Method for determining light interference area of display panel

Abstract

The invention provides a method for determining a light interference area of a display panel, and relates to the field of semiconductors, and the method comprises the steps: collecting a light-emitting image of the display panel under the condition that the display panel emits light; on the light-emitting image, determining a light-emitting body area of each light-emitting body in the red light-emitting body, the green light-emitting body and the blue light-emitting body; an area surrounded by the overlook edge of the luminous body is defined as a luminous body area; expanding an expanding annular area with a set pixel width towards the outer side of the luminophor area based on each luminophor area; establishing a three-dimensional Euclidean space by using the red, green and blue three-color component values, and constructing a three-dimensional thermodynamic diagram of the expanded annular region in the three-dimensional Euclidean space; and calculating a gradient vector and a gradient direction consistency index of the three-dimensional thermodynamic diagram, and determining a light interference region in the expanded annular region based on the gradient vector and the gradient direction consistency index. The problems that the segmentation precision is obviously insufficient when highly overlapped light-emitting areas are processed in the prior art, and the requirement of precision detection cannot be met are solved.

Description

Technical Field

[0001] This disclosure relates to the field of display technology, and more specifically to a method for determining the light interference region of a display panel. Background Technology

[0002] During the manufacturing process of display panels, visual inspection systems are used to detect characteristics such as, but not limited to, luminous uniformity and brightness. Display panels consist of multiple spaced and arrayed display units, each containing three luminescent elements: red, green, and blue (RGB). After the coating process, the RGB luminescent materials exhibit a significant halo effect, causing overlap between different color luminescent areas. Related technologies are clearly insufficient in their segmentation accuracy when dealing with highly overlapping luminescent areas, failing to meet the requirements of precision inspection. Summary of the Invention

[0003] The main objective of this disclosure is to provide a method for determining the light interference region of a display panel, so as to improve the problem that the segmentation accuracy is obviously insufficient when dealing with highly overlapping light-emitting regions in related technologies, which cannot meet the needs of precision detection.

[0004] To achieve the above objectives, a first aspect of this disclosure provides a method for determining the light interference region of a display panel, the method comprising: When the display panel emits light, an image of the illuminated display panel is captured; wherein the display panel includes multiple display units arranged in an array and spaced apart, and each display unit includes red light emitters, green light emitters and blue light emitters arranged sequentially and spaced apart; In the luminescence image, the luminescence locality of each of the red, green and blue luminescent bodies is determined; wherein, the area enclosed by the top-view edge of the luminescent body is defined as the luminescence locality. An extended annular region of a set pixel width is extended outward from the local area of ​​each light source; A three-dimensional Euclidean space is established using the red, green, and blue color component values, and a three-dimensional heat map of the extended annular region is constructed in the three-dimensional Euclidean space. Calculate the gradient vector and gradient direction consistency index of the three-dimensional heat map, and determine the optical interference region in the extended annular region based on the gradient vector and gradient direction consistency index.

[0005] In some embodiments of this disclosure, a three-dimensional Euclidean space is established using red, green, and blue color component values, and a three-dimensional heat map of an extended annular region is constructed in the three-dimensional Euclidean space, including: Multiple sampling points were collected in the extended ring area, and the red component value, green component value and blue component value of each sampling point were obtained. Based on the red, green, and blue component values ​​of each sampling point, a three-dimensional heat map of the extended annular region is constructed in three-dimensional Euclidean space.

[0006] In some embodiments of this disclosure, a three-dimensional heat map of an extended annular region is constructed in three-dimensional Euclidean space based on the red, green, and blue component values ​​of each sampling point, including: A three-dimensional color distribution point cloud is constructed based on the red, green, and blue component values ​​of each sampling point. Based on the three-dimensional color distribution point cloud, a continuous three-dimensional thermal density field of the extended ring region is constructed using the kernel density estimation method, and the three-dimensional thermal density field is used as a three-dimensional heat map.

[0007] In some embodiments of this disclosure, calculating the gradient vector and gradient direction consistency index of a three-dimensional heatmap includes: Calculate the gradient magnitude of the gradient vector of the three-dimensional thermal density field, and use the gradient magnitude to characterize the drasticness of color change; Define a gradient direction consistency index and calculate the gradient direction consistency index value of the 3D heatmap.

[0008] In some embodiments of this disclosure, the optical interference region in the extended annular region is determined based on the gradient vector and gradient direction consistency index, including: Based on the gradient magnitude and gradient direction consistency index values, the optical interference region in the extended annular region is determined.

[0009] In some embodiments of this disclosure, the optical interference region in the extended annular region is determined based on the gradient magnitude and gradient direction consistency index value, including: The region within the extended annular region that meets the set weak interference classification conditions is identified as a weak interference region within the optical interference region. The weak interference classification conditions are set as follows: the gradient magnitude is less than or equal to the first classification threshold and greater than the third classification threshold, and the gradient direction consistency index value is less than or equal to the second classification threshold and greater than the fourth classification threshold. The first, second, third, and fourth classification thresholds are preset.

