WO2014134880A1 - 背光模组瑕疵的检测方法及设备 - Google Patents

背光模组瑕疵的检测方法及设备 Download PDF

Info

Publication number
WO2014134880A1
WO2014134880A1 PCT/CN2013/076536 CN2013076536W WO2014134880A1 WO 2014134880 A1 WO2014134880 A1 WO 2014134880A1 CN 2013076536 W CN2013076536 W CN 2013076536W WO 2014134880 A1 WO2014134880 A1 WO 2014134880A1
Authority
WO
WIPO (PCT)
Prior art keywords
backlight module
image
component
detection
defect
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2013/076536
Other languages
English (en)
French (fr)
Inventor
严志伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
BOE Technology Group Co Ltd
BOE Optical Science and Technology Co Ltd
Original Assignee
BOE Technology Group Co Ltd
BOE Optical Science and Technology Co Ltd
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 BOE Technology Group Co Ltd, BOE Optical Science and Technology Co Ltd filed Critical BOE Technology Group Co Ltd
Priority to US14/346,868 priority Critical patent/US9330451B2/en
Publication of WO2014134880A1 publication Critical patent/WO2014134880A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • G06T7/001Industrial image inspection using an image reference approach
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01MTESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M11/00Testing of optical apparatus; Testing structures by optical methods not otherwise provided for
    • G01M11/08Testing mechanical properties
    • G01M11/081Testing mechanical properties by using a contact-less detection method, i.e. with a camera
    • 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
    • G01N21/8806Specially adapted optical and illumination features
    • 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
    • G01N21/95Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • GPHYSICS
    • G09EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09GARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G3/00Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes
    • G09G3/006Electronic inspection or testing of displays and display drivers, e.g. of LED or LCD displays
    • GPHYSICS
    • G09EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09GARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G3/00Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes
    • G09G3/20Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix no fixed position being assigned to or needed to be assigned to the individual characters or partial characters
    • G09G3/34Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix no fixed position being assigned to or needed to be assigned to the individual characters or partial characters by control of light from an independent source
    • G09G3/3406Control of illumination source
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10016Video; Image sequence
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30108Industrial image inspection
    • G06T2207/30164Workpiece; Machine component
    • GPHYSICS
    • G09EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09GARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G2330/00Aspects of power supply; Aspects of display protection and defect management
    • G09G2330/10Dealing with defective pixels

