WO2019024094A1 - Mura检测方法和Mura检测系统 - Google Patents

Mura检测方法和Mura检测系统 Download PDF

Info

Publication number
WO2019024094A1
WO2019024094A1 PCT/CN2017/096050 CN2017096050W WO2019024094A1 WO 2019024094 A1 WO2019024094 A1 WO 2019024094A1 CN 2017096050 W CN2017096050 W CN 2017096050W WO 2019024094 A1 WO2019024094 A1 WO 2019024094A1
Authority
WO
WIPO (PCT)
Prior art keywords
mura
image
captured image
detected
display panel
Prior art date
Application number
PCT/CN2017/096050
Other languages
English (en)
French (fr)
Inventor
朱广飞
黄顺宏
章勇
Original Assignee
深圳市柔宇科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市柔宇科技有限公司 filed Critical 深圳市柔宇科技有限公司
Priority to PCT/CN2017/096050 priority Critical patent/WO2019024094A1/zh
Priority to CN201780058735.1A priority patent/CN109791112A/zh
Publication of WO2019024094A1 publication Critical patent/WO2019024094A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination

Definitions

  • the present invention relates to the field of display technologies, and in particular, to a Mura detection method and a Mura detection system.
  • the probability of display unevenness (Mura) of the display panel is greatly increased, and the Mura detection of the display panel becomes a constraint to the development of the display panel industry. Key factor.
  • the Mura test mainly performs manual sampling on the display panel, and detects the Mura problem of the display panel through the human eye.
  • the detection result of this method is limited by the degree of occupational training and subjective judgment of the inspector, which may easily lead to problems such as missed detection and wrong inspection.
  • Embodiments of the present invention provide a Mura detection method and a Mura detection system.
  • comparing the captured image to the Mura image is implemented using a perceptual hashing algorithm.
  • comparing the captured image to a Mura image in a Mura image library comprises:
  • the comparison result including data of a fingerprint character string of the captured image and a fingerprint character string of the Mura image The number of bits.
  • determining, according to the result of the comparing, whether the display panel to be detected has a Mura includes:
  • the Mura detection method further includes:
  • the comparing the captured image with the Mura image is to compare a plurality of regions of the captured image with the Mura image.
  • the Mura image library includes a plurality of the Mura images, the comparing the captured image with a Mura image in a Mura image library by comparing the captured image to a plurality of the Mura images Compare separately.
  • the Mura detection method when it is determined that the display panel to be detected has a Mura, the Mura detection method further includes:
  • the type of Mura present in the to-be-detected display panel is determined based on a result of the comparison between the captured image and the plurality of the Mura images.
  • each of the Mura images has at least one Mura type
  • determining, according to a result of comparing the captured image with the plurality of the Mura images, respectively, determining a type of Mura in which the display panel to be detected exists includes :
  • the Mura type having the largest number is used as the kind of Mura in which the panel to be displayed is to be detected.
  • the Mura detection method further includes:
  • the captured image is uploaded to the Mura image library as a Mura image.
  • One or more processors are One or more processors;
  • One or more programs wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the program comprising instructions for performing the following steps:
  • comparing the captured image to the Mura image is implemented using a perceptual hashing algorithm.
  • comparing the captured image to a Mura image in a Mura image library comprises:
  • the comparison result including data of a fingerprint character string of the captured image and a fingerprint character string of the Mura image The number of bits.
  • determining, according to the result of the comparing, whether the display panel to be detected has a Mura includes:
  • the program further includes instructions for performing the following steps:
  • the comparing the captured image with the Mura image is to compare a plurality of regions of the captured image with the Mura image.
  • the Mura image library includes a plurality of the Mura images, the comparing the captured image with a Mura image in a Mura image library by comparing the captured image to a plurality of the Mura images Compare separately.
  • the program when it is determined that the display panel to be detected has Mura, the program further includes an instruction for performing the following steps:
  • the type of Mura present in the to-be-detected display panel is determined based on a result of the comparison between the captured image and the plurality of the Mura images.
  • each of the Mura images has at least one Mura type
  • determining, according to a result of comparing the captured image with the plurality of the Mura images, respectively, determining a type of Mura in which the display panel to be detected exists includes :
  • the Mura type having the largest number is used as the kind of Mura in which the panel to be displayed is to be detected.
  • the program further includes instructions for performing the following steps:
  • the captured image is uploaded to the Mura image library as a Mura image.
  • the Mura detecting method and the Mura detecting system determine whether the Mura to be detected exists in the display panel according to the comparison result between the captured image of the display panel to be detected and the Mura image in the Mura image library, the detection result is accurate, and the detection efficiency is high.
  • FIG. 1 is a schematic flow chart of a Mura detecting method according to an embodiment of the present invention.
  • FIG. 2 is a schematic block diagram of a Mura detection system according to an embodiment of the present invention.
  • FIG. 3 is a schematic flow chart of a Mura detecting method according to an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a 64-level grayscale captured image according to an embodiment of the present invention.
  • FIG. 5 is a schematic flow chart of a Mura detecting method according to an embodiment of the present invention.
  • FIG. 6 is a schematic flow chart of a Mura detecting method according to an embodiment of the present invention.
  • FIG. 7 is a schematic flow chart of a Mura detecting method according to an embodiment of the present invention.
  • FIG. 8 is a schematic diagram of application of a Mura detecting method according to an embodiment of the present invention.
  • FIG. 9 is a schematic flow chart of a Mura detecting method according to an embodiment of the present invention.
  • FIG. 10 is a schematic flow chart of a Mura detecting method according to an embodiment of the present invention.
  • the Mura detection system 100 the processor 10, and the memory 20.
  • first and second are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Or implicitly indicating the number of technical features indicated. Thus, features defining “first”, “second” may explicitly or implicitly include one or more of the features. In the description, “a plurality” means two or more, unless specifically defined otherwise.
  • connection should be understood broadly, and may be fixed connection, for example, or Removable connection, or integral connection; can be mechanical connection, electrical connection or communication with each other; can be direct connection or indirect connection through intermediate medium, can be internal connection of two components or two components Interaction relationship.
  • connection should be understood broadly, and may be fixed connection, for example, or Removable connection, or integral connection; can be mechanical connection, electrical connection or communication with each other; can be direct connection or indirect connection through intermediate medium, can be internal connection of two components or two components Interaction relationship.
  • the "on" or “below” of the second feature may include direct contact of the first and second features, and may also include the first sum, unless otherwise specifically defined and defined.
  • the second feature is not in direct contact but through additional features between them.
  • the first feature “above”, “above” and “above” the second feature includes the first feature directly above and above the second feature, or merely indicating that the first feature level is higher than the second feature.
  • the first feature “below”, “below” and “below” the second feature includes the first feature directly below and below the second feature, or merely the first feature level being less than the second feature.
  • a Mura detection method includes:
  • S30 Determine whether the Mura is to be detected on the display panel to be detected according to the result of the comparison.
  • the Mura detection method of the embodiment of the present invention can be implemented by the Mura detection system 100 of the embodiment of the present invention.
  • the Mura detection system 100 of an embodiment of the present invention includes one or more processors 10, Memory 20 and one or more programs, wherein one or more programs are stored in memory 20 and are configured to be executed by one or more processors 10.
  • the program includes instructions for performing the following steps:
  • S30 Determine whether the Mura is to be detected on the display panel to be detected according to the result of the comparison.
  • the Mura detecting method and the Mura detecting system 100 determine whether the Mura to be detected exists in the display panel according to the comparison result between the captured image of the display panel to be detected and the Mura image in the Mura image library, the detection result is accurate, and the detection efficiency is high.
  • the captured image of the display panel to be detected may be acquired by an image capturing device (such as a high-definition camera), and the Mura detecting system 100 acquires the captured image from the image capturing device; or the Mura detecting system 100 includes an image capturing device.
  • S10 is implemented directly by the image acquisition device of the Mura detection system 100.
  • the image capturing device can take a picture of each to-be-detected display panel in a vertical direction to make the captured image more standardized, and the Mura detecting system 100 can more easily determine whether the display panel has a Mura.