[0010] In some embodiments of this disclosure, the optical interference region in the extended annular region is determined based on the gradient magnitude and gradient direction consistency index value, including: The region within the extended annular region that meets the defined strong interference classification conditions is identified as the strong interference region within the optical interference region. The strong interference classification conditions are set as follows: the gradient magnitude is less than or equal to the third classification threshold, and the gradient direction consistency index value is less than or equal to the fourth classification threshold. The thresholds for the third and fourth categories are preset.

[0011] In some embodiments of this disclosure, the method further includes: determining the independent luminescent region of the luminescent body surrounded by the extended annular region based on the gradient magnitude and gradient direction consistency index value.

[0012] In some embodiments of this disclosure, the independent luminescent region of the luminescent body surrounded by the extended annular region is determined based on the gradient magnitude and gradient direction consistency index value, including: The region within the extended annular region that meets the set independent light emission classification conditions is defined as the independent light emission region of the light-emitting body surrounded by the extended annular region. The independent emission classification conditions are set as follows: the gradient magnitude is greater than the first classification threshold, and the gradient direction consistency index value is greater than the second classification threshold. The first and second classification thresholds are preset.

[0013] In some embodiments of this disclosure, the display panel further includes: a light-transmitting film covering a plurality of display units; and / or, Multiple display units are arranged in an interleaved or aligned array and spaced apart.

[0014] A second aspect of this disclosure provides an apparatus for determining the light interference region of a display panel. The apparatus includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the light interference region determination method for the display panel provided in any of the first aspects.

[0015] A third aspect of this disclosure provides a computer-readable storage medium storing computer instructions for causing a computer to perform the light interference region determination method for a display panel provided in any of the first aspects.

[0016] A fourth aspect of this disclosure provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the light interference region determination method for a display panel provided in any of the first aspects.

[0017] The method for determining the light interference region of a display panel provided in this disclosure extends an extended annular region of a set pixel width outward from the local area of ​​each light emitter. A three-dimensional Euclidean space is established using the red, green, and blue color component values, and a three-dimensional heat map of the extended annular region is constructed in the three-dimensional Euclidean space. Then, based on the gradient vector and gradient direction consistency index, the light interference region in the extended annular region is determined. This improves the segmentation accuracy of the light interference region in the extended annular region, which is a highly overlapping light-emitting region, to meet the requirements of precise detection of the light interference region. This improves the problem in related technologies where the segmentation accuracy is significantly insufficient when processing highly overlapping light-emitting regions, thus failing to meet the requirements of precise detection. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of this disclosure, the accompanying drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a method for determining the light interference region of a display panel according to an embodiment of this disclosure; Figure 2 A schematic flowchart illustrating the process of constructing a three-dimensional heat map of an extended annular region according to an embodiment of this disclosure; Figure 3 A schematic diagram illustrating the process of constructing a three-dimensional heat map of an extended annular region in three-dimensional Euclidean space, as provided in another embodiment of this disclosure; Figure 4 A flowchart illustrating the process of determining the optical interference region and the independent light-emitting region in an extended annular region according to an embodiment of this disclosure; Figure 5 A schematic diagram of a light-emitting image provided in an embodiment of this disclosure; Figure 6 This is a schematic diagram of the region of the light-emitting element provided in an embodiment of the present disclosure; Figure 7 A schematic diagram of the extended annular region and optical interference region provided in an embodiment of this disclosure; Figure 8 This is a flowchart illustrating another method for determining the light interference region of a display panel according to an embodiment of the present disclosure; Figure 9 This is a schematic diagram illustrating the construction of a three-dimensional color space heatmap according to an embodiment of this disclosure; Figure 10 This is a schematic diagram of a gradient change analysis and region classification model shown in one embodiment of the present disclosure; Figure 11 A block diagram of an electronic device provided in an embodiment of this disclosure.

[0020] It should be noted that the elements in the attached diagram are schematic and not drawn to scale. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] In this disclosure, the terms “upper,” “lower,” “left,” “right,” “front,” “rear,” “top,” “bottom,” “inner,” “outer,” and “middle,” etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings. These terms are primarily for the purpose of better describing this disclosure and its embodiments, and are not intended to limit the indicated devices, elements, or components to having a specific orientation, or to be constructed and operated in a specific orientation.

[0024] Furthermore, in addition to indicating location or positional relationship, some of the aforementioned terms may also have other meanings. For example, the term "above" may also be used in some cases to indicate a dependency or connection relationship. Those skilled in the art can understand the specific meaning of these terms in this disclosure according to the specific circumstances.

[0025] Furthermore, the terms "set up," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral structure; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection via an intermediate medium, or an internal connection between two devices, components, or parts. Those skilled in the art can understand the specific meaning of these terms in this disclosure according to the specific circumstances.