Definitions

  • Embodiments of the present invention relate to the field of flaw detection technology, and in particular, to a method and a device for detecting a backlight module. Background technique
  • the conventional detection method is to place the backlight module on the fixture to light up. That is, after the backlight module is lit, it is inspected by manual visual inspection and marked at the ⁇ position, and then the defective product is sent to the repairing unit for repair.
  • the existing method of manually detecting the backlight module is low in work efficiency, high in probability of missed detection, and cannot be quantitatively detected in combination with mass production.
  • Embodiments of the present invention provide a method and a device for detecting a backlight module, which are used to achieve high efficiency in detecting defects in the interior and appearance of a backlight module.
  • a method for detecting a backlight module ⁇ includes: acquiring an image including features of each component in the backlight module at a plurality of preset angles with a surface of the backlight module; An image containing features of each component in the backlight module is analyzed to determine defects existing in components of the backlight module.
  • a detection device for a backlight module includes: a machine; The cymbal detecting device of the machine and the loading platform for carrying the backlight module; wherein the cymbal detecting device comprises: acquiring the backlight module in a plurality of preset angles with the surface of the backlight module An image acquiring unit of the image of each component feature; and, in signal connection with the image acquiring unit, analyzing the acquired image containing the features of each component in the backlight module, and determining that each component in the backlight module exists The image analysis unit of the defect.
  • FIG. 1 is a schematic diagram of a feature graphic according to an embodiment of the present invention.
  • FIG. 2 is a schematic structural diagram of a device for detecting a backlight module according to an embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of a first embodiment according to an embodiment of the present invention
  • Embodiment 4 is a schematic structural diagram of Embodiment 2 according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of Embodiment 3 according to an embodiment of the present disclosure.
  • FIG. 6 is a schematic structural diagram of Embodiment 4 according to an embodiment of the present disclosure.
  • FIG. 7 is a schematic structural diagram of an image analysis unit according to an embodiment of the present invention. detailed description
  • the method for detecting a backlight module may include the following steps: S101: acquiring an image including features of each component in the backlight module by using a plurality of preset angles with a surface of the backlight module;
  • the backlight module is composed of a light guide plate, a diffusion plate, and an optical film layer such as a reflection sheet and a brightness enhancement sheet.
  • an image that highlights the features of the components in the backlight module can be obtained.
  • an external light source is used to illuminate the surface of the backlight module, the smaller the angle between the shooting direction and the surface of the backlight module, the more the image obtained on the surface of the backlight module can be displayed.
  • an image containing features of each component in the backlight module can be obtained by acquiring an image from different preset angles; after analyzing each image, it is possible to determine the existence of each component.
  • the method for detecting the backlight module ⁇ provided by the embodiment of the present invention can improve the accuracy of detection and detection relative to the manner of manually detecting the backlight module ⁇ .
  • the step S101 in the foregoing method obtaineds an image including the features of each component in the backlight module by using a plurality of preset angles with the surface of the backlight module, and specifically includes the following manners:
  • the specific implementation manner may be: when the external light source is irradiated to the backlight module at the first predetermined angle, the second surface is formed with the surface of the backlight module. Set the angle to obtain an image containing the surface features of the backlight module.
  • the external light source is white light better than other light sources such as green light.
  • the first predetermined angle at which the external light source illuminates the backlight module is 45 degrees.
  • the second predetermined angle at which the surface image of the backlight module is obtained is 90 degrees.
  • the specific implementation manner may be: when the backlight module is lit, to form a third preset angle with the surface of the backlight module, Obtain an image containing the characteristics of the light guide plate in the backlight module; at this time, the backlight module is not illuminated by an external light source.
  • the third predetermined angle for acquiring an image of the light guide plate feature in the backlight module is 90 degrees.
  • the specific implementation may be: when the external light source is irradiated to the backlight module at a first preset angle, The surface of the backlight module is at a fourth predetermined angle to obtain an image containing the features of the diffusion plate or the optical film layer in the backlight module.
  • the external light source is white light better than other light sources such as green light.
  • the first predetermined angle at which the external light source illuminates the backlight module is 45 degrees.
  • obtaining a fourth preset angle of an image including a diffuser plate or an optical film layer feature in the backlight module is 60 degrees or
  • step S102 analyzes the acquired image including the features of each component in the backlight module, and determines the location of the defect existing in each component of the backlight module. This is achieved by the following steps: 5201. Perform binarization processing on the obtained image containing the features of each component in the backlight module to obtain a corresponding binarized image. Specifically, the binarization process belongs to the prior art, and is not described in detail herein.
  • the first average gray value may be calculated by using each adjacent three pixel points in the binarized image as a group, and the adjacent three pixel points may be three adjacent ones in a row.
  • the pixel point may also be three adjacent pixel points in a column, which is not limited herein.
  • the adjacent three pixel points are adjacent three pixel points in a row, corresponding to calculating a second average gray value of the pixel of the row of the adjacent three pixel points of the group;
  • the second average gray value of the pixel of the column in which the adjacent three pixel points are located is calculated.
  • contrast variability I first average gray value - second average gray value I / second average gray value.
  • step S205 determining whether the contrast variability is greater than the set threshold; when determining that the contrast variability is greater than the set threshold, performing step S205; and determining that the contrast variability is not greater than the set threshold, returning to step S202, to the neighboring N of the other group Pixels are calculated;
  • the position of the defect is generally recorded to prepare for subsequent transplanting and repairing.
  • the foregoing detection method provided by the embodiment of the present invention may further include the steps of determining and counting the defect type after determining the defect of each component in the backlight module, and the specific steps include: calculating the existence of each component in the backlight module A geometric feature parameter of at least one feature graphic composed of all the defects, and determining a sampling type of the feature graphic according to the calculated geometric feature parameter of each feature graphic.
  • a cylindrical PCNN (Pulse Coupled Neural Network) model can be utilized.
  • the image of each component that determines the defect is subjected to binary segmentation processing, for example, where each defect in the image is located.
  • the pixel value of the pixel at the point is marked as 1, and the pixel value of the other pixel is marked as 0.
  • geometric parameters such as area, width, and height of a feature pattern composed of a plurality of consecutive points are calculated. For example, as shown in FIG. 1, the number of pixels having a pixel value of 1 in a feature pattern is counted.
  • the number of pixels with a pixel value of 1 between the leftmost end and the rightmost end of the statistical feature graph is the width W; the pixel value of the pixel value between the uppermost end and the lowermost end of the statistical feature graph is 1.
  • the number of points is the height 11.
  • the geometric feature parameters of each feature graphic can be compared with the features of each category stored in the database to obtain the ⁇ category of the feature graphic.
  • the stored data may be modified or added in the database.
  • the embodiment of the present invention further provides a detection device for a backlight module.
  • the principle of the detection device is similar to the detection method of the backlight module, and the implementation of the detection device can be implemented. See the implementation of the method, and the repetition will not be repeated.
  • a detection device for a backlight module includes: a machine 01; a detection device 02 mounted on the machine 01 and a carrier 03 for carrying the backlight module 04 ; among them,
  • ⁇ detection device 02 includes:
  • the signal acquisition unit 05 is connected to the signal, and the acquired image including the features of each component in the backlight module 04 is analyzed to determine the image analysis unit 06 of the defect existing in each component of the backlight module 04.
  • the image acquisition unit 05 can be at a preset angle of 90 degrees, 60 degrees, and 30 degrees with the surface of the backlight module 04 to obtain an image including features of the components in the backlight module 04.
  • the backlight module 04 is composed of a light guide plate, a diffusion plate, and an optical film layer such as a reflection sheet and a brightness enhancement sheet.
  • the image obtaining unit 05 may obtain an angle of 90 degrees from the surface of the backlight module when the external light source illuminates the backlight module 04 at the first predetermined angle.
  • An image containing the surface features of the backlight module when implemented, external The light source is white light better than other light sources such as green light.
  • the first predetermined angle at which the external light source illuminates the backlight module is 45 degrees.
  • the image obtaining unit 05 can obtain the backlight module at a 90 degree angle with the surface of the backlight module when the backlight module 04 is lit.
  • the image acquisition unit 05 may be configured to illuminate the backlight module with the external light source at a first predetermined angle. At an angle of 30 degrees or 60 degrees, an image containing the features of the diffuser or optical film layer in the backlight module 04 is obtained.
  • the flaw detecting device in the above detecting device provided by the embodiment of the present invention can be implemented in the following manners.
  • Example 1 As shown in FIG. 3, the if ⁇ detecting device 02 may have a detecting station; the image obtaining unit includes: a CCD device 07 located at the detecting station;
  • the detecting station has an external light source 08 for illuminating the backlight module 04; the external light source 08 generally illuminates the surface of the backlight module 04 at a 45 degree angle;
  • the stage 03 is a stage that can be flipped along an axis parallel to the surface of the stage 03. Thus, when the images of the components of the backlight module 03 are acquired at different preset angles, the stage 03 and the backlight module can be rotated. 04. Adjust the relative angle between the shooting direction of the CCD device 07 and the surface of the backlight module 04.
  • Example 2 As shown in FIG. 4, the flaw detection device 02 has a detection station;
  • the inspection station has an external light source 08 for illuminating the backlight module 04; the external light source 08 generally illuminates the surface of the backlight module 04 at a 45 degree angle.
  • the image acquisition unit includes: a CCD device 07 located at the detecting station; the angle between the image capturing direction of the CCD device 07 and the surface of the backlight module 04 can be adjusted, so that the components of the backlight module 04 are acquired at different preset angles.
  • the relative position between the CCD device 07 and the backlight module 04 can be adjusted by rotating the CCD device 07.
  • Example 3 As shown in FIG. 5, the flaw detection device 02 has a detection station
  • the inspection station has an external light source 08 for illuminating the backlight module 04; the external light source 08 generally illuminates the surface of the backlight module 04 at a 45 degree angle.
  • the image acquisition unit comprises: a plurality of CCD devices 07 located at the detection station, each CCD device The angle between the image capturing direction of the 07 and the surface of the backlight module 04 is different. In this way, each CCD device 07 can simultaneously acquire images of various components of the backlight module 04 through different preset angles.
  • Example 4 As shown in Fig. 6, the stage 03 is mounted on the machine table 01 by a conveying device; the ⁇ detecting device has a plurality of detecting stations located on the conveying device stroke;
  • At least one inspection station has an external light source 08 for illuminating the backlight module 04; the external light source 08 illuminates the surface of the backlight module 04 at a 45 degree angle.
  • the image acquisition unit includes at least one CCD device 07 each of the inspection stations, and the angle between the image capturing direction of each CCD device 07 and the surface of the backlight module 04 is at least two angles.
  • a CCD device 07 may be disposed in a detection station, and a plurality of CCD devices 07 may be disposed, which is not limited herein.
  • the angles of the acquired images of the CCD devices 07 may be different or partially identical, and are not limited herein.
  • the implementation of multiple CCD devices can realize non-stop detection and improve detection efficiency.
  • the CCD device 07 mentioned in the first embodiment, the second embodiment, the third embodiment, and the fourth embodiment may be a line CCD device or a surface array CCD device, which is not limited herein.
  • the image analyzing unit 06 in the above-mentioned detecting device provided by the embodiment of the present invention, as shown in FIG. 7, may specifically include:
  • the binarization processing sub-unit 061 is connected to the image acquisition unit 05 for performing binarization processing on the acquired images containing the features of the components in the backlight module to obtain corresponding binarized images;
  • the gray value calculation subunit 062 is connected to the binarization processing subunit 061, and is configured to determine, for each set of adjacent N pixel points in each binarized image, the set of adjacent N pixel points. a first average gray value, and a second average gray value of a pixel of the row or column in which the adjacent N pixel points are located;
  • a contrast variability subunit 063 coupled to the gray value calculation subunit 062, for determining a contrast variability of the first average gray value and the second average gray value;
  • the judging subunit 064 is connected to the contrast variability subunit 063, and is configured to determine, after the contrast variability subunit, that the contrast variability is greater than a set threshold, determine the neighboring N pixel points as the refreshing point. .
  • the image analyzing unit 06 in the above detecting apparatus provided by the embodiment of the present invention, As shown in FIG. 7, it may further include:
  • the geometric characteristic parameter calculation subunit 065 is connected to the ⁇ determination subunit 064 signal, and is used for calculating geometric characteristic parameters of at least one characteristic pattern composed of all defects existing in each component of the backlight module;
  • the ⁇ classification sub-unit 066 is connected to the geometric feature parameter calculation sub-unit 065 signal for determining the ⁇ category of the feature graphic according to the geometric feature parameter of each feature graphic.
  • the embodiments of the present invention can be implemented by hardware, and can also be implemented by means of software and a necessary general hardware platform.
  • the technical solution of the embodiment of the present invention may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a USB flash drive, a mobile hard disk, etc.).
  • a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods described in various embodiments of the present invention.
  • modules in the apparatus in the embodiments may be distributed in the apparatus of the embodiment according to the embodiment, or may be correspondingly changed in one or more apparatuses different from the embodiment.
  • the modules of the above embodiments may be combined into one module, or may be further split into a plurality of sub-modules.
  • the method for detecting a backlight module ⁇ provides a plurality of preset angles with a surface of the backlight module to obtain an image containing features of each component in the backlight module;
  • the images of the features of the various components are analyzed to determine the defects of the components in the backlight module.
  • an image containing the features of each component in the backlight module can be obtained.
  • the defects of each component can be determined, and the backlight module is realized. Internal and appearance flaws are detected.
  • the method for detecting the backlight module ⁇ provided by the embodiment of the present invention can improve the detection efficiency and the accuracy of detection compared to the manner of manually detecting the backlight module ⁇ .
  • a detecting device for a backlight module ⁇ includes a cymbal detecting device mounted on the machine and a loading platform for carrying the backlight module; wherein the cymbal detecting device comprises: a surface of the backlight module A map of images containing features of various components in the backlight module obtained at a plurality of preset angles
  • the image acquisition unit is configured to analyze the acquired image containing the features of each component in the backlight module, and determine an image analysis unit of the defect existing in each component of the backlight module. Since the image acquisition unit adopts the method of acquiring images from different preset angles, an image containing the features of each component in the backlight module can be obtained, and after the image analysis unit analyzes each image, the defects of each component can be determined.
  • the detection device of the backlight module ⁇ provided by the embodiment of the invention can improve the detection efficiency and the detection accuracy rate relative to the manner of manually detecting the backlight module ⁇ .