  • the Mura detection system 100 has a Mura image library established prior to performing the Mura detection.
  • the Mura Image Library is built for image acquisition, Mura classification and archiving of Mura generated by display panels during long-term production.
  • comparing the captured image to the Mura image is accomplished using a perceptual hashing algorithm.
  • the perceptual hash algorithm may generate a set of fingerprint strings according to the features included in each captured picture, and then compare the fingerprint string of the captured picture with the fingerprint string of the Mura image to determine whether the display panel to be detected is There is Mura.
  • the perceptual hash algorithm has the advantages of accurate detection results and high speed. When changing the height, width, brightness or color of the captured image, the fingerprint string of the captured image will not change.
  • S20 includes:
  • the predetermined size may be 8*8, and the predetermined level of gray may be 64 levels of gray.
  • the size of the captured image is generally larger, that is, larger than 8*8 size.
  • S21 reduces the captured image to a size of 8*8, a total of 64 pixels, to delete details in the image, and retains basic information such as structure, brightness, and the like, and removes due to different sizes and proportions. Image differences.
  • the captured image generally has 256 shades of gray, and the S22 converts the captured image of size 8*8 into 64 shades of gray, thereby simplifying the amount of calculation.
  • S23 calculates the gradation average value, that is, the gradation average value Gray_avg of Gray11, Gray12, Gray13, ..., Gray87, Gray88, based on the gradation value of each pixel of the captured image.
  • S24 compares the gray value of each pixel with the gray average value, that is, Gray11, Gray12, Gray13, ..., Gray87, Gray88 are respectively compared with Gray_avg, when the gray value of a certain pixel point is greater than or equal to gray
  • the average value is, for example, Gray11 ⁇ Gray_avg
  • the pixel is marked as 1
  • the gray value of a certain pixel is smaller than the gray average, for example, Gray12 ⁇ Gray_avg
  • the pixel is marked as 0.
  • the manner of generating the fingerprint string may be performed in a row-by-row order, or in a column-by-column order, or in any order, and only needs to ensure that the order of the fingerprint strings of each captured image is consistent, and The order of combination of the fingerprint strings of the Mura image is the same.
  • the S25 compares the fingerprint string of the captured image with the fingerprint string of the Mura image to obtain a comparison result, for example, the fingerprint string of the captured image is “111000...00101”, and the fingerprint string of the Mura image is “111001...00111”
  • the comparison result is the number of data bits of the fingerprint string of the captured image and the fingerprint string of the Mura image, in this example, the number of different data bits is 2 (assuming that the strings omitted in the middle are the same) . In this way, according to the size of the number of different data bits, it can be determined whether the display panel to be detected has Mura.
  • the specific working process of S20 is illustrated by taking a predetermined size of 8*8 and a predetermined level of grayscale as 64 gray levels as an example.
  • the values of the predetermined size and the predetermined level of gray may be selected and adjusted according to actual conditions and the experience of the engineers in the factory, and are not limited herein.
  • S30 includes:
  • the predetermined number may be 5, and when the number of data bits of the fingerprint string of the captured image and the fingerprint string of the Mura image is less than or equal to 5, indicating that the captured image is very similar to the Mura image, the display to be detected may be determined. There is a Mura in the panel; when the number of data bits of the fingerprint string of the captured image and the fingerprint string of the Mura image is greater than 5, indicating that the captured image and the Mura image are two different images, it can be determined that the display panel to be detected is not There is Mura.
  • the predetermined number of values may be set according to the type, size, and the like of the panel to be displayed, or may be set according to the experience value obtained by the production personnel during the long-term work, which is not limited herein.
  • the Mura detection method further includes:
  • comparing the captured image with the Mura image is to compare a plurality of regions of the captured image with the Mura image.
  • the program also includes instructions for performing the following steps:
  • comparing the captured image with the Mura image is to compare a plurality of regions of the captured image with the Mura image.
  • the Mura detecting method divides the captured image into a plurality of regions, and compares the plurality of regions with the Mura image at the same time to improve efficiency.
  • the Mura image library includes a plurality of Mura images, and S20 compares the captured image with a plurality of Mura images, respectively.
  • the Mura image library includes a plurality of Mura images, and the plurality of Mura images may contain the same or different types of Mura.
  • S20 compares the captured image with the plurality of Mura images, respectively, to more comprehensively determine whether or not the Mura is present on the display panel to be detected.
  • the Mura detection method when determining that there is a Mura in the display panel to be detected, the Mura detection method further includes:
  • S50 Determine the type of Mura present in the display panel to be detected according to the result of the comparison between the captured image and the plurality of Mura images.
  • the program when it is determined that the display panel to be detected has a Mura, the program further includes an instruction for performing the following steps:
  • S50 Determine the type of Mura present in the display panel to be detected according to the result of the comparison between the captured image and the plurality of Mura images.
  • the result of the comparison is that the captured image is similar to a certain Mura image
  • S50 determines that the type of Mura in which the captured image exists is the same as the Mura type that the Mura image has.
  • the result of the comparison is that the captured image is not similar to a certain Mura image
  • S50 determines that the type of Mura in which the captured image exists is different from the Mura type that the Mura image has.
  • the Mura types can be divided into dense text, small black dots, and V-Band.
  • the S20 will take images with Mura images with dense text, Mura images with small black dots, and V-Band with V-Band. The Mura images are compared.
  • the comparison result is that the captured image is similar to the Mura image with small black dots, and is not similar to the Mura image with dense text and the Mura image with V-Band, then S50 judges according to the result of the comparison.
  • the type of Mura present in the display panel is detected as a small black dot, and the reason for the Mura generation can be further traced, and the engineers of each process can be notified to perform the corresponding process improvement.
  • the track engineer can be notified; when the display panel to be detected is stored When the type of Mura is a small black dot, the Wet engineer can be notified; when the type of Mura to be detected on the display panel is V-Band, the PVD engineer can be notified.
  • each Mura image has at least one Mura type
  • S50 includes:
  • S51 recording a Mura type that can be used to determine a Mura image in which the display panel is to be detected to have Mura;
  • S52 The Mura type with the largest number is used as the kind of Mura to be detected for the panel to be displayed.
  • the result of the comparison may be that the captured image is similar to a plurality of Mura images, for example, a captured image and a Mura image with small black dots, a Mura image with intensive text, and The Mura images with V-Band are similar.
  • the similar numbers are three, two, and two.
  • S51 records the three black dots, dense text, and V-Band, and the images are small.
  • the Mura image of the black dot is the most similar, so S52 uses the small black dot as the kind of Mura in which the display panel to be detected exists.
  • the case where the captured image is similar to the plurality of Mura images is generally less likely to occur.
  • the engineer can be directly notified to perform manual detection to determine the type of Mura present in the display panel to be detected. .
  • the Mura detection method further includes:
  • the program also includes instructions for performing the following steps:
  • a "computer-readable medium” can be any apparatus that can contain, store, communicate, propagate, or transport a program for use in an instruction execution system, apparatus, or device, or in conjunction with the instruction execution system, apparatus, or device.
  • computer readable media include the following: electrical connections (IPM overcurrent protection circuits) with one or more wires, portable computer disk cartridges (magnetic devices), random access memories (RAM), read only memory (ROM), erasable editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM).
  • the computer readable medium may even be a paper or other suitable medium on which the program can be printed, as it may be optically scanned, for example by paper or other medium, followed by editing, interpretation or, if appropriate, other suitable The method is processed to obtain the program electronically and then stored in computer memory.
  • portions of the embodiments of the invention may be implemented in hardware, software, firmware or a combination thereof.
  • multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
  • a suitable instruction execution system For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or combination of the following techniques well known in the art: having logic gates for implementing logic functions on data signals. Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.
  • each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
  • the integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.
  • the above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like.