[0026] It should be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0027] Related technologies face the following technical bottlenecks when dealing with highly overlapping luminous regions: (1) Limitations of two-dimensional color space: Traditional color segmentation methods based on two-dimensional images cannot fully represent the complex characteristics of color mixing; (2) Blurred boundary problem: The halo effect causes the boundary of the color transition region to be blurred, and the threshold segmentation method fails; (3) Difficulty in identifying interference regions: There is a lack of effective mathematical models to quantify the degree of color interference and the boundary position. Related technologies such as segmentation methods based on HSV color space and segmentation algorithms based on edge detection have significantly insufficient segmentation accuracy when dealing with highly overlapping luminous regions, and cannot meet the needs of precise detection.

[0028] Example 1 To address at least some of the aforementioned problems, this disclosure provides a method for determining the light interference region of a display panel. The method aims to accurately segment the overlapping RGB (R for Red, G for Green, B for Blue) light-emitting regions after coating, thereby improving upon the problem in related technologies where the segmentation accuracy is significantly insufficient when processing highly overlapping light-emitting regions, failing to meet the requirements of precision detection. Figure 1 As shown, the method for determining the light interference area of ​​this display panel mainly includes the following steps: Step S110: When the display panel is emitting light, acquire the emitting image of the display panel; wherein, the display panel includes multiple display units arranged in an array and spaced apart, and each display unit includes red light emitters, green light emitters and blue light emitters arranged sequentially and spaced apart; Step S120: On the luminescence image, determine the luminescence local area of ​​each of the red, green and blue luminescence bodies; wherein, the area enclosed by the top view edge of the luminescence body is defined as the luminescence local area; Step S130: Based on each light-emitting body region, extend an extended annular region with a set pixel width outward from the light-emitting body region; Step S140: Establish a three-dimensional Euclidean space using the red, green and blue color component values, and construct a three-dimensional heat map of the extended annular region in the three-dimensional Euclidean space; Step S150: Calculate the gradient vector and gradient direction consistency index of the three-dimensional heat map, and determine the optical interference region in the extended annular region based on the gradient vector and gradient direction consistency index.

[0029] In the above scheme, an extended annular region of a set pixel width is extended outward from the local area of ​​each luminescent element. A three-dimensional Euclidean space is established using the red, green, and blue color component values. A three-dimensional heatmap of the extended annular region is then constructed within this space. This allows for multi-angle quantification and statistical analysis of the colors of pixels located within the extended annular region from the perspective of the red, green, and blue color components. Subsequently, the light interference region within the extended annular region is determined based on the gradient vector and gradient direction consistency index. This approach overcomes the limitations of traditional two-dimensional image processing by analyzing color distribution characteristics in a three-dimensional color space. By utilizing the gradient vector and gradient direction consistency index, the intensity and direction of color changes can be accurately reflected from the perspective of the red, green, and blue color components. This improves the segmentation accuracy of the light interference region within the extended annular region, which is a highly overlapping luminescent area, thus meeting the requirements for precise detection of the light interference region. This addresses the problem in related technologies where the segmentation accuracy is insufficient when processing highly overlapping luminescent areas, failing to meet the needs of precise detection. The following section, in conjunction with the appendix... Figures 1 to 11 The method disclosed herein is described in detail.

[0030] First, refer to Figure 1 and Figure 5 The system captures an image of the illuminated display panel when it is emitting light. Specifically, this can be achieved using a camera on the display panel. The display panel comprises multiple display units arranged in an array and spaced apart. Each display unit includes red, green, and blue light emitters arranged sequentially and at intervals.

[0031] There are various ways to arrange multiple display unit arrays. For example, in some embodiments, refer to... Figure 5 Multiple display units can be arranged in an interleaved array with intervals. In other embodiments, multiple display units can be arranged in an aligned array with intervals. The order of the red, green, and blue light emitters in each display unit can be the same or different.

[0032] For example, the display panel may include a light-transmitting film covering multiple display units, i.e., the display panel in this case is a film-coated display panel. The light-transmitting film can be a light-transmitting material film layer composed of any material.

[0033] Next, refer to Figure 1 and Figure 6On the luminescence image, the luminescence locality of each of the red, green, and blue luminescent bodies is determined. The area enclosed by the top-view edge of the luminescent body is defined as its luminescence locality. For example... Figure 6 The diagram shows a schematic of a blue luminescent body region. That is, the luminescent body region is the light-emitting area composed of light emitted by the luminescent body in a direction perpendicular to the display panel. The luminous brightness of the luminescent body region is often the strongest within the light-emitting area covered by each luminescent body.

[0034] There are various ways to determine the luminescent region of each of the red, green, and blue luminescent bodies in a luminescent image. Some methods are illustrated below.

[0035] For example, determining the luminous body region of each of the red, green, and blue luminous bodies in a luminous image can be achieved through the following steps: decomposing each pixel in the luminous image into red, green, and blue color component values; determining the optimal segmentation threshold using the Otsu algorithm based on the brightness distribution characteristics of the red, green, and blue color components; and determining the luminous body region of each of the red, green, and blue luminous bodies based on the optimal segmentation threshold and the red, green, and blue color component values ​​of each pixel in the luminous image.