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Analytical Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
  • Testing Of Optical Devices Or Fibers (AREA)

Abstract

本发明的实施例公开了一种背光模组瑕疵的检测方法及设备,以图像获取单元的拍摄方向与背光模组的表面成多个预设角度,获取含有背光模组中各部件特征的图像;对获取到的含有背光模组中各部件特征的图像进行分析,确定背光模组中各部件存在的瑕疵点。该检测方法及设备,相对于人工检测背光模组瑕疵的方式,可以提高检测效率以及检测的准确率。

Description

背光模组瑕疵的检测方法及设备 技术领域
本发明实施例涉及瑕疵检测技术领域, 尤其涉及一种背光模组瑕疵的检 测方法及设备。 背景技术
目前所使用的具有显示功能的电子产品, 如电视、 显示器、 数字相机、 移动电话、 PDA、 随身式 DVD等都是通过液晶面板配置来显示影音讯号, 而液晶面板的影像显示更依赖于背光模组的光源设计及品质管理, 背光模组 会直接影响显示影像的效果与画面对比品质, 因此, 良好的背光模组将会提 高液晶面板影像显示的品质。
在背光模组的制备过程中,需要对背光模组进行外观瑕疵检测,如刮伤、 异物、 脏污、 白点与漏光等, 传统的检测方法是将背光模组放置于治具上点 亮即背光模组点灯后, 以人工目视方式进行检查并在瑕疵位置标示, 之后将 检测有瑕疵的产品送到修补单位进行修补。 现有的这种人工检测背光模组瑕 疵的方式, 工作效率低, 漏检概率也较高, 并且也无法配合大批量生产而形 成量化检测。
此外, 如果采用现有的机械化检测装置对背光模组进行瑕疵检测, 仅能 对背光模组外观的瑕疵进行检测, 无法对背光模组内部的瑕疵进行检测。 发明内容
本发明实施例提供了一种背光模组瑕疵的检测方法及设备, 用以实现高 效率检测背光模组内部和外观具有的瑕疵。
本发明实施例提供的一种背光模组瑕疵的检测方法, 包括: 以与背光模 组的表面成多个预设角度, 获取含有所述背光模组中各部件特征的图像; 对 获取到的含有所述背光模组中各部件特征的图像进行分析, 确定所述背光模 组中各部件存在的瑕疵点。
本发明实施例提供的一种背光模组瑕疵的检测设备, 包括: 机台; 安装 于所述机台的瑕疵检测装置和用于承载背光模组的载台; 其中, 所述瑕疵检 测装置包括: 以与背光模组的表面成多个预设角度获取含有所述背光模组中 各部件特征的图像的图像获取单元; 以及, 与所述图像获取单元信号连接, 对获取到的含有所述背光模组中各部件特征的图像进行分析, 确定所述背光 模组中各部件存在的瑕疵点的图像分析单元。 附图说明
图 1为本发明实施例提供的特征图形的示意图;
图 2为本发明实施例提供的背光模组瑕疵的检测设备的结构示意图; 图 3为本发明实施例提供的实例一的结构示意图;
图 4为本发明实施例提供的实例二的结构示意图;
图 5为本发明实施例提供的实例三的结构示意图;
图 6为本发明实施例提供的实例四的结构示意图;
图 7为本发明实施例提供的图像分析单元的结构示意图。 具体实施方式
下面结合附图, 对本发明实施例提供的背光模组瑕疵的检测方法及设备 的具体实施方式进行详细地说明。
本发明实施例提供的一种背光模组瑕疵的检测方法,可以包括以下步骤: S101、 以与背光模组的表面成多个预设角度, 获取含有背光模组中各部 件特征的图像;
S102、 对获取到的含有背光模组中各部件特征的图像进行分析, 确定背 光模组中各部件存在的瑕疵点。
通常, 背光模组是由导光板、 扩散板、 以及诸如反射片和增光片的光学 膜层等部件组成的。 利用不同光照方式和不同拍摄角度, 可以获取到凸显背 光模组中各部件上瑕疵特征的图像。 在利用外部光源照射背光模组表面时, 拍摄方向与背光模组表面的夹角越小, 获取到的图像中越能体现靠近背光模 组表面的部件上具有的瑕疵特征。 本发明实施例提供的上述检测方法, 通过 从不同预设角度获取图像的方式, 可以获取到含有背光模组中各部件特征的 图像; 在对各图像进行分析后, 就可以确定各部件存在的瑕疵点, 实现了对 背光模组内部和外观具有的瑕疵进行检测。 并且, 本发明实施例提供的背光 模组瑕疵的检测方法, 相对于人工检测背光模组瑕疵的方式, 可以提高检测 以及检测的准确率。
Figure imgf000004_0001
具体地, 本发明实施例提供的上述方法中的步骤 S101 以与背光模组的 表面成多个预设角度, 获取含有背光模组中各部件特征的图像, 具体包括如 下方式:
( 1 )当需要获取含有背光模组外观特征的图像时,具体实施方式可以为: 在外部光源成第一预设角度照射背光模组的情况下, 以与背光模组的表面成 第二预设角度, 获取含有背光模组表面特征的图像。
例如, 在具体实施时, 外部光源为白光效果优于诸如绿光的其他光源。 例如, 外部光源照射背光模组的第一预设角度为 45度。 进一步地, 例如, 获 取背光模组的表面图像的第二预设角度为 90度。
( 2 )当需要获取含有背光模组中最底层的导光板特征的图像时,具体实 施方式可以为: 在背光模组点灯的情况下, 以与背光模组的表面成第三预设 角度, 获取含有背光模组中导光板特征的图像; 此时, 背光模组无外部光源 照射。
例如, 获取含有背光模组中导光板特征的图像的第三预设角度为 90度。 ( 3 ) 当需要获取含有背光模组中除了导光板之外其他部件特征的图像 时, 具体实施方式可以为: 在外部光源成第一预设角度照射所述背光模组的 情况下, 以与背光模组的表面成第四预设角度, 获取含有背光模组中的扩散 板或光学膜层特征的图像。
例如, 在具体实施时, 外部光源为白光效果优于诸如绿光的其他光源。 例如, 外部光源照射背光模组的第一预设角度为 45度。 进一步地, 例如, 获 取含有背光模组中扩散板或光学膜层特征的图像的第四预设角度为 60度或
30度。
具体地, 在获取到背光模组中各部件图像后, 步骤 S102对获取到的含 有背光模组中各部件特征的图像进行分析, 确定背光模组中各部件存在的瑕 疵点的位置, 具体可以通过如下步骤实现: 5201、 对获取到的含有背光模组中各部件特征的图像分别进行二值化处 理得到对应的二值化图像; 具体地, 二值化处理过程属于现有技术, 在此不 作详述。
5202、针对每个二值化图像中每组相邻的 N个像素点, 确定该组相邻的 N个像素点的第一平均灰度值, 以及计算该组相邻的 N个像素点所在行或所 在列的像素点的第二平均灰度值, 其中, N为正整数;
具体地, 可以以二值化图像中每相邻的 3个像素点为一组, 计算其第一 平均灰度值, 并且, 该相邻的 3个像素点可以是一行中相邻的 3个像素点, 也可以是一列中相邻的 3个像素点, 在此不做限定。 当该相邻的 3个像素点 是一行中相邻的 3个像素点时, 对应计算该组相邻的 3个像素点所在行的像 素点的第二平均灰度值; 当该相邻的 3个像素点是一列中相邻的 3个像素点 时, 对应计算该组相邻的 3个像素点所在列的像素点的第二平均灰度值。
S203、 确定第一平均灰度值与第二平均灰度值的对比变异度;
其中, 对比变异度的具体计算公式为: 对比变异度 = I第一平均灰度值- 第二平均灰度值 I /第二平均灰度值。
5204、 判断对比变异度是否大于设定阈值; 在判断对比变异度大于设定 阈值时, 执行步骤 S205; 在判断对比变异度不大于设定阈值时, 返回步骤 S202, 对其他组相邻的 N个像素点进行计算;
5205、 确定出该组相邻的 N个像素点为 ί艮疵点。
在确定出该组相邻的 Ν个像素点为瑕疵点后,一般会记录该瑕疵点的位 置, 为后续移栽返修做准备。
本发明实施例提供的上述检测方法, 在确定出背光模组中各部件存在的 瑕疵点之后, 还可以包括判断和统计瑕疵点类型的步骤, 具体步骤包括: 计算背光模组中各部件存在的所有瑕疵点组成的至少一个特征图形的几 何特征参数, 并根据计算出的每个特征图形的几何特征参数确定特征图形的 取疵类别。
在具体实施时, 可以利用筒化的 PCNN ( Pulse Coupled Neural Network, 脉沖耦合神经网络)模型, 首先, 将判断出瑕疵点的各部件图像进行二值分 割处理, 例如, 将图像中各瑕疵点所在处的像素点的像素值标记为 1 , 其他 像素点的像素值标记为 0。 然后, 计算由连续的多个瑕疵点组成的一个特征图形的区域面积, 宽度 和高度等几何特征参数, 例如, 如图 1所示, 统计一个特征图形中像素值为 1 的像素点的个数, 即为面积 S; 统计特征图形中最左端到最右端之间像素 值为 1的像素点的个数, 即为宽度 W; 统计特征图形中最上端到最下端之间 像素值为 1的像素点的个数, 即为高度11。
