CN108844966A - Screen detection method and system - Google Patents
Screen detection method and system Download PDFInfo
- Publication number
- CN108844966A CN108844966A CN201810746927.8A CN201810746927A CN108844966A CN 108844966 A CN108844966 A CN 108844966A CN 201810746927 A CN201810746927 A CN 201810746927A CN 108844966 A CN108844966 A CN 108844966A
- Authority
- CN
- China
- Prior art keywords
- screen
- detection
- gray value
- sample
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 140
- 230000007547 defect Effects 0.000 claims abstract description 74
- 238000003860 storage Methods 0.000 claims abstract description 9
- 239000004973 liquid crystal related substance Substances 0.000 claims abstract description 4
- 230000007246 mechanism Effects 0.000 claims description 25
- 238000012545 processing Methods 0.000 claims description 16
- 239000000463 material Substances 0.000 claims description 12
- 238000009434 installation Methods 0.000 claims description 11
- 230000002950 deficient Effects 0.000 claims description 8
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 230000000737 periodic effect Effects 0.000 abstract description 3
- 239000000523 sample Substances 0.000 description 39
- 238000005516 engineering process Methods 0.000 description 16
- 238000007689 inspection Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000000034 method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 239000013072 incoming material Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000013068 control sample Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005389 magnetism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
- G01N21/95607—Inspecting patterns on the surface of objects using a comparative method
-
- G—PHYSICS
- G02—OPTICS
- G02F—OPTICAL DEVICES OR ARRANGEMENTS FOR THE CONTROL OF LIGHT BY MODIFICATION OF THE OPTICAL PROPERTIES OF THE MEDIA OF THE ELEMENTS INVOLVED THEREIN; NON-LINEAR OPTICS; FREQUENCY-CHANGING OF LIGHT; OPTICAL LOGIC ELEMENTS; OPTICAL ANALOGUE/DIGITAL CONVERTERS
- G02F1/00—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics
- G02F1/01—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics for the control of the intensity, phase, polarisation or colour
- G02F1/13—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics for the control of the intensity, phase, polarisation or colour based on liquid crystals, e.g. single liquid crystal display cells
- G02F1/1306—Details
- G02F1/1309—Repairing; Testing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Nonlinear Science (AREA)
- Health & Medical Sciences (AREA)
- Optics & Photonics (AREA)
- Crystallography & Structural Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
Description
技术领域technical field
本发明涉及屏幕检测方法技术领域,尤其涉及一种屏幕检测方法及检测系统。The invention relates to the technical field of screen detection methods, in particular to a screen detection method and a detection system.
背景技术Background technique
在液晶屏幕的生产过程中,屏幕显示缺陷检测是其中一个重要环节,通过屏幕检测工序以检测屏幕是否存在缺陷,以避免缺陷品流入市场。In the production process of LCD screens, screen display defect inspection is one of the important links. The screen inspection process is used to detect whether there are defects in the screen, so as to prevent defective products from entering the market.
目前主要通过人工检测或半自动点灯检测的方式对屏幕加以检测。人工检测的检测效率较低,检测一块屏幕的时间大约为45S,并且易忽略屏幕中的暗点缺陷,误检率较高。而半自动检测中主要采取人工对位的方式,导致检测效率较低,并且检测精度相比人工检测方式并没有太大的改善,误检率高的问题得不到有效的解决。At present, the screen is mainly detected by manual detection or semi-automatic lighting detection. The detection efficiency of manual detection is low, and the time to detect a screen is about 45S, and it is easy to ignore dark spot defects in the screen, and the false detection rate is high. In semi-automatic detection, manual alignment is mainly adopted, resulting in low detection efficiency, and the detection accuracy is not much improved compared with manual detection, and the problem of high false detection rate cannot be effectively solved.
发明内容Contents of the invention
本发明的目的在于提供一种屏幕检测方法及检测系统,以解决上述问题。The object of the present invention is to provide a screen detection method and detection system to solve the above problems.
为达此目的,本发明采用以下技术方案:For reaching this purpose, the present invention adopts following technical scheme:
一种屏幕检测方法,包括点、线缺陷检测方法,所述点、线缺陷检测方法包括如下步骤:A screen detection method, including point, line defect detection method, described point, line defect detection method comprises the steps:
采集正常屏幕图像,通过图像处理得到对照图像,获取对照图像的对照像素灰度值周期;Collect a normal screen image, obtain a control image through image processing, and obtain the control pixel gray value period of the control image;
采集待检测屏幕图像,通过图像处理得到样本图像,获取待检测屏幕图像的样本像素灰度值;Collect the screen image to be detected, obtain the sample image through image processing, and obtain the sample pixel gray value of the screen image to be detected;
将所述样本像素灰度值与所述像素灰度值周期内的照像素灰度值一一做差,当样本像素灰度值对应的差值大于预设值时,则判定为屏幕缺陷。Making a difference between the sample pixel gray value and the pixel gray value within the pixel gray value period, and when the difference corresponding to the sample pixel gray value is greater than a preset value, it is determined as a screen defect.