[0036] For details, please refer to Figure 8 A color threshold-based region segmentation method can be used to initially locate the red, green, and blue emission color channels. First, RGB channel separation is performed, decomposing the input emission image into three independent color channels (R, G, B) to obtain the red, green, and blue color component values ​​for each pixel. Next, adaptive threshold segmentation is performed, using the Otsu algorithm to determine the optimal segmentation threshold based on the brightness distribution characteristics of each emission color channel. Finally, morphological optimization is performed, filling holes within the region through closing operations and eliminating noise interference through opening operations.

[0037] Its mathematical expression principle is as follows: Let the input luminescent image be I(x,y), and the segmented binary mask be M. k Given (x, y), where k ∈ {R, G, B}, then: M k (x,y) = 1, if I k (x,y)≥T k ; M k (x,y) = 0, if I k (x,y) <T k ; Where T k This is the adaptive threshold for each color channel.

[0038] Next, refer to Figure 1 , Figure 7 and Figure 8 An extended annular region of a predetermined pixel width is formed by extending the region of each luminescent element outward from its own edge. This predetermined pixel width can be represented by Δr pixels, and it is the annular region formed by extending the predetermined pixel width outward from the edge of the luminescent element's own region. Often, overlapping light regions formed by the halos emitted by adjacent luminescent elements exist within this extended annular region. The specific size of the predetermined pixel width can be determined based on factors such as the spacing between different luminescent elements.

[0039] Next, refer to Figure 1 , Figure 7 , Figure 8 and Figure 9 A three-dimensional Euclidean space is established using the red, green, and blue color components. Within this space, a three-dimensional heatmap of an extended annular region is constructed. This allows for multi-angle quantification and statistical analysis of the colors of pixels located within the extended annular region from the perspective of the red, green, and blue color components.

[0040] There are various ways to construct a three-dimensional Euclidean space using red, green, and blue color component values, and to build a three-dimensional heat map of an extended annular region in the three-dimensional Euclidean space. Some of these methods are illustrated below.

[0041] For example, refer to Figure 2 , Figure 8 and Figure 9 This method establishes a three-dimensional Euclidean space using red, green, and blue color component values. Within this space, a three-dimensional heatmap of an extended annular region is constructed. This process includes: collecting multiple sampling points within the extended annular region to obtain the red, green, and blue component values ​​for each point; and constructing a three-dimensional heatmap of the extended annular region in three-dimensional Euclidean space based on these values. In other words, by sampling, the red, green, and blue component values ​​of multiple points are obtained, simplifying the construction of the three-dimensional heatmap. Furthermore, by constructing a three-dimensional heatmap of the extended annular region in three-dimensional Euclidean space based on these values, the color of pixels located within the extended annular region can be quantified and statistically analyzed from multiple perspectives, based on the red, green, and blue color components.

[0042] There are several ways to construct a three-dimensional heat map of an extended annular region in three-dimensional Euclidean space based on the red, green, and blue component values ​​of each sampling point. Some of these methods are illustrated below.

[0043] For example, refer to Figure 3 , Figure 8 and Figure 9Based on the red, green, and blue component values ​​of each sampling point, a 3D heatmap of the extended ring region is constructed in 3D Euclidean space. This can include: constructing a 3D color distribution point cloud based on the red, green, and blue component values ​​of each sampling point; and constructing a continuous 3D thermal density field of the extended ring region based on the 3D color distribution point cloud using a kernel density estimation method, using this 3D thermal density field as the 3D heatmap. This improves the accuracy of the constructed 3D heatmap.

[0044] The following is an example of constructing a three-dimensional heatmap.

[0045] refer to Figure 8 and Figure 9 The three-dimensional color space mapping model is as follows: a three-dimensional Euclidean space is constructed using the RGB three-channel values, and each pixel P... i It can be represented as: P i = (r i , g i , b i ) ∈ [0,255]³.

[0046] For each initially located luminous body region, an extended annular region is obtained by expanding outward by Δr pixels. Dense sampling is performed within the extended annular region to construct a three-dimensional color distribution point cloud.

[0047] The thermal density field is calculated using the following method: a continuous three-dimensional thermal density field is constructed using the kernel density estimation method. f(r,g,b) = (1 / n) · ∑ i K((rr i ) / h, (gg i ) / h, (bb i ) / h) Where K(·) is the three-dimensional Gaussian kernel function, h is the bandwidth parameter, and n is the number of sampling points.

[0048] Next, refer to Figure 1 , Figure 7 and Figure 8 The gradient vector and gradient direction consistency index of the three-dimensional heatmap are calculated, and based on these indices, the optical interference region in the extended annular region is determined. For example, refer to... Figure 7The determined blue-red and blue-green light interference regions are identified. By utilizing gradient vectors and gradient direction consistency indices, the intensity and direction of color changes can be accurately reflected from the perspective of the red, green, and blue color components. This improves the segmentation accuracy of the light interference region, which is a highly overlapping light-emitting area in the extended annular region, thus meeting the requirements for precise detection of the light interference region. This addresses the problem in related technologies where the segmentation accuracy is significantly insufficient when dealing with highly overlapping light-emitting areas, failing to meet the needs of precise detection.