在计算出各特征图形的几何特征参数后, 可以将各特征图形的几何特征 参数与数据库中存储的各瑕疵类别的特征进行比对, 得到该特征图形的瑕疵 类别。
此外, 若发现数据库中存储的各瑕疵类别的特征与特征图形的几何特征 参数不符, 或数据库中没有存储对应的瑕疵类别时, 还可以在数据库中修改 或添加存储的数据。
基于同一发明构思, 本发明实施例还提供了一种背光模组瑕疵的检测设 备, 由于该检测设备解决问题的原理与前述一种背光模组瑕疵的检测方法相 似, 因此该检测设备的实施可以参见方法的实施, 重复之处不再赘述。
本发明实施例提供的一种背光模组瑕疵的检测设备,如图 2所示, 包括: 机台 01; 安装于机台 01的瑕疵检测装置 02和用于承载背光模组 04的载台 03; 其中,
瑕疵检测装置 02包括:
以与背光模组 04的表面成多个预设角度获取含有背光模组 04中各部件 特征图像的图像获取单元 05;
以及, 与图像获取单元 05信号连接, 对获取到的含有背光模组 04中各 部件特征的图像进行分析,确定背光模组 04中各部件存在的瑕疵点的图像分 析单元 06。
在具体实施时, 图像获取单元 05可以与背光模组 04的表面成 90度、 60 度和 30度的预设角度, 以获取含有背光模组 04中各部件特征的图像。
通常, 背光模组 04是由导光板、扩散板、 以及诸如反射片和增光片的光 学膜层等部件组成的。
当需要获取含有背光模组 04外观特征的图像时, 图像获取单元 05可以 在外部光源以第一预设角度照射背光模组 04的情况下,以与背光模组的表面 成 90度角, 获取含有背光模组表面特征的图像。 例如, 在具体实施时, 外部 光源为白光效果优于诸如绿光的其他光源。 例如, 外部光源照射背光模组的 第一预设角度为 45度。
当需要获取含有背光模组 04中最底层导光板特征的图像时,图像获取单 元 05可以在背光模组 04点灯的情况下,以与背光模组的表面成 90度角,获 取含有背光模组中导光板特征的图像; 此时, 背光模组无外部光源照射。
当需要获取含有背光模组 04中除了导光板之外其他部件特征的图像时, 图像获取单元 05可以在外部光源成第一预设角度照射背光模组的情况下,以 与背光模组的表面成 30度或 60度角,获取含有背光模组 04中扩散板或光学 膜层特征的图像。
本发明实施例提供的上述检测设备中的瑕疵检测装置可以通过如下几种 方式实施。
实例一: 如图 3所示, if 疵检测装置 02可以具有一个检测工位; 图像获取单元包括: 位于检测工位的一个 CCD装置 07;
检测工位具有用于照射背光模组 04的外部光源 08;该外部光源 08—般 成 45度角照射背光模组 04的表面;
载台 03为可沿着与载台 03表面平行的轴线翻转的载台, 这样, 在以不 同预设角度获取背光模组 03各部件图像时, 可以通过转动载台 03以及承载 的背光模组 04, 调整 CCD装置 07拍摄方向和背光模组 04表面之间的相对 角度。
实例二: 如图 4所示, 瑕疵检测装置 02具有一个检测工位;
检测工位具有用于照射背光模组 04的外部光源 08;该外部光源 08—般 成 45度角照射背光模组 04的表面。
图像获取单元包括: 位于检测工位的一个 CCD装置 07; CCD装置 07 的图像拍摄方向与背光模组 04的表面之间角度可调节,这样,在以不同预设 角度获取背光模组 04各部件图像时, 可以通过转动 CCD装置 07的方式, 调整 CCD装置 07和背光模组 04之间的相对位置。
实例三: 如图 5所示, 瑕疵检测装置 02具有一个检测工位;
检测工位具有用于照射背光模组 04的外部光源 08;该外部光源 08—般 成 45度角照射背光模组 04的表面。
图像获取单元包括: 多个位于检测工位的多个 CCD装置 07,各 CCD装 置 07的图像拍摄方向与背光模组 04的表面之间角度各不相同。这样 ,各 CCD 装置 07可以通过不同预设角度同时获取背光模组 04各部件的图像。
实例四: 如图 6所示, 载台 03通过传送装置安装于机台 01上; 瑕疵检测装置具有位于传送装置行程上的多个检测工位;
至少一个检测工位具有用于照射背光模组 04的外部光源 08; 该外部光 源 08—般成 45度角照射背光模组 04的表面。
图像获取单元包括:每个检测工位具有的至少一个 CCD装置 07,各 CCD 装置 07的图像拍摄方向与背光模组 04的表面之间角度至少为两个角度。
在具体实施时, 在一个检测工位中可以设置一个 CCD装置 07, 也可以 设置多个 CCD装置 07, 在此不做限定。 各 CCD装置 07的获取图像角度可 以各不相同, 也可以部分相同, 在此不做限定。
通过实例四的这种多工位, 多个 CCD装置的实施方式, 可以实现无停 顿检测, 提高检测效率。
并且, 在实例一、 实例二、 实例三和实例四中提到的 CCD装置 07可以 是线阵 CCD装置, 也可以是面阵 CCD装置, 在此不做限定。
本发明实施例提供的上述检测设备中的图像分析单元 06, 如图 7所示, 具体可以包括:
二值化处理子单元 061 , 与图像获取单元 05信号连接, 用于对获取到的 含有背光模组中各部件特征的图像分别进行二值化处理得到对应的二值化图 像;
灰度值计算子单元 062, 与二值化处理子单元 061信号连接, 用于针对 每个二值化图像中每组相邻的 N个像素点,确定该组相邻的 N个像素点的第 一平均灰度值, 以及计算该组相邻的 N个像素点所在行或所在列的像素点的 第二平均灰度值;
对比变异度子单元 063 , 与灰度值计算子单元 062信号连接, 用于确定 第一平均灰度值与第二平均灰度值的对比变异度;
瑕疵判断子单元 064, 与对比变异度子单元 063信号连接, 用于在对比 变异度子单元判断出对比变异度大于设定阈值后,确定出该组相邻的 N个像 素点为取爽点。
进一步地, 在本发明实施例提供的上述检测设备中的图像分析单元 06, 如图 7所示, 还可以包括:
几何特征参数计算子单元 065 , 与瑕疵判断子单元 064信号连接, 用于 计算背光模组中各部件存在的所有瑕疵点组成的至少一个特征图形的几何特 征参数;
瑕疵分类子单元 066, 与几何特征参数计算子单元 065信号连接, 用于 根据计算出每个特征图形的几何特征参数确定特征图形的瑕疵类别。
通过以上实施方式的描述, 本领域的技术人员可以清楚地了解到本发明 实施例可以通过硬件实现, 也可以借助软件和必要的通用硬件平台的方式来 实现。 基于这样的理解, 本发明实施例的技术方案可以以软件产品的形式体 现出来, 该软件产品可以存储在一个非易失性存储介质 (可以是 CD-ROM, U盘, 移动硬盘等) 中, 包括若干指令用以使得一台计算机设备(可以是个 人计算机, 服务器, 或者网络设备等)执行本发明各个实施例所述的方法。
本领域技术人员可以理解附图只是一个优选实施例的示意图, 附图中的 模块或流程并不一定是实施本发明所必须的。
本领域技术人员可以理解实施例中的装置中的模块可以按照实施例描述 分布于实施例的装置中, 也可以进行相应变化位于不同于本实施例的一个或 多个装置中。 上述实施例的模块可以合并为一个模块, 也可以进一步拆分成 多个子模块。
上述本发明实施例序号仅仅为了描述, 不代表实施例的优劣。
本发明实施例提供的一种背光模组瑕疵的检测方法, 以与背光模组的表 面成多个预设角度, 获取含有背光模组中各部件特征的图像; 对获取到的含 有背光模组中各部件特征的图像进行分析, 确定背光模组中各部件存在的瑕 疵点。 通过从不同预设角度获取图像的方式, 可以获取到含有背光模组中的 各部件特征的图像, 在对各图像进行分析后, 就可以确定各部件存在的瑕疵 点, 实现了对背光模组内部和外观具有的瑕疵进行检测。 并且, 本发明实施 例提供的背光模组瑕疵的检测方法, 相对于人工检测背光模组瑕疵的方式, 可以提高检测效率以及检测的准确率。
本发明实施例提供的一种背光模组瑕疵的检测设备, 包括安装于机台的 瑕疵检测装置和用于承载背光模组的载台; 其中, 瑕疵检测装置包括: 以与 背光模组的表面成多个预设角度获取含有背光模组中各部件特征的图像的图 像获取单元; 以及,对获取到的含有背光模组中各部件特征的图像进行分析, 确定背光模组中各部件存在的瑕疵点的图像分析单元。 由于图像获取单元是 采用从不同预设角度获取图像的方式, 可以获取到含有背光模组中各部件特 征的图像, 在图像分析单元对各图像进行分析后, 就可以确定各部件存在的 瑕疵点, 实现了对背光模组内部和外观具有的瑕疵进行检测。 并且, 本发明 实施例提供的背光模组瑕疵的检测设备, 相对于人工检测背光模组瑕疵的方 式, 可以提高检测效率以及检测的准确率。 发明的精神和范围。 这样, 倘若本发明的这些修改和变型属于本发明权利要 求及其等同技术的范围之内, 则本发明也意图包含这些改动和变型在内。