可选的,在将所述样本像素灰度值与对照像素灰度值周期一一做差时,若差值大于预设值的样本呈点状,则该缺陷判定为点缺陷。Optionally, when the gray value of the sample pixel is compared with the gray value of the control pixel one by one, if the sample with a difference value greater than a preset value is in the shape of a point, then the defect is determined as a point defect.
可选的,在将所述样本像素灰度值与对照像素灰度值周期一一做差时,若差值大于预设值的样本呈线状,则该缺陷判定为线缺陷。Optionally, when the gray value of the sample pixel is compared with the gray value of the control pixel one by one, if the sample with a difference value greater than a preset value is in a line shape, the defect is determined as a line defect.
可选的,所述图像处理包括滤波处理。Optionally, the image processing includes filtering processing.
可选的,还包括Mura缺陷检测方法,所述Mura缺陷检测方法包括:Optionally, a Mura defect detection method is also included, and the Mura defect detection method includes:
采集屏幕图像,并进行Mura缺陷检测;Collect screen images and perform Mura defect detection;
当出现Mura缺陷时,将该屏幕标记为有缺陷屏幕;当不存在Mura缺陷时,将该屏幕标记为无缺陷屏幕;When a mura defect occurs, the screen is marked as a defective screen; when there is no mura defect, the screen is marked as a non-defective screen;
建立样本图像数据库,重复上述步骤,直至采集到满足检测精度的足够数量的样本图像,并将样本图像储存于所述样本图像数据库中。A sample image database is established, and the above steps are repeated until a sufficient number of sample images meeting the detection accuracy are collected, and the sample images are stored in the sample image database.
本发明还提供了一种屏幕检测系统,包括检测区,所述检测区包括:The present invention also provides a screen detection system, which includes a detection area, and the detection area includes:
采集装置,用于采集图像;An acquisition device, configured to acquire images;
储存装置,用于储存经过所述采集装置采集所得样本图像数据库,所述储存装置电连接所述采集装置;a storage device for storing a sample image database collected by the collection device, and the storage device is electrically connected to the collection device;
判断装置,用于判断图像是否存在缺陷,所述判断装置电连接所述采集装置;A judging device, used to judge whether there is a defect in the image, the judging device is electrically connected to the acquisition device;
视觉对位装置,所述视觉对位装置电连接所述对位平台并对准所述工作台,用于实现屏幕方位的调整。A visual alignment device, the visual alignment device is electrically connected to the alignment platform and aligned with the workbench, so as to adjust the orientation of the screen.
可选的,所述检测区内设有安装架,所述采集装置装设于所述安装架上;Optionally, a mounting frame is provided in the detection area, and the collection device is mounted on the mounting frame;
所述安装架上还设有对位平台,所述对位平台上设有工作台,所述工作台位于所述采集装置下方;所述安装架上还设有第二抓取机构,所述第二抓取机构用于将待检测屏幕固定于工作台上;The installation frame is also provided with an alignment platform, the alignment platform is provided with a workbench, and the workbench is located below the collection device; the installation frame is also provided with a second grasping mechanism, the The second grabbing mechanism is used to fix the screen to be detected on the workbench;
所述工作台下方设有背光源,所述背光源电连接有光源控制器。A backlight is provided under the workbench, and the backlight is electrically connected to a light source controller.
可选的,所述屏幕检测系统还包括位于所述检测区一侧的待料区;所述待料区所述待料区上设有读码器,所述读码器用于读取待检测屏幕的ID;Optionally, the screen detection system also includes a material waiting area located on one side of the detection area; a code reader is arranged on the material waiting area in the material waiting area, and the code reader is used to read the the ID of the screen;
其中,所述待料区与所述检测区之间设有第一抓取机构,所述待料区和所述检测区围设于所述第一抓取机构外侧;所述第一抓取机构用于将待料区上的待检测屏幕抓取放至检测区中进行检测。Wherein, a first grasping mechanism is provided between the material waiting area and the detection area, and the material waiting area and the detection area are surrounded by the outside of the first grasping mechanism; the first grasping The mechanism is used to grab the screen to be detected on the waiting area and put it into the detection area for detection.
可选的,所述安装架上设有调整单轴,所述采集装置通过所述调整单轴装设于安装架上,所述调整单轴用于调整采集装置与待检测屏幕之间的距离。Optionally, the installation frame is provided with an adjustment uniaxial, and the acquisition device is installed on the installation frame through the adjustment uniaxial, and the adjustment uniaxial is used to adjust the distance between the acquisition device and the screen to be detected .
可选的,所述屏幕检测系统还包括工作站,所述工作站与Mes系统建立连接,并与采集装置、储存装置、判断装置以及读码器电连接。Optionally, the screen detection system further includes a workstation, which establishes a connection with the Mes system, and is electrically connected with the collection device, the storage device, the judging device and the code reader.