[0049] There are several ways to calculate the gradient vector and gradient direction consistency index of a 3D heatmap. Some of these methods are illustrated below.

[0050] For example, refer to Figure 10 Calculating the gradient vector and gradient direction consistency index of a three-dimensional heat map can include: calculating the gradient magnitude of the gradient vector of the three-dimensional thermal density field, using the gradient magnitude to characterize the intensity of color change; defining the gradient direction consistency index, and calculating the gradient direction consistency index value of the three-dimensional heat map.

[0051] The following is an example of calculating the gradient vector and gradient direction consistency index of a three-dimensional heatmap.

[0052] refer to Figure 10 The following three-dimensional gradient field calculation is performed: For the thermodynamic density field f(r,g,b), its gradient vector is calculated: f = ( f / r, f / g, f / b) The gradient magnitude of the gradient vector of the three-dimensional heatmap is calculated using the following formula to characterize the drasticness of color changes: || f‖ = √[( f / r) 2 + ( f / g) 2 + ( f / b) 2 ] Gradient direction consistency analysis is performed as follows. The gradient direction consistency index is defined as follows, and the value of the gradient direction consistency index for the 3D heatmap is calculated using the following formula: C = (1 / N) · ∑ i ∑ j f i , f j / (‖ f i ‖ · ‖ f j ‖) in ·,· denoted as vector inner product, where N is the number of gradient pairs within the local region.

[0053] There are several ways to determine the optical interference region in the extended annular region based on the gradient vector and gradient direction consistency index. Some of these methods are illustrated below.

[0054] For example, refer to Figure 4 and Figure 10 Based on the gradient vector and gradient direction consistency index, the optical interference region within the extended annular region is determined, including: determining the optical interference region within the extended annular region based on the gradient magnitude and gradient direction consistency index values. This quantitative approach determines the optical interference region within the extended annular region, thereby improving the segmentation accuracy of the optical interference region.

[0055] There are several ways to determine the optical interference region in the extended annular region based on the gradient magnitude and gradient direction consistency index. Some of these methods are illustrated below.

[0056] For example, refer to Figure 4 and Figure 10 Based on the gradient magnitude and gradient direction consistency index, the optical interference region within the extended annular region is determined. This can include: identifying regions within the extended annular region that meet predefined weak interference classification criteria as weak interference regions within the optical interference region. The predefined weak interference classification criteria are: a gradient magnitude less than or equal to a first classification threshold and greater than a third classification threshold; and a gradient direction consistency index value less than or equal to a second classification threshold and greater than a fourth classification threshold. The first, second, third, and fourth classification thresholds are pre-set. This method facilitates accurate segmentation of weak interference regions within the extended annular region, thereby quantifying the degree of interference and classifying it to improve the accuracy of optical interference region segmentation.

[0057] For example, refer to Figure 4 and Figure 10Based on the gradient magnitude and gradient direction consistency index, the optical interference region within the extended annular region is determined. This can include: identifying regions within the extended annular region that meet predefined strong interference classification conditions as strong interference regions within the optical interference region; wherein the predefined strong interference classification conditions are: the gradient magnitude is less than or equal to a third classification threshold, and the gradient direction consistency index value is less than or equal to a fourth classification threshold; the third and fourth classification thresholds are pre-set. This method facilitates the accurate segmentation of strong interference regions within the extended annular region, thereby quantifying the degree of interference and classifying it, thus improving the accuracy of optical interference region segmentation.

[0058] For example, refer to Figure 4 , Figure 7 and Figure 10 The method may further include: determining the independent luminescent region of the luminescent body surrounded by the extended annular region based on the gradient magnitude and gradient direction consistency index value. For example, refer to... Figure 7 The independent luminescent region of the blue luminescent body is shown. This allows for the determination of the independent luminescent region of the luminescent body surrounded by the extended annular region using quantitative indicators, thus improving the accuracy of the determined independent luminescent region.

[0059] Regarding the method of determining the independent luminous region of the luminous body surrounded by the extended annular region based on the gradient magnitude and gradient direction consistency index value, there are many ways to do so. Some methods are exemplified below.

[0060] For example, refer to Figure 4 , Figure 7 and Figure 10 Based on the gradient magnitude and gradient direction consistency index, the independent luminous regions of the luminescent body surrounded by the extended annular region are determined. This can include: identifying regions within the extended annular region that meet predefined independent luminous region classification criteria as independent luminous region of the luminescent body surrounded by the extended annular region; wherein the predefined independent luminous region classification criteria are: a gradient magnitude greater than a first classification threshold, and a gradient direction consistency index greater than a second classification threshold; the first and second classification thresholds are pre-set. This method facilitates accurate segmentation of independent luminous regions within the extended annular region, thereby quantifying the degree of independent luminous region segmentation and classifying them to improve the accuracy of independent luminous region segmentation.