Claims

权利要求书
1、 一种背光模组瑕疵的检测方法, 包括:
以与背光模组的表面成多个预设角度, 获取含有所述背光模组中各部件 特征的图像;
对获取到的含有所述背光模组中各部件特征的图像进行分析, 确定所述 背光模组中各部件存在的瑕疵点。
2、如权利要求 1所述的检测方法, 其中, 以与背光模组的表面成多个预 设角度, 获取含有所述背光模组中各部件特征的图像, 具体包括:
在外部光源成第一预设角度照射所述背光模组的情况下, 以与背光模组 的表面成第二预设角度, 获取含有所述背光模组表面特征的图像;
在所述背光模组点灯的情况下, 以与背光模组的表面成第三预设角度, 获取含有所述背光模组中导光板特征的图像;
在外部光源成第一预设角度照射所述背光模组的情况下, 以与背光模组 的表面成第四预设角度, 获取含有所述背光模组中扩散板或光学膜层特征的 图像。
3、如权利要求 1所述的检测方法, 其中,对获取到的含有所述背光模组 中各部件特征的图像进行分析, 确定所述背光模组中各部件存在的瑕疵点, 具体包括:
对获取到的含有所述背光模组中各部件特征的图像分别进行二值化处理 得到对应的二值化图像;
针对每个二值化图像中每组相邻的 N个像素点,确定该组相邻的 N个像 素点的第一平均灰度值, 以及计算该组相邻的 N个像素点所在行或所在列的 像素点的第二平均灰度值; 确定所述第一平均灰度值与第二平均灰度值的对 比变异度, 在判断所述对比变异度大于设定阈值时, 确定出该组相邻的 N个 像素点为瑕疵点, 其中, N为正整数。
4、如权利要求 3所述的检测方法, 其中,在确定所述背光模组中各部件 存在的瑕疵点之后, 还包括:
计算所述背光模组中各部件存在的所有瑕疵点组成的至少一个特征图形 的几何特征参数, 并根据计算出的每个特征图形的几何特征参数确定所述特 征图形的瑕疵类别。
5、 一种背光模组瑕疵的检测设备, 包括: 机台; 安装于所述机台的瑕疵 检测装置和用于承载背光模组的载台; 其中,
所述瑕疵检测装置包括:
以与背光模组的表面成多个预设角度获取含有所述背光模组中各部件特 征的图像的图像获取单元;
以及, 与所述图像获取单元信号连接, 对获取到的含有所述背光模组中 各部件特征的图像进行分析, 确定所述背光模组中各部件存在的瑕疵点的图 像分析单元。
6、 如权利要求 5所述的检测设备, 其中, 所述预设角度包括: 90度、
60度和 30度。
7、 如权利要求 5所述的检测设备, 其中,
所述瑕疵检测装置具有一个检测工位;
所述图像获取单元包括: 位于所述检测工位的一个 CCD装置; 所述检测工位具有用于照射所述背光模组的外部光源;
所述载台为可沿着与所述载台表面平行的轴线翻转的载台。
8、 如权利要求 5所述的检测设备, 其中,
所述瑕疵检测装置具有一个检测工位;
所述图像获取单元包括:位于所述检测工位的一个 CCD装置,所述 CCD 装置的图像拍摄方向与背光模组的表面之间角度可调节;
所述检测工位具有用于照射所述背光模组的外部光源。
9、 如权利要求 5所述的检测设备, 其中,
所述瑕疵检测装置具有一个检测工位;
所述图像获取单元包括: 多个位于所述检测工位的多个 CCD装置, 各 所述 CCD装置的图像拍摄方向与背光模组的表面之间角度各不相同;
所述检测工位具有用于照射所述背光模组的外部光源。
10、 如权利要求 5所述的检测设备, 其中,
所述载台通过传送装置安装于所述机台上;
所述瑕疵检测装置具有位于所述传送装置行程上的多个检测工位; 至少一个所述检测工位具有用于照射所述背光模组的外部光源; 所述图像获取单元包括: 每个检测工位具有的至少一个 CCD装置, 各 CCD装置的图像拍摄方向与背光模组的表面之间角度至少为两个角度。
11、如权利要求 5-10任一项所述的检测设备,其中,所述图像分析单元, 具体包括:
二值化处理子单元, 与所述图像获取单元信号连接, 用于对获取到的含 有所述背光模组中各部件特征的图像分别进行二值化处理得到对应的二值化 图像;
灰度值计算子单元, 与所述二值化处理子单元信号连接, 用于针对每个 二值化图像中每组相邻的 N个像素点,确定该组相邻的 N个像素点的第一平 均灰度值, 以及计算该组相邻的 N个像素点所在行或所在列的像素点的第二 平均灰度值;
对比变异度子单元, 与所述灰度值计算子单元信号连接, 用于确定所述 第一平均灰度值与第二平均灰度值的对比变异度;
瑕疵判断子单元, 与所述对比变异度子单元信号连接, 用于在所述对比 个像素点为瑕疵点。
12、如权利要求 11所述的检测设备,其中,所述图像分析单元,还包括: 几何特征参数计算子单元, 与所述瑕疵判断子单元信号连接, 用于计算 所述背光模组中各部件存在的所有瑕疵点组成的至少一个特征图形的几何特 征参数;
瑕疵分类子单元, 与所述几何特征参数计算子单元信号连接, 用于根据 计算出每个特征图形的几何特征参数确定所述特征图形的瑕疵类别。
PCT/CN2013/076536 2013-03-06 2013-05-31 背光模组瑕疵的检测方法及设备 Ceased WO2014134880A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US14/346,868 US9330451B2 (en) 2013-03-06 2013-05-31 Method and apparatus for detecting defect of backlight module