Landscapes

  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

一种Mura检测方法。Mura检测方法包括:(S10)获取待检测显示面板的拍摄图像;(S20)将拍摄图像与Mura图像库中的Mura图像进行比较;和(S30)根据比较的结果判断待检测显示面板是否存在Mura。此外,还公开了一种Mura检测系统(100)。

Description

Mura检测方法和Mura检测系统 技术领域
本发明涉及显示技术领域,特别涉及一种Mura检测方法和Mura检测系统。
背景技术
随着显示面板向大尺寸、轻薄化、低功耗、高分辨率的方向发展,显示面板的显示不均匀缺陷(Mura)产生的几率大大增加,显示面板的Mura检测成为制约显示面板产业发展的重要因素。目前,Mura检测主要是人工对显示面板进行抽检,通过人眼检测显示面板的Mura问题。然而,这种方式检测结果受检测员的职业受训程度和主观判断的限制,容易导致漏检、错检等问题发生。
发明内容
本发明实施方式提供一种Mura检测方法和Mura检测系统。
本发明实施方式的Mura检测方法,包括:
获取待检测显示面板的拍摄图像;
将所述拍摄图像与Mura图像库中的Mura图像进行比较;和
根据所述比较的结果判断所述待检测显示面板是否存在Mura。
在某些实施方式中,将所述拍摄图像与所述Mura图像进行比较是采用感知哈希算法来实现的。
在某些实施方式中,所述将所述拍摄图像与Mura图像库中的Mura图像进行比较包括:
处理所述拍摄图像以使其尺寸为预定尺寸;
将所述预定尺寸的所述拍摄图像转化为预定级灰度;
计算转化为所述预定级灰度的所述拍摄图像的灰度平均值;
将所述拍摄图像每个像素点的灰度值与所述灰度平均值进行比较,以生成所述拍摄图像的指纹字符串;和
将所述拍摄图像的指纹字符串与所述Mura图像的指纹字符串进行比较以得到比较结果,所述比较结果包括所述拍摄图像的指纹字符串与所述Mura图像的指纹字符串不同的数据位的个数。
在某些实施方式中,所述根据所述比较的结果判断所述待检测显示面板是否存在Mura包括:
当所述个数小于或等于预定数量时,确定所述待检测显示面板存在Mura;和
当所述个数大于所述预定数量时,确定所述待检测显示面板不存在Mura。
在某些实施方式中,所述Mura检测方法还包括:
将所述拍摄图像划分为多个区域;
其中,将所述拍摄图像与所述Mura图像进行比较是将所述拍摄图像的多个区域分别与所述Mura图像进行比较。
在某些实施方式中,所述Mura图像库包括多个所述Mura图像,所述将所述拍摄图像与Mura图像库中的Mura图像进行比较是将所述拍摄图像与多个所述Mura图像分别比较。
在某些实施方式中,在判断所述待检测显示面板存在Mura时,所述Mura检测方法还包括:
根据所述拍摄图像与多个所述Mura图像分别比较的结果判断所述待检测显示面板存在的Mura的种类。
在某些实施方式中,每个所述Mura图像具有至少一个Mura种类,所述根据所述拍摄图像与多个所述Mura图像分别比较的结果判断所述待检测显示面板存在的Mura的种类包括:
记录能够用于确定所述待检测显示面板存在Mura的所述Mura图像的Mura种类;和
将数量最多的Mura种类作为所述待检测待显示面板存在的Mura的种类。
在某些实施方式中,所述Mura检测方法还包括:
在判断所述待检测显示面板存在Mura时,将所述拍摄图像上传至所述Mura图像库以作为Mura图像。
本发明实施方式的Mura检测系统,包括:
一个或多个处理器;
存储器;和
一个或多个程序,其中所述一个或多个程序被存储在所述存储器中,并且被配置成由所述一个或多个处理器执行,所述程序包括用于执行以下步骤的指令:
获取待检测显示面板的拍摄图像;
将所述拍摄图像与Mura图像库中的Mura图像进行比较;和
根据所述比较的结果判断所述待检测显示面板是否存在Mura。
在某些实施方式中,将所述拍摄图像与所述Mura图像进行比较是采用感知哈希算法来实现的。
在某些实施方式中,所述将所述拍摄图像与Mura图像库中的Mura图像进行比较包括:
处理所述拍摄图像以使其尺寸为预定尺寸;
将所述预定尺寸的所述拍摄图像转化为预定级灰度;
计算转化为所述预定级灰度的所述拍摄图像的灰度平均值;
将所述拍摄图像每个像素点的灰度值与所述灰度平均值进行比较,以生成所述拍摄图像的指纹字符串;和
将所述拍摄图像的指纹字符串与所述Mura图像的指纹字符串进行比较以得到比较结果,所述比较结果包括所述拍摄图像的指纹字符串与所述Mura图像的指纹字符串不同的数据位的个数。
在某些实施方式中,所述根据所述比较的结果判断所述待检测显示面板是否存在Mura包括:
当所述个数小于或等于预定数量时,确定所述待检测显示面板存在Mura;和
当所述个数大于所述预定数量时,确定所述待检测显示面板不存在Mura。
在某些实施方式中,所述程序还包括用于执行以下步骤的指令:
将所述拍摄图像划分为多个区域;
其中,将所述拍摄图像与所述Mura图像进行比较是将所述拍摄图像的多个区域分别与所述Mura图像进行比较。
在某些实施方式中,所述Mura图像库包括多个所述Mura图像,所述将所述拍摄图像与Mura图像库中的Mura图像进行比较是将所述拍摄图像与多个所述Mura图像分别比较。
在某些实施方式中,在判断所述待检测显示面板存在Mura时,所述程序还包括用于执行以下步骤的指令:
根据所述拍摄图像与多个所述Mura图像分别比较的结果判断所述待检测显示面板存在的Mura的种类。
在某些实施方式中,每个所述Mura图像具有至少一个Mura种类,所述根据所述拍摄图像与多个所述Mura图像分别比较的结果判断所述待检测显示面板存在的Mura的种类包括:
记录能够用于确定所述待检测显示面板存在Mura的所述Mura图像的Mura种类;和
