The serial number representing the brightness of the pixel, represents the average pixel brightness; The texture feature coefficient is calculated according to the standard pixel brightness difference and the average pixel brightness, wherein the calculation formula is: ; in, represents the texture feature coefficient, represents the average pixel brightness, Indicates the standard pixel brightness difference; An average hue contrast is obtained according to the multiple hue contrasts, and a standard hue contrast difference is calculated according to the multiple hue contrasts and the average hue contrast, wherein the calculation formula is: ; in, Indicates the standard hue contrast difference, represents the i-th hue contrast, N represents the number of hue contrasts, i represents the sequence number of hue contrasts, represents the average tonal contrast; The grayscale characteristic coefficient is calculated according to the standard hue contrast difference and the average hue contrast, wherein the calculation formula is: ; in, represents the grayscale characteristic coefficient, represents the average hue contrast, Indicates the standard hue contrast difference; Obtaining weight factors of texture feature coefficients; The RGB standard feature value is calculated according to the texture feature coefficient, the weight factor of the texture feature coefficient and the grayscale feature coefficient, wherein the calculation formula is: ; in, Represents the RGB standard feature value, represents the texture feature coefficient, a represents the weight factor of the texture feature coefficient, Represents the grayscale characteristic coefficient; a second acquisition module, used to acquire a plurality of first screen pixel points in the starting growth area, acquire a plurality of corresponding RGB feature values according to the plurality of first screen pixel points, and sequentially determine whether the plurality of RGB feature values are equal to a first preset condition; if they are equal, the screen pixel points corresponding to the plurality of RGB feature values equal to the first preset condition are used as standard pixel seeds; The third acquisition module is used to obtain the center coordinates of the starting growth area and use the one of the multiple standard pixel seeds closest to the center coordinates as the first area seed; a fourth acquisition module, used to acquire a plurality of second screen pixel points corresponding to the remaining plurality of regional pixel areas, acquire a plurality of corresponding first RGB feature values according to the plurality of second screen pixel points, acquire a first standard RGB feature value corresponding to a first regional seed, input the plurality of first RGB feature values and the first standard RGB feature value into a comparison model in sequence for training, and output a plurality of comparison values; A first judging module, used for judging in sequence whether the plurality of comparison values are equal to a preset comparison value; If they are equal, then the plurality of second screen pixel points corresponding to the regional pixel area corresponding to the first RGB feature value equal to the preset contrast value are used as second regional seeds, the first regional seed is used as the origin, the plurality of second regional seeds are used as base points of the corresponding region, and the screen pixel points within the plurality of regional pixel areas are regionally positioned based on the origin of the corresponding region and the plurality of base points; The plurality of the first RGB feature values and the first standard RGB feature values are sequentially input into a comparison model for training, and a plurality of comparison values are output, wherein the function formula of the comparison model is: ; in, represents the comparison value from the fth to the tth, represents the fth first standard RGB eigenvalue, represents the fth first RGB eigenvalue, represents the tth first standard RGB eigenvalue, Represents the tth first RGB eigenvalue.
4. A computer device comprising a memory and a processor, wherein the memory stores a computer program, It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 2 are implemented.
5. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.