与现有技术相比,本发明实施例具有以下有益效果:Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
本发明提供一种屏幕检测方法,通过周期算法、人工智能检测方法检测屏幕的点缺陷、线缺陷以及Mura缺陷,同时,本发明还提供了一种屏幕检测系统,提高了屏幕检测的效率以及精度。The invention provides a screen detection method, which detects point defects, line defects and mura defects of the screen through a periodic algorithm and an artificial intelligence detection method. At the same time, the invention also provides a screen detection system, which improves the efficiency and accuracy of screen detection .
附图说明Description of drawings
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其它的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained according to these drawings on the premise of not paying creative efforts.
图1为本发明实施例提供的一种点、线缺陷检测方法的流程图;Fig. 1 is a flow chart of a point and line defect detection method provided by an embodiment of the present invention;
图2为本发明实施例提供的一种Mura缺陷检测方法的流程图;Fig. 2 is the flowchart of a kind of Mura defect detection method provided by the embodiment of the present invention;
图3图3为本发明实施例提供的一种屏幕检测系统的结构示意图。FIG. 3 is a schematic structural diagram of a screen detection system provided by an embodiment of the present invention.
上述图中:10、待料区;20、第一抓取机构;30、检测区;31、工作站;32、光源控制器;33、对位平台;34、采集装置;35、第二抓取机构。In the above figure: 10, material waiting area; 20, first grabbing mechanism; 30, detection area; 31, workstation; 32, light source controller; 33, alignment platform; 34, acquisition device; 35, second grabbing mechanism.
具体实施方式Detailed ways
本发明的核心思想为:通过周期算法、人工智能检测方法检测屏幕的点缺陷、线缺陷以及Mura缺陷,同时,提供了一种屏幕检测系统以提高屏幕检测的效率以及精度。The core idea of the present invention is to detect point defects, line defects and mura defects of the screen through periodic algorithm and artificial intelligence detection method, and meanwhile, provide a screen detection system to improve the efficiency and precision of screen detection.
为使得本发明的发明目的、特征、优点能够更加的明显和易懂,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,下面所描述的实施例仅仅是本发明一部分实施例,而非全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例,都属于本发明保护的范围。In order to make the purpose, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the following The described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
下面结合附图并通过具体实施方式来进一步说明本发明的技术方案。The technical solution of the present invention will be further described below in conjunction with the accompanying drawings and through specific implementation methods.
实施例一Embodiment one
近年来,随着TFT-LCD产业发展迅速,相关的制造和检测设备已经呈现出光、气、电、磁于一体的趋势,变得越来越自动化、集成化、信息化和智能化。为了保证液晶屏高效生产,本实施例实施例提供了一种屏幕检测方法,将该检测方法嵌入在生产流水线中,实现高效率的缺陷检测。In recent years, with the rapid development of the TFT-LCD industry, related manufacturing and testing equipment has shown a trend of integrating light, gas, electricity, and magnetism, and has become more and more automated, integrated, informatized, and intelligent. In order to ensure efficient production of liquid crystal screens, the embodiment of this embodiment provides a screen detection method, which is embedded in a production line to achieve high-efficiency defect detection.
如图1所示,图1为本发明实施例提供的一种点、线缺陷检测方法的流程图,该点、线缺陷检测方法包括如下步骤:As shown in Figure 1, Figure 1 is a flow chart of a point and line defect detection method provided by an embodiment of the present invention, the point and line defect detection method includes the following steps:
S101、采集正常屏幕图像,通过图像处理得到对照图像,获取对照图像的对照像素灰度值周期。S101. Collect a normal screen image, obtain a contrast image through image processing, and obtain a contrast pixel gray value period of the contrast image.
本步骤中,先将正常屏幕切换到纯色画面,然后通过高像素工业相机采集图像,得到正常屏幕图像;对该正常屏幕图像进行图像处理得到对照图像,并获取对照图像中的灰度值PitchX(X轴方向上的灰度值周期)和PitchY(Y轴方向上的灰度值周期)。In this step, the normal screen is first switched to a solid-color picture, and then the image is collected by a high-pixel industrial camera to obtain a normal screen image; image processing is performed on the normal screen image to obtain a comparison image, and the gray value PitchX( Grayscale value period in the X-axis direction) and PitchY (grayscale value period in the Y-axis direction).
由于正常屏幕的像素灰度值是呈周期性分布的,因而在该步骤中最终获取对照像素灰度值周期。该对照像素灰度值用于在后续的屏幕检测中起对照样本的作用。Since the pixel gray value of the normal screen is periodically distributed, the control pixel gray value period is finally obtained in this step. The gray value of the control pixel is used as a control sample in the subsequent screen detection.
其中,图像处理包括滤波处理,即进行噪声滤波、提取点像素等步骤,为本领域的常规技术手段,在此不再进行详细描述。Wherein, image processing includes filtering processing, that is, noise filtering, point pixel extraction and other steps, which are conventional technical means in the art, and will not be described in detail here.
S102、采集待检测屏幕图像,通过图像处理得到样本图像,获取待检测屏幕图像的样本像素灰度值。S102. Collect a screen image to be detected, obtain a sample image through image processing, and obtain a sample pixel gray value of the screen image to be detected.