将数量最多的Mura种类作为所述待检测待显示面板存在的Mura的种类。
在某些实施方式中,所述程序还包括用于执行以下步骤的指令:
在判断所述待检测显示面板存在Mura时,将所述拍摄图像上传至所述Mura图像库以作为Mura图像。
本发明实施方式的Mura检测方法和Mura检测系统,根据待检测显示面板的拍摄图像与Mura图像库中的Mura图像的比较结果判断待检测显示面板是否存在Mura,检测结果准确,检测效率高。
本发明实施方式的附加方面和优点将在下面的描述中部分给出,部分将从下面的描述中变得明显,或通过本发明的实践了解到。
附图说明
本发明的上述和/或附加的方面和优点可以从结合下面附图对实施方式的描述中将变得明显和容易理解,其中:
图1是本发明实施方式的Mura检测方法的流程示意图;
图2是本发明实施方式的Mura检测系统的模块示意图;
图3是本发明实施方式的Mura检测方法的流程示意图;
图4是本发明实施方式的64级灰度的拍摄图像的示意图;
图5是本发明实施方式的Mura检测方法的流程示意图;
图6是本发明实施方式的Mura检测方法的流程示意图;
图7是本发明实施方式的Mura检测方法的流程示意图;
图8是本发明实施方式的Mura检测方法的应用示意图;
图9是本发明实施方式的Mura检测方法的流程示意图;
图10是本发明实施方式的Mura检测方法的流程示意图;
主要元件及符号说明:
Mura检测系统100、处理器10、存储器20。
具体实施方式
下面详细描述本发明的实施方式,所述实施方式的示例在附图中示出,其中,相同或类似的标号自始至终表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施方式是示例性的,仅用于解释本发明的实施方式,而不能理解为对本发明的实施方式的限制。
在本发明的实施方式的描述中,需要理解的是,术语“中心”、“纵向”、“横向”、“长度”、“宽度”、“厚度”、“上”、“下”、“前”、“后”、“左”、“右”、“竖直”、“水平”、“顶”、“底”、“内”、“外”、“顺时针”、“逆 时针”等指示的方位或位置关系为基于附图所示的方位或位置关系,仅是为了便于描述本发明的实施方式和简化描述,而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作,因此不能理解为对本发明的实施方式的限制。此外,术语“第一”、“第二”仅用于描述目的,而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此,限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个所述特征。在本发明的实施方式的描述中,“多个”的含义是两个或两个以上,除非另有明确具体的限定。
在本发明的实施方式的描述中,需要说明的是,除非另有明确的规定和限定,术语“安装”、“连接”、“连接”应做广义理解,例如,可以是固定连接,也可以是可拆卸连接,或一体地连接;可以是机械连接,也可以是电连接或可以相互通讯;可以是直接连接,也可以通过中间媒介间接连接,可以是两个元件内部的连通或两个元件的相互作用关系。对于本领域的普通技术人员而言,可以根据具体情况理解上述术语在本发明的实施方式中的具体含义。
在本发明的实施方式中,除非另有明确的规定和限定,第一特征在第二特征之“上”或之“下”可以包括第一和第二特征直接接触,也可以包括第一和第二特征不是直接接触而是通过它们之间的另外的特征接触。而且,第一特征在第二特征“之上”、“上方”和“上面”包括第一特征在第二特征正上方和斜上方,或仅仅表示第一特征水平高度高于第二特征。第一特征在第二特征“之下”、“下方”和“下面”包括第一特征在第二特征正下方和斜下方,或仅仅表示第一特征水平高度小于第二特征。
下文的公开提供了许多不同的实施方式或例子用来实现本发明的实施方式的不同结构。为了简化本发明的实施方式的公开,下文中对特定例子的部件和设置进行描述。当然,它们仅仅为示例,并且目的不在于限制本发明。此外,本发明的实施方式可以在不同例子中重复参考数字和/或参考字母,这种重复是为了简化和清楚的目的,其本身不指示所讨论各种实施方式和/或设置之间的关系。此外,本发明的实施方式提供了的各种特定的工艺和材料的例子,但是本领域普通技术人员可以意识到其他工艺的应用和/或其他材料的使用。
请参阅图1,本发明实施方式的Mura检测方法,包括:
S10:获取待检测显示面板的拍摄图像;
S20:将拍摄图像与Mura图像库中的Mura图像进行比较;和
S30:根据比较的结果判断待检测显示面板是否存在Mura。
请参阅图2,本发明实施方式的Mura检测方法可以由本发明实施方式的Mura检测系统100实现。本发明实施方式的Mura检测系统100包括一个或多个处理器10、 存储器20和一个或多个程序,其中,一个或多个程序被存储在存储器20中,并且被配置成由一个或多个处理器10执行。程序包括用于执行以下步骤的指令:
S10:获取待检测显示面板的拍摄图像;
S20:将拍摄图像与Mura图像库中的Mura图像进行比较;和
S30:根据比较的结果判断待检测显示面板是否存在Mura。
本发明实施方式的Mura检测方法和Mura检测系统100,根据待检测显示面板的拍摄图像与Mura图像库中的Mura图像的比较结果判断待检测显示面板是否存在Mura,检测结果准确,检测效率高。
具体地,在S10前,待检测显示面板的拍摄图像可由图像采集装置(如高清相机)采集得到,Mura检测系统100从图像采集装置处获取该拍摄图像;或者Mura检测系统100包括图像采集装置,S10直接由Mura检测系统100的图像采集装置实现。其中,图像采集装置可以在垂直方向对每个待检测显示面板进行拍照,以使得拍摄图像更为规范,Mura检测系统100更易判断出待检测显示面板是否存在Mura。