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201310071403.0 2013-03-06
CN201310071403.0A CN103217436B (zh) 2013-03-06 2013-03-06 一种背光模组瑕疵的检测方法及设备

Publications (1)

Publication Number Publication Date
WO2014134880A1 true WO2014134880A1 (zh) 2014-09-12

Family

ID=48815418

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2013/076536 Ceased WO2014134880A1 (zh) 2013-03-06 2013-05-31 背光模组瑕疵的检测方法及设备

Country Status (3)

Country Link
US (1) US9330451B2 (zh)
CN (1) CN103217436B (zh)
WO (1) WO2014134880A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113012607A (zh) * 2019-12-19 2021-06-22 西安诺瓦星云科技股份有限公司 显示模块检测方法、装置和系统
CN116385445A (zh) * 2023-06-06 2023-07-04 东莞市希锐自动化科技股份有限公司 一种基于视觉技术的电镀五金件瑕疵检测方法
CN116703951A (zh) * 2023-08-09 2023-09-05 成都理工大学 基于随机耦合神经网络的图像分割方法
CN117252872A (zh) * 2023-11-16 2023-12-19 深圳市华海电子科技有限公司 一种手机屏幕缺陷视觉检测方法及系统

Families Citing this family (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103411755B (zh) * 2013-08-08 2015-11-11 深圳市华星光电技术有限公司 一种光学测试装置
CN104267034B (zh) * 2014-09-11 2017-04-05 汕头轻工装备研究院 一种背光屏视觉检测设备
CN104406689B (zh) * 2014-11-28 2016-06-22 江门市宏丰电子科技有限公司 导光条检测装置
CN105388642B (zh) * 2015-11-14 2019-01-15 合肥骇虫信息科技有限公司 一种液晶面板异物检验系统
CN105424723A (zh) * 2015-11-28 2016-03-23 惠州高视科技有限公司 一种显示屏幕模组缺陷检测方法
CN105607317B (zh) * 2016-03-24 2018-11-23 京东方科技集团股份有限公司 显示器亮度调整方法、测试方法及装置、显示器测试设备
CN106200036B (zh) * 2016-06-28 2020-03-13 京东方科技集团股份有限公司 点灯检测设备
CN108205210B (zh) * 2016-12-19 2020-12-04 南京理工大学 基于傅里叶梅林及特征匹配的lcd缺陷检测系统及方法
JPWO2019058512A1 (ja) * 2017-09-22 2020-10-15 オリンパス株式会社 観察システム
CN109507815B (zh) * 2018-12-05 2022-06-21 武汉精立电子技术有限公司 一种液晶显示屏背光检测中快速定位缺陷位置的方法
CN109767428A (zh) * 2018-12-26 2019-05-17 中国科学院西安光学精密机械研究所 一种摄像模组脏污检测方法
CN109597247B (zh) * 2019-02-19 2022-04-29 京东方科技集团股份有限公司 显示面板、背光源及其校正装置
CN111598828B (zh) * 2019-02-20 2022-03-11 东莞先知大数据有限公司 一种基于图形分析pcnn特征的声发射断刀检测方法
CN111693530A (zh) * 2019-03-11 2020-09-22 深圳市联得自动化装备股份有限公司 检测装置和方法
CN112801930A (zh) * 2019-10-28 2021-05-14 上海铼钠克数控科技股份有限公司 基于机器视觉的织物的背光经纬瑕疵检测方法和设备
CN113313664A (zh) * 2020-02-07 2021-08-27 财团法人石材暨资源产业研究发展中心 基于石材加工的石材图像分析方法
CN111721505A (zh) * 2020-06-30 2020-09-29 东莞市聚明电子科技有限公司 基于极坐标的键盘背光模组的自动校准检测方法及装置
US11763758B2 (en) * 2021-05-27 2023-09-19 Sharp Kabushiki Kaisha Luminance unevenness correction system and luminance unevenness correction method
CN113705501B (zh) * 2021-09-02 2024-04-26 浙江索思科技有限公司 一种基于图像识别技术的海上目标检测方法和系统
CN113628212B (zh) * 2021-10-12 2022-03-11 高视科技(苏州)有限公司 不良偏光片识别方法、电子设备和存储介质
CN115100143B (zh) * 2022-06-23 2024-10-22 凯盛科技集团有限公司 背光模组瑕疵的检测方法
CN117350934A (zh) * 2022-06-29 2024-01-05 北京小米移动软件有限公司 补光检测方法、装置及存储介质
CN116413283A (zh) * 2022-07-28 2023-07-11 大鱼视觉技术(河南)有限公司 基于机器视觉检测背光屏幕表面瑕疵的方法
CN115393332A (zh) * 2022-08-31 2022-11-25 歌尔科技有限公司 一种漏光检测方法、装置及设备
CN116305366B (zh) * 2023-05-23 2023-09-15 四川启睿克科技有限公司 液晶电视散热仿真模组的建模方法及简化模型
CN116883803B (zh) * 2023-09-07 2023-12-05 南京诺源医疗器械有限公司 一种用于胶质瘤边缘获取的图像融合方法及系统
CN120894357B (zh) * 2025-09-28 2026-01-02 苏州天禄光科技股份有限公司 一种导光板热压线前aoi检测系统及检测方法
CN120908212B (zh) * 2025-10-09 2026-01-02 苏州天禄光科技股份有限公司 导光板缺陷样本增强与检测一体化方法