本步骤中,将待检测屏幕切换到纯色画面,通过高像素工业相机采集待检测屏幕图像,对该待检测屏幕图像,由已知的图像灰度周期PitchX、PitchY,对图像进行处理获得对照图像。该步骤所获取的样本像素灰度值用于作为检测的根据,以判断屏幕是否存在点缺陷或线缺陷。In this step, the screen to be inspected is switched to a solid-color image, and the image of the screen to be inspected is collected by a high-pixel industrial camera. The image of the screen to be inspected is processed by the known image grayscale periods PitchX and PitchY to obtain a comparison image . The sample pixel gray value obtained in this step is used as a basis for detection to determine whether there is a point defect or a line defect on the screen.
S103、将所述样本像素灰度值与所述像素灰度值周期内的照像素灰度值一一做差,当样本像素灰度值对应的差值大于预设值时,则判定为屏幕缺陷。S103. Make a difference between the sample pixel gray value and the pixel gray value within the pixel gray value period, and when the difference corresponding to the sample pixel gray value is greater than the preset value, it is determined that the screen defect.
当待检测屏幕为正常屏幕时,屏幕图像中的像素灰度值在任意周期倍数下应当与样本像素灰度值相同,或屏幕图像中的像素灰度值与样本像素灰度值的差值应当在预设值的范围内。When the screen to be tested is a normal screen, the pixel gray value in the screen image should be the same as the sample pixel gray value at any period multiple, or the difference between the pixel gray value in the screen image and the sample pixel gray value should be within the preset range.
当样本像素灰度值对应的差值大于预设值时,则该样本则判定为屏幕缺陷。When the difference corresponding to the pixel gray value of the sample is greater than the preset value, the sample is determined to be a screen defect.
在将所述样本像素灰度值与对照像素灰度值周期一一做差时,若差值大于预设值的样本呈点状,则该缺陷判定为点缺陷。在将所述样本像素灰度值与对照像素灰度值周期一一做差时,若差值大于预设值的样本呈线状,则该缺陷判定为线缺陷。When the gray value of the sample pixel is compared with the gray value of the control pixel one by one, if the sample with a difference value greater than a preset value is in the shape of a point, the defect is determined as a point defect. When the gray value of the sample pixel is compared with the gray value of the control pixel one by one, if the sample with a difference value greater than a preset value is in a line shape, the defect is determined as a line defect.
在上述提供的点、线缺陷检测方法中,实际工况下采集的待检测屏幕图像与正常屏幕图像的采集条件均相同,即场景相同、视点相同,以确保检测的精确度。通过上述缺陷检测方法能够精确地检测出屏幕的缺陷,并能够快速确定缺陷的类型、位置,解决了现有技术中检测精度不高、检测效率低的问题。In the point and line defect detection method provided above, the acquisition conditions of the screen image to be inspected and the normal screen image collected under actual working conditions are the same, that is, the same scene and the same viewpoint, so as to ensure the accuracy of detection. The defects of the screen can be accurately detected through the defect detection method, and the type and location of the defects can be quickly determined, which solves the problems of low detection accuracy and low detection efficiency in the prior art.
本实施例还提供一种Mura缺陷检测方法,用于提高Mura缺陷检测的检测效率以及精度,并与点、线缺陷检测方法相辅相成,以完善屏幕的缺陷检测工序。This embodiment also provides a mura defect detection method, which is used to improve the detection efficiency and accuracy of mura defect detection, and complements the point and line defect detection method to improve the defect detection process of the screen.
请参阅图2,图2为本发明实施例提供的一种Mura缺陷检测方法的流程图。Please refer to FIG. 2 . FIG. 2 is a flowchart of a mura defect detection method provided by an embodiment of the present invention.
该Mura缺陷检测方法包括如下步骤:The Mura defect detection method comprises the steps:
S201、采集屏幕图像,并进行Mura缺陷检测。S201. Collect a screen image, and perform mura defect detection.
在该步骤中,采集屏幕图像作为样本,并对这些屏幕图像进行Mura检测。In this step, screen images are collected as samples, and mura detection is performed on these screen images.
S202、当出现Mura缺陷时,将该屏幕标记为有缺陷屏幕;当不存在Mura缺陷时,将该屏幕标记为无缺陷屏幕。S202. When a mura defect occurs, mark the screen as a defective screen; when there is no mura defect, mark the screen as a non-defective screen.
该步骤用于给样本图像进行分类,为后续屏幕Mura检测时奠定基础。This step is used to classify the sample images and lay the foundation for the subsequent screen Mura detection.
S203、建立样本图像数据库,重复上述步骤,直至采集到满足检测精度的足够数量的样本图像,并将样本图像储存于所述样本图像数据库中。S203. Establish a sample image database, and repeat the above steps until a sufficient number of sample images meeting the detection accuracy are collected, and store the sample images in the sample image database.