可以理解,Mura检测系统100在进行Mura检测前建立有Mura图像库。Mura图像库是对长期生产过程中显示面板产生的Mura进行图像采集、Mura分类和存档来建立的。
在某些实施方式中,将拍摄图像与Mura图像进行比较是采用感知哈希算法来实现的。
具体地,感知哈希算法可以根据每张拍摄图片所包含的特征来生成一组指纹字符串,然后将拍摄图片的指纹字符串与Mura图像的指纹字符串进行比较,以判断待检测显示面板是否存在Mura。感知哈希算法具有检测结果准确、速度快的优点,当改变拍摄图像的高宽、亮度或颜色等,拍摄图像的指纹字符串都不会改变。
请参阅图3和图4,在某些实施方式中,S20包括:
S21:处理拍摄图像以使其尺寸为预定尺寸;
S22:将预定尺寸的拍摄图像转化为预定级灰度;
S23:计算转化为预定级灰度的拍摄图像的灰度平均值;
S24:将拍摄图像每个像素点的灰度值与灰度平均值进行比较,以生成拍摄图像的指纹字符串;和
S25:将拍摄图像的指纹字符串与Mura图像的指纹字符串进行比较以得到比较结果,比较结果包括拍摄图像的指纹字符串与Mura图像的指纹字符串不同的数据位的个数。
例如,预定尺寸可以为8*8,预定级灰度可以为64级灰度。
可以理解,拍摄图像的尺寸一般较大,即大于8*8尺寸。在某些实施方式中,S21将拍摄图像缩小到8*8的尺寸,共64个像素,以删除图像中的细节,保留结构、明暗等基本信息,去除由于不同的尺寸、比例所带来的图像差异。拍摄图像一般具有256级灰度,S22将尺寸为8*8的拍摄图像转化为64级灰度,从而简化运算量。S23根据拍摄图像的每个像素点的灰度值计算灰度平均值,即Gray11、Gray12、Gray13、……、Gray87、Gray88的灰度平均值Gray_avg。S24将每个像素点的灰度值与灰度平均值进行比较,即将Gray11、Gray12、Gray13、……、Gray87、Gray88分别与Gray_avg进行比较,当某个像素点的灰度值大于或等于灰度平均值时,例如,Gray11≥Gray_avg,则将该像素点标记为1,当某个像素点的灰度值小于灰度平均值时,例如,Gray12<Gray_avg,则将该像素点标记为0,最后将这些标记值组合以生成拍摄图像的指纹字符串。具体地,生成指纹字符串的方式可以是逐行的顺序进行组合,或逐列的顺序进行组合,或者任意顺序进行组合,只需要保证每张拍摄图像的指纹字符串的组合顺序一致,并与Mura图像的指纹字符串的组合顺序一致即可。S25将拍摄图像的指纹字符串与Mura图像的指纹字符串进行比较以得到比较结果,例如拍摄图像的指纹字符串为“111000……00101”,Mura图像的指纹字符串为“111001……00111”时,比较结果为拍摄图像的指纹字符串与Mura图像的指纹字符串不同的数据位的个数,在该例子中,不同数据位的个数为2(假设中间省略的字符串是相同的)。如此,根据不同数据位的个数的大小可以判断待检测显示面板是否存在Mura。
需要指出的是,在本发明实施方式中,以预定尺寸为8*8,预定级灰度为64级灰度为例来说明S20的具体工作流程。在其他例子中,预定尺寸和预定级灰度的值可以根据实际情况和厂内工程师的经验等因素进行选择和调整,这里不作限制。
请参阅图5,在某些实施方式中,S30包括:
S31:当个数小于或等于预定数量时,确定待检测显示面板存在Mura;和
S32:当个数大于预定数量时,确定待检测显示面板不存在Mura。
例如,预定数量可以为5,当拍摄图像的指纹字符串与Mura图像的指纹字符串不同的数据位的个数小于或等于5时,表明拍摄图像与Mura图像十分相似,则可以确定待检测显示面板存在Mura;当拍摄图像的指纹字符串与Mura图像的指纹字符串不同的数据位的个数大于5时,表明拍摄图像与Mura图像为两张不同的图像,则可以确定待检测显示面板不存在Mura。其中,预定数量的值可以根据待显示面板的种类、尺寸等进行设置,也可以根据生产人员在长期工作过程中得到的经验值进行设置,这里不作限制。
请参阅图6,在某些实施方式中,Mura检测方法还包括:
S40:将拍摄图像划分为多个区域;
其中,将拍摄图像与Mura图像进行比较是将拍摄图像的多个区域分别与Mura图像进行比较。
在某些实施方式中,程序还包括用于执行以下步骤的指令:
S40:将拍摄图像划分为多个区域;
其中,将拍摄图像与Mura图像进行比较是将拍摄图像的多个区域分别与Mura图像进行比较。
如此,当待显示面板的拍摄图像的尺寸较大时,Mura检测方法将拍摄图像划分为多个区域,并将多个区域分别与Mura图像同时进行比较,以提高效率。
在某些实施方式中,Mura图像库包括多个Mura图像,S20是将拍摄图像与多个Mura图像分别比较。
可以理解,Mura图像库包括多个Mura图像,多个Mura图像包含的Mura的种类可以相同或不同。S20将拍摄图像与多个Mura图像分别进行比较,以更全面地判断出待检测显示面板是否存在Mura。
请参阅图7,在某些实施方式中,在判断待检测显示面板存在Mura时,Mura检测方法还包括:
S50:根据拍摄图像与多个Mura图像分别比较的结果判断待检测显示面板存在的Mura的种类。
在某些实施方式中,在判断待检测显示面板存在Mura时,程序还包括用于执行以下步骤的指令:
S50:根据拍摄图像与多个Mura图像分别比较的结果判断待检测显示面板存在的Mura的种类。
具体地,当比较的结果为拍摄图像与某个Mura图像相似时,则S50确定拍摄图像存在的Mura的种类与该Mura图像具有的Mura种类相同。当比较的结果为拍摄图像与某个Mura图像不相似时,则S50确定拍摄图像存在的Mura的种类与该Mura图像具有的Mura种类不同。例如,请参阅图8,Mura种类可分为密集文、小黑点和V-Band等,S20分别将拍摄图像与具有密集文的Mura图像、具有小黑点的Mura图像和具有V-Band的Mura图像进行比较,当比较的结果为拍摄图像与具有小黑点的Mura图像相似,而与具有密集文的Mura图像和具有V-Band的Mura图像不相似时,则S50根据比较的结果判断待检测显示面板存在的Mura的种类为小黑点,并进一步可以由此追溯Mura产生的原因,以及通知各制程的工程师进行相应制程的改善。例如,当待检测显示面板存在的Mura的种类为密集文时,可以通知Track工程师;当待检测显示面板存 在的Mura的种类为小黑点时,可以通知Wet工程师;当待检测显示面板存在的Mura的种类为V-Band时,可以通知PVD工程师。