[0061] The following is an example of region classification based on gradient magnitude and gradient direction consistency index values.

[0062] refer to Figure 10 A regional classification mathematical model is established. Based on the gradient feature magnitude and gradient direction consistency index, a regional classification decision function is established, and classification is performed in the following manner: If ‖ |f| > θ1 and C > θ2, then determine that this area is the independent light-emitting area of the light-emitting body surrounded by the extended annular area; If θ3 < ‖ |f| ≤ θ1 and θ4 < C ≤ θ2, then determine that this area is the weak interference area in the optical interference area; If ‖ |f| ≤ θ3 and C ≤ θ4, then determine that this area is the strong interference area in the optical interference area.

[0063] Among them, θ1 - θ4 are the first classification threshold, the second classification threshold, the third classification threshold and the fourth classification area respectively, and these classification thresholds are classification thresholds determined through a large amount of experimental data. The above method establishes a region classification model based on the gradient magnitude and direction consistency of three-dimensional gradient features, providing a quantitative basis for the identification of the interference area.

[0064] It should be noted that the above weak interference area and strong interference area are two areas quantitatively classified according to the relative relationship of the interference degree.

[0065] Exemplarily, the method may further include: inputting the optical interference area image into a deep learning network model, and enabling the deep learning network model to segment the optical interference area to obtain a deep learning segmentation result. Since the data volume of the optical interference area image is much smaller than that of the entire light-emitting image, the processing rate of the deep learning network can be improved, so as to improve the problem that the segmentation speed is slow and cannot meet the detection requirements when the related technology uses the deep learning network to segment the light-emitting area of the light-emitting body. The deep learning segmentation result output after the deep learning network model segments the optical interference area has some fine-tuning compared with the Figure 7 shown optical interference area, thereby improving the classification accuracy. The deep learning segmentation result not only outputs the segmentation result of the optical interference area, but also outputs the confidence of the segmented area, thereby facilitating the subsequent determination of the transition area of the light-emitting body based on the confidence.

[0066] For example, a deep learning network model may include an encoder, an attention module, and a decoder, coupled sequentially in input-output order. The deep learning network model segments light interference regions, which may include the following steps: the encoder extracts multi-level features of the light interference region image input to the deep learning network model through its convolutional and pooling layers; the attention module, based on the multi-level features output by the encoder, uses its own luminous channel attention mechanism and spatial attention mechanism to classify and obtain a classification result; the decoder processes the classification result output by the attention module through upsampling and skip connections to restore spatial resolution and outputs pixel-level deep learning segmentation results. Through this approach, the accuracy and detail of the deep learning network model in segmenting light interference regions can be improved, thereby meeting higher detection standards.

[0067] Specifically, for regions classified as light interference areas, a deep learning network is used for fine segmentation. The deep learning network model adopts an encoder-decoder structure with an attention mechanism. The encoder extracts multi-level features through convolutional and pooling layers; the attention module enhances attention to the interference region based on channel attention and spatial attention; and the decoder restores spatial resolution through upsampling and skip connections, outputting pixel-level deep learning segmentation results.

[0068] For example, the attention module uses its own luminescent channel attention mechanism and spatial attention mechanism to obtain classification results. This can include: the attention module performs weighted processing based on luminescent channel-related features and spatial-related features using the luminescent channel attention mechanism and spatial attention mechanism to obtain a weighted feature map; the attention module then performs classification based on the weighted feature map to obtain the classification result. By using the luminescent channel attention mechanism and spatial attention mechanism to perform weighted processing to obtain the weighted feature map, and then performing classification based on the weighted feature map, the accuracy of the classification results can be improved.

[0069] For example, the deep learning network model may further include a loss function monitoring module, which evaluates the deep learning segmentation results output by the deep learning network model to obtain evaluation results, so that the deep learning network model adjusts its own parameters based on the evaluation results. This enables the deep learning network model to adaptively optimize its parameters during application, thereby increasing the accuracy of the deep learning network model's output results with increasing application time.

[0070] For example, after the deep learning network model outputs the deep learning segmentation result, the loss function monitoring module calculates the loss value between the deep learning segmentation result and the light interference region image; if the loss value is less than or equal to a set threshold, the deep learning segmentation result is used as the final result output by the deep learning network model. This ensures that the output result of the deep learning network model meets the application requirements.

[0071] If the loss value exceeds a set threshold, the deep learning network model adjusts its parameters based on the loss value and processes the light interference region image again until the loss value is less than or equal to the set threshold. In other words, if the loss value of the deep learning segmentation result output by the deep learning network model relative to the light interference region image is greater than the set threshold, it indicates that the accuracy of the deep learning segmentation result output by the deep learning network model is poor, thus enabling real-time monitoring of the output quality. If the output result does not meet the requirements, the deep learning network model optimizes its parameters based on the loss value of the current deep learning segmentation result relative to the light interference region image, and performs at least one iteration until the loss value of the deep learning segmentation result output by the deep learning network model relative to the light interference region is less than or equal to the set threshold.