将步骤S202中经过归类标记的样本图像均储存于样本图像数据库中,后续在Mura检测工序中,将待检测屏幕图像与这些样本图像进行比对。经过样本分类标记储存,能够锻炼检测的神经网络,随着检测数量的上升,Mura检测越来越智能,则Mura检测的精度也会随之增长。The sample images classified and marked in step S202 are all stored in the sample image database, and then in the mura detection process, the screen image to be detected is compared with these sample images. After the samples are classified and marked, the neural network for detection can be trained. As the number of detections increases and the Mura detection becomes more and more intelligent, the accuracy of Mura detection will also increase accordingly.
实施例二Embodiment two
基于实施例一所提供的屏幕检测方法,本实施例二相应地提供一种屏幕检测系统。Based on the screen detection method provided in the first embodiment, the second embodiment correspondingly provides a screen detection system.
请参阅图3,图3为本发明实施例提供的一种屏幕检测系统的结构示意图。Please refer to FIG. 3 . FIG. 3 is a schematic structural diagram of a screen detection system provided by an embodiment of the present invention.
该屏幕检测系统包括:The screen detection system includes:
待料区10,用于接收从流水线传送过来的、待检测的屏幕。其中,待料区10上设有读码器,通过该读码器实现待检测屏幕ID的读取,将ID与待检测屏幕绑定起来,以便于后续各个屏幕信息的追溯。The material waiting area 10 is used to receive screens to be inspected transmitted from the assembly line. Wherein, a code reader is provided on the waiting area 10, and the ID of the screen to be detected is read through the code reader, and the ID is bound to the screen to be detected, so as to facilitate the traceability of subsequent screen information.
第一抓取机构20,用于在检测前将待检测屏幕从待料区10抓取放至检测区30,在检测完成后将检测完成的屏幕抓取放至下一工位。在本实施例中,第一抓取机构20为六轴机器人,且该第一抓取机构20设有两个,以提高工作效率。The first grabbing mechanism 20 is used to grab the screen to be inspected from the waiting area 10 to the inspection area 30 before inspection, and grab the inspected screen to the next station after the inspection is completed. In this embodiment, the first grabbing mechanism 20 is a six-axis robot, and there are two first grabbing mechanisms 20 to improve work efficiency.
检测区30,位于待料区10一侧,并与待料区10一同围设于第一抓取机构20外,这样的位置设置使该屏幕检测系统结构紧凑,一定程度上也提高了检测效率。The detection area 30 is located on the side of the waiting area 10, and is surrounded by the first grasping mechanism 20 together with the waiting area 10. Such a position setting makes the screen detection system compact and improves the detection efficiency to a certain extent. .
工作站31,该工作站31与Mes系统建立连接,并与读码器和检测区30各装置电连接,用于将屏幕检测画面信息发送给Mes系统,以便于查询以及追溯。Workstation 31. The workstation 31 is connected to the Mes system, and is electrically connected to the code reader and the devices in the detection area 30, and is used to send the screen detection picture information to the Mes system for query and traceability.
其中,检测区30包括:Wherein, detection area 30 comprises:
安装架,用于为各机构提供支撑作用。所述安装架上设有对位平台33,所述对位平台33上设有工作台,该工作台用于放置待检测屏幕。所述安装架上还设有第二抓取机构35,所述第二抓取机构35用于将待检测屏幕固定于工作台上。其中,该第二抓取机构35为单轴机械手。此外,工作台下方设有背光源,该背光源电连接有光源控制器32。The mounting frame is used to provide support for each mechanism. An alignment platform 33 is provided on the installation frame, and a workbench is arranged on the alignment platform 33, and the workbench is used for placing the screen to be tested. A second grabbing mechanism 35 is also provided on the mounting frame, and the second grabbing mechanism 35 is used to fix the screen to be tested on the workbench. Wherein, the second grasping mechanism 35 is a single-axis manipulator. In addition, a backlight is provided under the workbench, and the backlight is electrically connected to a light source controller 32 .
采集装置34,装设于安装架上,并位于工作台的上方,用于采集屏幕上的图像。在本实施例中,该采集装置34为高像素工业相机,用于采集待检测屏幕的图像,以实现屏幕的检测功能。其中,所述安装架上设有调整单轴,所述采集装置34通过所述调整单轴装设于安装架上,所述调整单轴用于调整采集装置34与待检测屏幕之间的距离,在检测前可针对不同尺寸的屏幕通过调整单轴调整采集装置34的物距,以适应不同尺寸的屏幕。The acquisition device 34 is installed on the installation frame and located above the workbench, and is used to acquire images on the screen. In this embodiment, the acquisition device 34 is a high-pixel industrial camera, which is used to acquire images of the screen to be inspected, so as to realize the inspection function of the screen. Wherein, the mounting frame is provided with an adjustment single axis, and the acquisition device 34 is installed on the installation frame through the adjustment single axis, and the adjustment single axis is used to adjust the distance between the acquisition device 34 and the screen to be detected , the object distance of the acquisition device 34 can be adjusted for screens of different sizes by adjusting the single axis before detection, so as to adapt to screens of different sizes.
储存装置,电连接所述采集装置34以及工作站31,用于储存经过所述采集装置34采集所得样本图像数据库。The storage device is electrically connected to the collection device 34 and the workstation 31 , and is used for storing the sample image database collected by the collection device 34 .