请参阅图9,在某些实施方式中,每个Mura图像具有至少一个Mura种类,S50包括:
S51:记录能够用于确定待检测显示面板存在Mura的Mura图像的Mura种类;
S52:将数量最多的Mura种类作为待检测待显示面板存在的Mura的种类。
可以理解,具有同一Mura种类的Mura图像的可能有多个,比较的结果可能为拍摄图像与多个Mura图像相似,例如,拍摄图像与具有小黑点的Mura图像、具有密集文的Mura图像和具有V-Band的Mura图像都相似,相似的数量分别为三个、两个、两个,则S51将小黑点、密集文、V-Band这三个种类记录下来,而拍摄图像与具有小黑点的Mura图像相似的数量最多,因此S52将小黑点作为待检测显示面板存在的Mura的种类。
可以理解,拍摄图像与多个Mura图像相似的情况一般较少出现,当出现拍摄图像与多个Mura图像相似时,也可以直接通知工程师来进行人工检测以判断待检测显示面板存在的Mura的种类。
请参阅图10,在某些实施方式中,Mura检测方法还包括:
S60:在判断待检测显示面板存在Mura时,将拍摄图像上传至Mura图像库以作为Mura图像。
在某些实施方式中,程序还包括用于执行以下步骤的指令:
S60:在判断待检测显示面板存在Mura时,将拍摄图像上传至Mura图像库以作为Mura图像。
如此,Mura图像库将不断扩大和完善,待检测显示面板的Mura的检测结果将更加准确。
在本说明书的描述中,参考术语“一个实施方式”、“一些实施方式”、“示意性实施方式”、“示例”、“具体示例”或“一些示例”等的描述意指结合所述实施方式或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施方式或示例中。在本说明书中,对上述术语的示意性表述不一定指的是相同的实施方式或示例。而且,描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施方式或示例中以合适的方式结合。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为,表示包括一个或更多个用于实现特定逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分,并且本发明的优选实施方式的范围包括另外的实现,其中可以不按所示出或 讨论的顺序,包括根据所涉及的功能按基本同时的方式或按相反的顺序,来执行功能,这应被本发明的实施例所属技术领域的技术人员所理解。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤,例如,可以被认为是用于实现逻辑功能的可执行指令的定序列表,可以具体实现在任何计算机可读介质中,以供指令执行系统、装置或设备(如基于计算机的系统、包括处理模块的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用,或结合这些指令执行系统、装置或设备而使用。就本说明书而言,"计算机可读介质"可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下:具有一个或多个布线的电连接部(IPM过流保护电路),便携式计算机盘盒(磁装置),随机存取存储器(RAM),只读存储器(ROM),可擦除可编辑只读存储器(EPROM或闪速存储器),光纤装置,以及便携式光盘只读存储器(CDROM)。另外,计算机可读介质甚至可以是可在其上打印所述程序的纸或其他合适的介质,因为可以例如通过对纸或其他介质进行光学扫描,接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序,然后将其存储在计算机存储器中。
应当理解,本发明的实施方式的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中,多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。例如,如果用硬件来实现,和在另一实施方式中一样,可用本领域公知的下列技术中的任一项或他们的组合来实现:具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路,具有合适的组合逻辑门电路的专用集成电路,可编程门阵列(PGA),现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成,所述的程序可以存储于一种计算机可读存储介质中,该程序在执行时,包括方法实施例的步骤之一或其组合。
此外,在本发明的各个实施例中的各功能单元可以集成在一个处理模块中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现,也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时,也可以存储在一个计算机可读取存储介质中。
上述提到的存储介质可以是只读存储器,磁盘或光盘等。
尽管上面已经示出和描述了本发明的实施方式,可以理解的是,上述实施方式是示例性的,不能理解为对本发明的限制,本领域的普通技术人员在本发明的范围内可以对上述实施实施进行变化、修改、替换和变型。