[0072] For example, the loss function monitoring module calculates the loss value between the deep learning segmentation result and the light interference region image, which may include: the loss function monitoring module calculates the cross-entropy loss value and the Dice loss value between the deep learning segmentation result and the light interference region image respectively; calculates the product of the cross-entropy loss value and the first weight coefficient to obtain a first product value; calculates the product of the Dice loss value and the second weight coefficient to obtain a second product value; and uses the sum of the first product value and the second product value as the loss value between the deep learning segmentation result and the light interference region image calculated by the loss function monitoring module.

[0073] For example, the loss function monitoring module combines cross-entropy loss and Dice loss to optimize segmentation boundary accuracy. The loss function monitoring module calculates the loss value between the deep learning segmentation result and the light interference region image: L = λ1*L_CE + λ2*L_Dice. Here, L_CE represents the cross-entropy loss value between the deep learning segmentation result and the light interference region image, addressing class imbalance; λ1 represents the first weighting coefficient. L_Dice represents the Dice loss value between the deep learning segmentation result and the light interference region image, optimizing boundary alignment accuracy; λ2 represents the second weighting coefficient.

[0074] For example, the method may further include: using a confidence-based weighted fusion method to determine the transition region of each of the red, green and blue luminescent bodies in the luminescent image.

[0075] For example, traditional segmentation results and deep learning segmentation results can be intelligently fused. Independent luminescent regions can directly utilize traditional segmentation results. The segmentation results for light interference regions can utilize the deep learning segmentation results output by the aforementioned deep learning network model. Transition regions can be obtained through a confidence-based weighted fusion method. Morphological operations and connectivity analysis are used to optimize the final segmentation boundaries, ensuring the continuity and integrity of the regions.

[0076] From the above description, it can be seen that this disclosure achieves the following technical effects: It solves the technical bottleneck of traditional methods in processing color interference regions by combining three-dimensional thermal gradient analysis and deep learning. A complete three-dimensional color space analysis system is constructed, combining gradient change mathematical models and deep learning technology to achieve accurate segmentation of luminescent body overlap regions. This method can be applied to computer vision, image processing, and machine learning technologies, especially for the accurate segmentation of RGB luminescent body overlap halo regions in laminated display panels. It is suitable for precision optical inspection, semiconductor manufacturing, and display panel quality control. This method significantly improves segmentation accuracy: through three-dimensional thermal gradient analysis, color interference regions can be accurately identified, with segmentation accuracy 40-60% higher than traditional two-dimensional methods; moreover, the mathematical model in this method is innovative, establishing a region classification mathematical model based on three-dimensional gradient changes, providing a theoretical basis for color interference analysis. This method has strong generalization ability, is not dependent on specific imaging conditions or material properties, and is highly adaptable. This method has high engineering practical value and can be integrated into existing industrial vision inspection systems, significantly improving the quality control level of laminated display panel processes. Processing efficiency has been optimized. Through a region classification mechanism, the deep learning network model is activated only in necessary light interference areas, resulting in an overall processing speed 2-3 times faster than the full deep learning approach. A hybrid architecture design is employed, intelligently combining traditional image processing and deep learning to optimize processing efficiency while maintaining accuracy. An adaptive parameter mechanism automatically adjusts key parameters in the deep learning network model based on image characteristics, adapting to different application scenarios.

[0077] Example 2 This disclosure also provides an apparatus for determining the light interference region of a display panel, the apparatus comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the method for determining the light interference region of a display panel provided in any of the first aspects.

[0078] The specific methods of execution of each unit in the above device embodiments have been described in detail in Embodiment 1 of the method, and will not be elaborated here.

[0079] Example 3 This disclosure provides a computer-readable storage medium storing computer instructions for causing a computer to execute the light interference region determination method for a display panel provided in any of the first aspects.

[0080] Example 4 This disclosure provides an electronic device, such as... Figure 11 As shown, the electronic device includes: at least one processor 111; and a memory 112 communicatively connected to the at least one processor 111; wherein the memory 112 stores a computer program executable by the at least one processor 111, the computer program being executed by the at least one processor 111 to cause the at least one processor 111 to perform the light interference region determination method for the display panel provided in any of the first aspects.

[0081] refer to Figure 11 The electronic device includes one or more processors 111 and a memory 112. Figure 11 Taking a processor 111 as an example, the electronic device may also include an input device 113 and an output device 114. The processor 111, memory 112, input device 113, and output device 114 can be connected via a bus or other means. Figure 11 Taking the example of a connection between China and Israel via a bus.

[0082] Processor 111 can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips. The general-purpose processor can be a microprocessor or any conventional processor.

[0083] The memory 112, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the construction method in the embodiments of this disclosure. The processor 111 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions, and modules stored in the memory 112, thereby implementing the method for determining the light interference region of the display panel in the above method embodiments.