判断装置,电连接所述采集装置34以及工作站31,用于判断图像是否存在缺陷。The judging device is electrically connected to the acquisition device 34 and the workstation 31, and is used for judging whether there is a defect in the image.
视觉对位装置,所述视觉对位装置电连接所述对位平台33,并对准所述工作台,用于实现屏幕方位的调整。通过视觉对位装置以及对位平台33相配合,使待检测屏幕上的mark点与探针位置相匹配;调整好待检测屏幕的方位后,通过探针下压实现屏幕的导通。A visual alignment device, the visual alignment device is electrically connected to the alignment platform 33 and aligned with the workbench for adjusting the orientation of the screen. Through the cooperation of the visual alignment device and the alignment platform 33, the mark point on the screen to be detected is matched with the position of the probe; after the orientation of the screen to be detected is adjusted, the conduction of the screen is realized by pressing down the probe.
在本实施例中,该屏幕检测系统还包括:In this embodiment, the screen detection system also includes:
自动上下料模块,具体为包括上下料伺服机构、基于机器视觉的自动对位模块、机器人拾取模块、点灯探针气缸控制模块、读取屏幕ID模块、控制模块、安全防护模块等。主要用到运动控制技术及机器人自动对位等技术。Automatic loading and unloading module, specifically including loading and unloading servo mechanism, automatic alignment module based on machine vision, robot picking module, lighting probe cylinder control module, reading screen ID module, control module, safety protection module, etc. It mainly uses motion control technology and robot automatic alignment technology.
缺陷检测模块:包括图像采集模块、光源照明模块、图像处理硬件模块和图像处理算法模块等。主要用到光建模技术、检测识别技术及大数据实时处理技术。Defect detection module: including image acquisition module, light source lighting module, image processing hardware module and image processing algorithm module, etc. It mainly uses optical modeling technology, detection and recognition technology and big data real-time processing technology.
信息化模块:包括产品质量信息数据库、设备状态检测模块。主要用到网络数据库技术、大数据分析技术。例如,用于采集设备用电情况的电流传感器、用于监测来料数的计数传感器,以及用于实时监测第一抓取机构20和第二抓取机构35运行状况的运行控制器,以便于工作人员实时了解设备的工作状态。该电流传感器、计数传感器以及运行控制器均与工作站31电连接。Information module: including product quality information database and equipment status detection module. It mainly uses network database technology and big data analysis technology. For example, the current sensor used to collect the power consumption of the equipment, the counting sensor used to monitor the number of incoming materials, and the operation controller used to monitor the operating conditions of the first grabbing mechanism 20 and the second grabbing mechanism 35 in real time, so that The staff can know the working status of the equipment in real time. The current sensor, counting sensor and operation controller are all electrically connected to the workstation 31 .
在本实施例中,待检测屏幕从上一工位清洗机构通过传送带传送至待料区10,并在这个过程中通过读码器实现ID的读取,将ID和液晶片绑定起来。第一抓取机构20收到可上料信号后,将待检测屏幕抓取到检测区30中的工作台上,通过视觉对位装置和对位平台33实现探针对位、下压接通电路,再通过点灯板点亮,切换屏幕的不同画面,在切换屏幕的同时进行采集装置34进行拍照处理,在判断装置中对检测的数据分析,将结果传送至工作站31后,上传至Mes系统,并储存至储存装置中。检测完后,通过一下料机械手根据检测结果将检测完成后的屏幕对应搬运到相应区域。In this embodiment, the screen to be inspected is transported from the cleaning mechanism of the previous station to the waiting area 10 through the conveyor belt, and the ID is read by the code reader during this process, and the ID and the liquid crystal are bound together. After the first grasping mechanism 20 receives the signal that the material can be loaded, it grasps the screen to be detected onto the workbench in the detection area 30, and realizes the probe alignment and push-down connection through the visual alignment device and the alignment platform 33 The circuit is then lit by the lighting board to switch different screens of the screen. While switching the screen, the acquisition device 34 is used to take pictures, analyze the detected data in the judgment device, and transmit the results to the workstation 31 before uploading to the Mes system , and save to storage. After the detection, the screen after detection is transported to the corresponding area by the unloading manipulator according to the detection result.
工作人员能够通过电流传感器实时监测设备的用电情况、通过控制器监测机械手的运行状况、通过读码器读取待检测屏幕的二维码信息、以及通过计数传感器获取来料的速度,此外,通过工作站31获取到当前的来料总数,以及正常屏幕与缺陷屏幕的的比例情况,最后将结果实时传送Mes系统,让远在办公室的管理人员实时的查询和了解最新的生产状态,从而为工厂的智能制造提供数据基础和信息基础。The staff can monitor the power consumption of the equipment in real time through the current sensor, monitor the operation status of the manipulator through the controller, read the two-dimensional code information of the screen to be detected through the code reader, and obtain the speed of the incoming material through the counting sensor. In addition, The current total number of incoming materials and the ratio of normal screens to defective screens are obtained through the workstation 31, and finally the results are transmitted to the Mes system in real time, allowing managers far away in the office to inquire and understand the latest production status in real time, thus providing for the factory Intelligent manufacturing provides data foundation and information foundation.