Claims (18)

  1. 一种Mura检测方法,其特征在于,包括:
    获取待检测显示面板的拍摄图像;
    将所述拍摄图像与Mura图像库中的Mura图像进行比较;和
    根据所述比较的结果判断所述待检测显示面板是否存在Mura。
  2. 根据权利要求1所述的Mura检测方法,其特征在于,将所述拍摄图像与所述Mura图像进行比较是采用感知哈希算法来实现的。
  3. 根据权利要求1所述的Mura检测方法,其特征在于,所述将所述拍摄图像与Mura图像库中的Mura图像进行比较包括:
    处理所述拍摄图像以使其尺寸为预定尺寸;
    将所述预定尺寸的所述拍摄图像转化为预定级灰度;
    计算转化为所述预定级灰度的所述拍摄图像的灰度平均值;
    将所述拍摄图像每个像素点的灰度值与所述灰度平均值进行比较,以生成所述拍摄图像的指纹字符串;和
    将所述拍摄图像的指纹字符串与所述Mura图像的指纹字符串进行比较以得到比较结果,所述比较结果包括所述拍摄图像的指纹字符串与所述Mura图像的指纹字符串不同的数据位的个数。
  4. 根据权利要求3所述的Mura检测方法,其特征在于,所述根据所述比较的结果判断所述待检测显示面板是否存在Mura包括:
    当所述个数小于或等于预定数量时,确定所述待检测显示面板存在Mura;和
    当所述个数大于所述预定数量时,确定所述待检测显示面板不存在Mura。
  5. 根据权利要求1所述的Mura检测方法,其特征在于,所述Mura检测方法还包括:
    将所述拍摄图像划分为多个区域;
    其中,将所述拍摄图像与所述Mura图像进行比较是将所述拍摄图像的多个区域分别与所述Mura图像进行比较。
  6. 根据权利要求1所述的Mura检测方法,其特征在于,所述Mura图像库包括多个所述Mura图像,所述将所述拍摄图像与Mura图像库中的Mura图像进行比较是将所述拍摄图像与多个所述Mura图像分别比较。
  7. 根据权利要求6所述的Mura检测方法,其特征在于,在判断所述待检测显示面板存在Mura时,所述Mura检测方法还包括:
    根据所述拍摄图像与多个所述Mura图像分别比较的结果判断所述待检测显示面板存在的Mura的种类。
  8. 根据权利要求7所述的Mura检测方法,其特征在于,每个所述Mura图像具有至少一个Mura种类,所述根据所述拍摄图像与多个所述Mura图像分别比较的结果判断所述待检测显示面板存在的Mura的种类包括:
    记录能够用于确定所述待检测显示面板存在Mura的所述Mura图像的Mura种类;和
    将数量最多的Mura种类作为所述待检测待显示面板存在的Mura的种类。
  9. 根据权利要求1所述的Mura检测方法,其特征在于,所述Mura检测方法还包括:
    在判断所述待检测显示面板存在Mura时,将所述拍摄图像上传至所述Mura图像库以作为Mura图像。
  10. 一种Mura检测系统,其特征在于,包括:
    一个或多个处理器;
    存储器;和
    一个或多个程序,其中所述一个或多个程序被存储在所述存储器中,并且被配置成由所述一个或多个处理器执行,所述程序包括用于执行以下步骤的指令:
    获取待检测显示面板的拍摄图像;
    将所述拍摄图像与Mura图像库中的Mura图像进行比较;和
    根据所述比较的结果判断所述待检测显示面板是否存在Mura。
  11. 根据权利要求10所述的Mura检测系统,其特征在于,将所述拍摄图像与所述Mura图像进行比较是采用感知哈希算法来实现的。
  12. 根据权利要求10所述的Mura检测系统,其特征在于,所述将所述拍摄图像与Mura图像库中的Mura图像进行比较包括:
    处理所述拍摄图像以使其尺寸为预定尺寸;
    将所述预定尺寸的所述拍摄图像转化为预定级灰度;
    计算转化为所述预定级灰度的所述拍摄图像的灰度平均值;
    将所述拍摄图像每个像素点的灰度值与所述灰度平均值进行比较,以生成所述拍摄图像的指纹字符串;和
    将所述拍摄图像的指纹字符串与所述Mura图像的指纹字符串进行比较以得到比较结果,所述比较结果包括所述拍摄图像的指纹字符串与所述Mura图像的指纹字符串不同的数据位的个数。
  13. 根据权利要求12所述的Mura检测系统,其特征在于,所述根据所述比较的结果判断所述待检测显示面板是否存在Mura包括:
    当所述个数小于或等于预定数量时,确定所述待检测显示面板存在Mura;和
    当所述个数大于所述预定数量时,确定所述待检测显示面板不存在Mura。
  14. 根据权利要求10所述的Mura检测系统,其特征在于,所述程序还包括用于执行以下步骤的指令:
    将所述拍摄图像划分为多个区域;
    其中,将所述拍摄图像与所述Mura图像进行比较是将所述拍摄图像的多个区域分别与所述Mura图像进行比较。
  15. 根据权利要求10所述的Mura检测系统,其特征在于,所述Mura图像库包括多个所述Mura图像,所述将所述拍摄图像与Mura图像库中的Mura图像进行比较是将所述拍摄图像与多个所述Mura图像分别比较。
  16. 根据权利要求15所述的Mura检测系统,其特征在于,在判断所述待检测显示面板存在Mura时,所述程序还包括用于执行以下步骤的指令:
    根据所述拍摄图像与多个所述Mura图像分别比较的结果判断所述待检测显示面板存在的Mura的种类。
  17. 根据权利要求16所述的Mura检测系统,其特征在于,每个所述Mura图像具有至少一个Mura种类,所述根据所述拍摄图像与多个所述Mura图像分别比较的结果判断所述待检测显示面板存在的Mura的种类包括:
    记录能够用于确定所述待检测显示面板存在Mura的所述Mura图像的Mura种类;和
    将数量最多的Mura种类作为所述待检测待显示面板存在的Mura的种类。
  18. 根据权利要求10所述的Mura检测系统,其特征在于,所述程序还包括用于执行以下步骤的指令:
    在判断所述待检测显示面板存在Mura时,将所述拍摄图像上传至所述Mura图像库以作为Mura图像。
PCT/CN2017/096050 2017-08-04 2017-08-04 Mura检测方法和Mura检测系统 WO2019024094A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2017/096050 WO2019024094A1 (zh) 2017-08-04 2017-08-04 Mura检测方法和Mura检测系统
CN201780058735.1A CN109791112A (zh) 2017-08-04 2017-08-04 Mura检测方法和Mura检测系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/096050 WO2019024094A1 (zh) 2017-08-04 2017-08-04 Mura检测方法和Mura检测系统

Publications (1)

Publication Number Publication Date
WO2019024094A1 true WO2019024094A1 (zh) 2019-02-07