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6965120B1 (en) * 1998-12-21 2005-11-15 Hottinger Maschinenbau Gmbh Method and apparatus for quality control in the manufacture of foundry cores or core packets
CN1996441A (zh) * 2006-01-04 2007-07-11 台湾薄膜电晶体液晶显示器产业协会 显示器多角度测量系统与方法
TW201027067A (en) * 2008-12-24 2010-07-16 Ibm Non-uniformity evaluation apparatus, non-uniformity evaluation method, and display inspection apparatus and program
CN101825781B (zh) * 2009-03-06 2012-02-29 北京京东方光电科技有限公司 光学测试装置
CN102374995A (zh) * 2010-08-11 2012-03-14 乐金显示有限公司 用于检查显示设备的装置和方法
CN101419176B (zh) * 2007-10-26 2012-03-28 比亚迪股份有限公司 表面瑕疵检测方法及装置
CN102739952A (zh) * 2011-03-29 2012-10-17 财团法人工业技术研究院 多视角取像方法及其应用系统

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100541449B1 (ko) * 2003-07-23 2006-01-11 삼성전자주식회사 패널검사장치
CN100371702C (zh) * 2004-03-20 2008-02-27 鸿富锦精密工业(深圳)有限公司 背光模组检测装置
JP4884738B2 (ja) * 2005-09-26 2012-02-29 株式会社日本マイクロニクス 液晶パネル検査装置
TWI320497B (en) * 2005-12-09 2010-02-11 Taiwan Tft Lcd Ass Multiple-angle imaging machine, multiple-angle inspection system and method for blemish measurement of a flat panel display
JP2007333449A (ja) * 2006-06-13 2007-12-27 Heiwa Tokei Mfg Co Ltd 検査装置
CN101261234B (zh) * 2008-03-26 2010-06-09 广州中国科学院工业技术研究院 表面缺陷检测装置
US8602603B2 (en) * 2010-07-14 2013-12-10 Shenzhen China Star Optoelectronics Technology Co., Ltd. Backlight module and display apparatus

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6965120B1 (en) * 1998-12-21 2005-11-15 Hottinger Maschinenbau Gmbh Method and apparatus for quality control in the manufacture of foundry cores or core packets
CN1996441A (zh) * 2006-01-04 2007-07-11 台湾薄膜电晶体液晶显示器产业协会 显示器多角度测量系统与方法
CN101419176B (zh) * 2007-10-26 2012-03-28 比亚迪股份有限公司 表面瑕疵检测方法及装置
TW201027067A (en) * 2008-12-24 2010-07-16 Ibm Non-uniformity evaluation apparatus, non-uniformity evaluation method, and display inspection apparatus and program
CN101825781B (zh) * 2009-03-06 2012-02-29 北京京东方光电科技有限公司 光学测试装置
CN102374995A (zh) * 2010-08-11 2012-03-14 乐金显示有限公司 用于检查显示设备的装置和方法
CN102739952A (zh) * 2011-03-29 2012-10-17 财团法人工业技术研究院 多视角取像方法及其应用系统

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113012607A (zh) * 2019-12-19 2021-06-22 西安诺瓦星云科技股份有限公司 显示模块检测方法、装置和系统
CN116385445A (zh) * 2023-06-06 2023-07-04 东莞市希锐自动化科技股份有限公司 一种基于视觉技术的电镀五金件瑕疵检测方法
CN116385445B (zh) * 2023-06-06 2023-08-11 东莞市希锐自动化科技股份有限公司 一种基于视觉技术的电镀五金件瑕疵检测方法
CN116703951A (zh) * 2023-08-09 2023-09-05 成都理工大学 基于随机耦合神经网络的图像分割方法
CN116703951B (zh) * 2023-08-09 2023-10-20 成都理工大学 基于随机耦合神经网络的图像分割方法
CN117252872A (zh) * 2023-11-16 2023-12-19 深圳市华海电子科技有限公司 一种手机屏幕缺陷视觉检测方法及系统
CN117252872B (zh) * 2023-11-16 2024-03-12 深圳市华海电子科技有限公司 一种手机屏幕缺陷视觉检测方法及系统

Also Published As

Publication number Publication date
CN103217436A (zh) 2013-07-24
US9330451B2 (en) 2016-05-03
CN103217436B (zh) 2015-05-20
US20150063675A1 (en) 2015-03-05

Similar Documents

Publication Publication Date Title
CN103217436B (zh) 一种背光模组瑕疵的检测方法及设备
CN108445007B (zh) 一种基于图像融合的检测方法及其检测装置
CN104081192B (zh) 一种对玻璃多层面摄像的摄像装置及其方法
CN104374551B (zh) 一种led发光均匀性检测方法及其系统
CN111289536B (zh) 一种电子设备屏幕的缺陷检测装置
CN109813223B (zh) 同时对物体相邻两个表面进行光学检测的装置及方法
JP2017049974A (ja) 識別器生成装置、良否判定方法、およびプログラム
KR101867015B1 (ko) 글라스 결함 검사 장치, 검사 방법 및 검사 시스템
CN101074932A (zh) 图像检查方法以及使用了该方法的图像检查装置
US20150357216A1 (en) Computer visual recognition output image-aided led die sorting system and sorting method
KR102632169B1 (ko) 유리기판 검사 장치 및 방법
TWI264793B (en) Defect detection apparatus and defect detection method
CN103630544B (zh) 一种视觉在线检测系统
CN104655646A (zh) 玻璃基板内部缺陷检查系统及所处高度位置的检查方法
CN104122264B (zh) 外观瑕疵检测系统及方法
CN105823780B (zh) 面板检测装置与方法
TWI495867B (zh) Application of repeated exposure to multiple exposure image blending detection method
CN109827974B (zh) 一种树脂滤光片膜裂检测设备及检测方法
CN104568977A (zh) 平面玻璃表面缺陷自动检测系统和检测方法
CN103091332B (zh) 一种基于机器视觉的u型粉管的检测方法及其检测系统
CN107656387B (zh) 一种液晶屏对位偏移缺陷检测方法
JP2013134185A (ja) ガラス容器の欠陥検査方法及び装置
CN115980059A (zh) 表面缺陷检测系统及其检测方法、装置、设备、存储介质
KR102008224B1 (ko) 곡면 검사가 가능한 검사시스템
CN110243336A (zh) 屏体翘曲检测方法

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 14346868

Country of ref document: US

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

Ref document number: 13877148

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 12.01.2016)

122 Ep: pct application non-entry in european phase

Ref document number: 13877148

Country of ref document: EP

Kind code of ref document: A1