本发明所提供的屏幕检测方法和屏幕检测系统,结合了利用像素灰度值周期检测屏幕缺陷的技术、以深度学习为基础的相关(软、硬件)技术、物联网技术、机器人自动上下料技术等为主的现代自动化产业前沿技术,实现了液晶屏从上料、自动检测、数据上传、下料的全自动一体化检测系统。深度学习技术通过计算机自动识别液晶屏缺陷特征,并检测缺陷,省去了前一代检测系统复杂的参数调试步骤;物联网技术可以实时对检测产品进行数据汇总并上传,工作人员可以在PC端追溯每个产品的检测数据,以便及时分析和处理;以机器人对位技术为主的机器人上下料技术,解决了物料从上料、对位、检测、自动分类下料等一系列操作。通过上述技术手段达到了将一个屏幕画面的检测时间控制在1.2S以内的效果,在确保检测精度的同时大大提高了检测效率。The screen detection method and screen detection system provided by the present invention combine the technology of periodically detecting screen defects by using the pixel gray value, the related (software and hardware) technology based on deep learning, Internet of Things technology, robot automatic loading and unloading technology The cutting-edge technology of the modern automation industry, etc., has realized a fully automatic integrated detection system for LCD screens from loading, automatic detection, data uploading, and unloading. The deep learning technology automatically identifies the defect characteristics of the LCD screen through the computer and detects the defects, eliminating the complicated parameter debugging steps of the previous generation of detection systems; the Internet of Things technology can collect and upload the data of the detected products in real time, and the staff can trace back on the PC side The detection data of each product can be analyzed and processed in time; the robot loading and unloading technology based on robot alignment technology solves a series of operations such as material loading, alignment, detection, and automatic classification and unloading. Through the above-mentioned technical means, the effect of controlling the detection time of a screen image within 1.2S is achieved, and the detection efficiency is greatly improved while ensuring the detection accuracy.
以上所述,以上实施例仅用以说明本发明的技术方案,而非对其限制;尽管参照前述实施例对本发明进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still understand the foregoing The technical solutions recorded in each embodiment are modified, or some of the technical features are replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810746927.8A CN108844966A (en) | 2018-07-09 | 2018-07-09 | Screen detection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810746927.8A CN108844966A (en) | 2018-07-09 | 2018-07-09 | Screen detection method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108844966A true CN108844966A (en) | 2018-11-20 |
Family
ID=64195963
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810746927.8A Pending CN108844966A (en) | 2018-07-09 | 2018-07-09 | Screen detection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108844966A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109856824A (en) * | 2018-12-21 | 2019-06-07 | 惠科股份有限公司 | Display picture detection method and detection system thereof |
CN110781888A (en) * | 2019-10-25 | 2020-02-11 | 北京字节跳动网络技术有限公司 | Method and device for regressing screen in video picture, readable medium and electronic equipment |
CN111260612A (en) * | 2020-01-09 | 2020-06-09 | 北京良业环境技术股份有限公司 | LED screen fault diagnosis method on street lamp |
CN111340795A (en) * | 2020-03-09 | 2020-06-26 | 珠海格力智能装备有限公司 | Method and device for determining quality of article |
CN111598869A (en) * | 2020-04-03 | 2020-08-28 | 惠州高视科技有限公司 | Method, equipment and storage medium for detecting Mura of display screen |
CN114136981A (en) * | 2021-11-26 | 2022-03-04 | 广东速美达自动化股份有限公司 | Detection method and detection system for Mylar film of lithium battery pack |
CN114879388A (en) * | 2021-02-05 | 2022-08-09 | 合肥统旭智慧科技有限公司 | Intelligent detection method for monitoring display picture of liquid crystal display |
CN117152103A (en) * | 2023-09-08 | 2023-12-01 | 深圳市明昌光电科技有限公司 | Display screen point defect, line defect and Mura defect judging method, system and device |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004239733A (en) * | 2003-02-05 | 2004-08-26 | Seiko Epson Corp | Screen defect detection method and apparatus |
US20070296962A1 (en) * | 2006-06-22 | 2007-12-27 | Akio Ishikawa | Surface inspection apparatus and surface inspection method |
CN103792705A (en) * | 2014-01-28 | 2014-05-14 | 北京京东方显示技术有限公司 | Detecting method and detecting device for detecting substrate defects |
US20140204202A1 (en) * | 2013-01-18 | 2014-07-24 | Nuflare Technology, Inc. | Inspection apparatus |