[0084] The memory 112 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the use of the processing device operated by the server. Furthermore, the memory 112 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 112 may optionally include memory remotely located relative to the processor 111, and these remote memories can be connected to a network connection device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0085] Input device 113 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the server's processing device. Output device 114 may include display devices such as a display screen.

[0086] One or more modules are stored in memory 112, and when executed by one or more processors 111, they perform actions such as... Figure 1 The method is shown. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be performed in a different order than that shown here.

[0087] Those skilled in the art will understand that all or part of the processes in the above method embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes as described in the above method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory (FM), hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0088] Although embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for determining the optical interference region of a display panel, characterized in that, include: When the display panel is emitting light, an image of the emitting light from the display panel is captured; wherein, the display panel includes a plurality of display units arranged in an array and spaced apart, and each display unit includes red light emitters, green light emitters and blue light emitters arranged sequentially and spaced apart; On the luminescent image, the luminescent body region of each of the red, green, and blue luminescent bodies is determined; wherein, the area enclosed by the top-view edge of the luminescent body is defined as the luminescent body region; An extended annular region of a set pixel width is extended outward from the local area of ​​each light source; A three-dimensional Euclidean space is established using the red, green, and blue color component values, and a three-dimensional heat map of the extended annular region is constructed in the three-dimensional Euclidean space. Calculate the gradient vector and gradient direction consistency index of the three-dimensional heat map, and determine the optical interference region in the extended annular region based on the gradient vector and the gradient direction consistency index.

2. The method as described in claim 1, characterized in that, The process of establishing a three-dimensional Euclidean space using red, green, and blue color component values, and constructing a three-dimensional heat map of the extended annular region within that three-dimensional Euclidean space, includes: Multiple sampling points were collected in the extended annular area to obtain the red component value, green component value and blue component value of each sampling point; Based on the red, green, and blue component values ​​of each sampling point, a three-dimensional heat map of the extended annular region is constructed in the three-dimensional Euclidean space.

3. The method as described in claim 2, characterized in that, Based on the red, green, and blue component values ​​of each sampling point, a three-dimensional heat map of the extended annular region is constructed in the three-dimensional Euclidean space, including: A three-dimensional color distribution point cloud is constructed based on the red, green, and blue component values ​​of each sampling point. Based on the three-dimensional color distribution point cloud, a continuous three-dimensional thermal density field of the extended annular region is constructed using the kernel density estimation method, and the three-dimensional thermal density field is used as the three-dimensional thermal map.

4. The method as described in claim 3, characterized in that, The calculation of the gradient vector and gradient direction consistency index of the three-dimensional heatmap includes: Calculate the gradient magnitude of the gradient vector of the three-dimensional thermal density field, and use the gradient magnitude to characterize the drasticness of the color change; Define a gradient direction consistency index and calculate the gradient direction consistency index value of the three-dimensional heatmap.

5. The method as described in claim 4, characterized in that, The step of determining the optical interference region in the extended annular region based on the gradient vector and the gradient direction consistency index includes: Based on the gradient magnitude and the gradient direction consistency index value, the optical interference region in the extended annular region is determined.

6. The method as described in claim 5, characterized in that, The step of determining the optical interference region in the extended annular region based on the gradient magnitude and the gradient direction consistency index value includes: The region in the extended annular region that meets the set weak interference classification conditions is determined as the weak interference region in the optical interference region; The weak interference classification condition is defined as follows: the gradient magnitude is less than or equal to the first classification threshold and greater than the third classification threshold, and the gradient direction consistency index value is less than or equal to the second classification threshold and greater than the fourth classification threshold. The first classification threshold, the second classification threshold, the third classification threshold, and the fourth classification threshold are preset.

7. The method as described in claim 5, characterized in that, The step of determining the optical interference region in the extended annular region based on the gradient magnitude and the gradient direction consistency index value includes: The region in the extended annular region that meets the set strong interference classification conditions is determined as the strong interference region in the optical interference region; The strong interference classification condition is defined as follows: the gradient magnitude is less than or equal to the third classification threshold, and the gradient direction consistency index value is less than or equal to the fourth classification threshold. The third and fourth classification thresholds are preset.

8. The method as described in claim 5, characterized in that, Also includes: Based on the gradient magnitude and the gradient direction consistency index value, the independent luminous region of the luminescent body surrounded by the extended annular region is determined.

9. The method as described in claim 8, characterized in that, The step of determining the independent luminous region of the luminescent body surrounded by the extended annular region based on the gradient magnitude and the gradient direction consistency index value includes: The region within the extended annular region that meets the set independent light emission classification conditions is determined as the independent light emission region of the light-emitting body surrounded by the extended annular region; The independent emission classification condition is defined as follows: the gradient magnitude is greater than the first classification threshold, and the gradient direction consistency index value is greater than the second classification threshold. The first classification threshold and the second classification threshold are preset.

10. The method as described in claim 1, characterized in that, The display panel further includes: a light-transmitting film covering the plurality of display units; and / or, The multiple display units are arranged in an interleaved or aligned array and spaced apart.

Images