Family

ID=65233335

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/096050 WO2019024094A1 (zh) 2017-08-04 2017-08-04 Mura检测方法和Mura检测系统

Country Status (2)

Country Link
CN (1) CN109791112A (zh)
WO (1) WO2019024094A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111179795A (zh) * 2020-02-19 2020-05-19 京东方科技集团股份有限公司 显示面板的检测方法及其装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20080060469A (ko) * 2006-12-27 2008-07-02 엘지디스플레이 주식회사 무라 검출장치 및 그의 구동방법
US20100188412A1 (en) * 2009-01-28 2010-07-29 Microsoft Corporation Content based cache for graphics resource management
CN101840078A (zh) * 2009-03-20 2010-09-22 北京京东方光电科技有限公司 水波纹级别测试方法
CN103558229A (zh) * 2013-11-25 2014-02-05 苏州富鑫林光电科技有限公司 一种tft-lcd制程的mura视觉自动检测方法及装置
CN105069042A (zh) * 2015-07-23 2015-11-18 北京航空航天大学 基于内容的无人机侦察图像数据检索方法
CN106383124A (zh) * 2016-08-30 2017-02-08 四川石棉华瑞电子有限公司 电容铝箔表面缺陷视觉在线检查系统及方法

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100454006C (zh) * 2006-09-07 2009-01-21 哈尔滨工业大学 一种基于机器视觉的液晶显示器斑痕缺陷检测方法与系统
US8026927B2 (en) * 2007-03-29 2011-09-27 Sharp Laboratories Of America, Inc. Reduction of mura effects
CN105158942B (zh) * 2015-09-24 2018-07-06 昆山龙腾光电有限公司 一种Mura自动检测方法及系统
CN105380590B (zh) * 2015-10-27 2017-11-07 杭州镜之镜科技有限公司 一种具有眼位检测功能的设备及其实现方法
KR102519371B1 (ko) * 2016-01-20 2023-04-10 삼성디스플레이 주식회사 Ela 얼룩 보상 방법 및 이를 채용한 표시 장치
CN105589230B (zh) * 2016-03-09 2018-10-26 深圳市华星光电技术有限公司 面板标记侦测方法及面板标记区域的Mura补偿方法
CN105845062A (zh) * 2016-03-31 2016-08-10 京东方科技集团股份有限公司 检测显示面板的方法及系统和显示面板的批量检测方法
CN105913419B (zh) * 2016-04-07 2018-07-17 南京汇川图像视觉技术有限公司 基于ICA学习和多通道融合的TFT-LCD mura缺陷检测方法
CN106126574A (zh) * 2016-06-16 2016-11-16 深圳市矽伟智科技有限公司 图片的识别方法、系统及物联网摄像设备
CN106157310B (zh) * 2016-07-06 2018-09-14 南京汇川图像视觉技术有限公司 基于混合自适应水平集模型与多通道结合的TFT LCD mura缺陷检测方法
CN106650770B (zh) * 2016-09-29 2019-12-17 南京大学 一种基于样本学习和人眼视觉特性的mura缺陷检测方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20080060469A (ko) * 2006-12-27 2008-07-02 엘지디스플레이 주식회사 무라 검출장치 및 그의 구동방법
US20100188412A1 (en) * 2009-01-28 2010-07-29 Microsoft Corporation Content based cache for graphics resource management
CN101840078A (zh) * 2009-03-20 2010-09-22 北京京东方光电科技有限公司 水波纹级别测试方法
CN103558229A (zh) * 2013-11-25 2014-02-05 苏州富鑫林光电科技有限公司 一种tft-lcd制程的mura视觉自动检测方法及装置
CN105069042A (zh) * 2015-07-23 2015-11-18 北京航空航天大学 基于内容的无人机侦察图像数据检索方法
CN106383124A (zh) * 2016-08-30 2017-02-08 四川石棉华瑞电子有限公司 电容铝箔表面缺陷视觉在线检查系统及方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111179795A (zh) * 2020-02-19 2020-05-19 京东方科技集团股份有限公司 显示面板的检测方法及其装置
CN111179795B (zh) * 2020-02-19 2023-07-21 京东方科技集团股份有限公司 显示面板的检测方法及其装置

Also Published As

Publication number Publication date
CN109791112A (zh) 2019-05-21

Similar Documents

Publication Publication Date Title
US10672115B2 (en) Weakly supervised anomaly detection and segmentation in images
KR20230124713A (ko) 결함 검출 방법, 장치 및 시스템
US8599270B2 (en) Computing device, storage medium and method for identifying differences between two images
US8289397B2 (en) System and method for testing a digital camera module
KR101174105B1 (ko) 비접촉식 구조물 변위 측정용 파라미터 데이터 생성 방법
TW201317904A (zh) 標籤檢測系統、裝置及其檢測標籤的方法
JP2012142935A (ja) 夜景光源検知装置及び夜景光源検知方法
JP5242248B2 (ja) 欠陥検出装置、欠陥検出方法、欠陥検出プログラム、及び、記録媒体
CN109191386B (zh) 一种基于BPNN的快速Gamma校正方法及装置
US8803998B2 (en) Image optimization system and method for optimizing images
JPWO2014013792A1 (ja) ノイズ評価方法、画像処理装置、撮像装置およびプログラム
US8547430B2 (en) System and method for marking discrepancies in image of object
US9823122B2 (en) Computing device and method for detecting lightness of lighting device
CN113362270A (zh) 显示屏画面显示异常监测方法及其装置
JP2020155128A (ja) シンボルを評価するためのシステムおよび方法
JP7410323B2 (ja) 異常検出装置、異常検出方法及び異常検出システム
WO2019024094A1 (zh) Mura检测方法和Mura检测系统
CN110288557A (zh) 一种红外图像修复方法、装置、设备及可读存储介质
CN116862810A (zh) 亮度调节方法和装置
JP2009038666A (ja) フリッカ補正装置及びフリッカ補正方法
JP2015108522A (ja) 検査装置、検査方法及び検査プログラム
CN112734719B (zh) 一种图像传感器的坏点检测方法、存储介质以及拍摄装置
CN110991361B (zh) 面向高清高速视频的多通道多模态背景建模方法
CN110672631B (zh) 面板缺陷拍照方法和面板缺陷拍照装置
JP7340487B2 (ja) プログラム作成装置、対象物検知システム、アンカー設定方法及びアンカー設定プログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17920034

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17920034

Country of ref document: EP

Kind code of ref document: A1