CN104252056A (en) * | 2014-09-18 | 2014-12-31 | 京东方科技集团股份有限公司 | Detection method and device of substrate |
CN104732900A (en) * | 2013-12-20 | 2015-06-24 | 昆山国显光电有限公司 | Pixel defect detection method and device |
CN106019650A (en) * | 2016-06-16 | 2016-10-12 | 昆山金箭机械设备有限公司 | Liquid crystal display screen detecting equipment with location function |
CN106054421A (en) * | 2016-07-28 | 2016-10-26 | 京东方科技集团股份有限公司 | Liquid crystal display panel defect detecting method and device |
CN205720971U (en) * | 2016-06-16 | 2016-11-23 | 昆山金箭机械设备有限公司 | There is the LCD screen detection equipment of positioning function |
CN106650770A (en) * | 2016-09-29 | 2017-05-10 | 南京大学 | Mura defect detection method based on sample learning and human visual characteristics |
CN106875373A (en) * | 2016-12-14 | 2017-06-20 | 浙江大学 | Mobile phone screen MURA defect inspection methods based on convolutional neural networks pruning algorithms |
CN107272234A (en) * | 2017-07-31 | 2017-10-20 | 上海斐讯数据通信技术有限公司 | A kind of detection method and system based on lcd panel test picture |
CN107402221A (en) * | 2017-08-08 | 2017-11-28 | 广东工业大学 | A kind of defects of display panel recognition methods and system based on machine vision |
CN107845087A (en) * | 2017-10-09 | 2018-03-27 | 深圳市华星光电半导体显示技术有限公司 | The detection method and system of the uneven defect of liquid crystal panel lightness |
CN107966836A (en) * | 2017-11-29 | 2018-04-27 | 南昌工程学院 | TFT-L CD defect optical automatic detection system |
CN108171707A (en) * | 2018-01-23 | 2018-06-15 | 武汉精测电子集团股份有限公司 | A kind of Mura defects level evaluation method and device based on deep learning |
-
2018
- 2018-07-09 CN CN201810746927.8A patent/CN108844966A/en active Pending
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004239733A (en) * | 2003-02-05 | 2004-08-26 | Seiko Epson Corp | Screen defect detection method and apparatus |
US20070296962A1 (en) * | 2006-06-22 | 2007-12-27 | Akio Ishikawa | Surface inspection apparatus and surface inspection method |
US20140204202A1 (en) * | 2013-01-18 | 2014-07-24 | Nuflare Technology, Inc. | Inspection apparatus |
CN104732900A (en) * | 2013-12-20 | 2015-06-24 | 昆山国显光电有限公司 | Pixel defect detection method and device |
CN103792705A (en) * | 2014-01-28 | 2014-05-14 | 北京京东方显示技术有限公司 | Detecting method and detecting device for detecting substrate defects |
CN104252056A (en) * | 2014-09-18 | 2014-12-31 | 京东方科技集团股份有限公司 | Detection method and device of substrate |
CN205720971U (en) * | 2016-06-16 | 2016-11-23 | 昆山金箭机械设备有限公司 | There is the LCD screen detection equipment of positioning function |
CN106019650A (en) * | 2016-06-16 | 2016-10-12 | 昆山金箭机械设备有限公司 | Liquid crystal display screen detecting equipment with location function |
CN106054421A (en) * | 2016-07-28 | 2016-10-26 | 京东方科技集团股份有限公司 | Liquid crystal display panel defect detecting method and device |
CN106650770A (en) * | 2016-09-29 | 2017-05-10 | 南京大学 | Mura defect detection method based on sample learning and human visual characteristics |
CN106875373A (en) * | 2016-12-14 | 2017-06-20 | 浙江大学 | Mobile phone screen MURA defect inspection methods based on convolutional neural networks pruning algorithms |
CN107272234A (en) * | 2017-07-31 | 2017-10-20 | 上海斐讯数据通信技术有限公司 | A kind of detection method and system based on lcd panel test picture |
CN107402221A (en) * | 2017-08-08 | 2017-11-28 | 广东工业大学 | A kind of defects of display panel recognition methods and system based on machine vision |
CN107845087A (en) * | 2017-10-09 | 2018-03-27 | 深圳市华星光电半导体显示技术有限公司 | The detection method and system of the uneven defect of liquid crystal panel lightness |
CN107966836A (en) * | 2017-11-29 | 2018-04-27 | 南昌工程学院 | TFT-L CD defect optical automatic detection system |
CN108171707A (en) * | 2018-01-23 | 2018-06-15 | 武汉精测电子集团股份有限公司 | A kind of Mura defects level evaluation method and device based on deep learning |
Non-Patent Citations (4)
Title |
---|
严成宸等: "结合加权模板差图与双边滤波的TFT-LCD检测算法", 《电子测量与仪器学报》 * |
朱炳斐等: "基于Fourier-Mellin变换的液晶显示屏", 《激光与光电子学进展》 * |
简川霞: "TFT-LCD表面缺陷检测方法综述", 《电视技术》 * |
苏小红等: "TFT-LCD微米级显示缺陷的自动检测算法", 《哈尔冰年工业大学学报》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109856824A (en) * | 2018-12-21 | 2019-06-07 | 惠科股份有限公司 | Display picture detection method and detection system thereof |
CN109856824B (en) * | 2018-12-21 | 2022-05-17 | 惠科股份有限公司 | Display picture detection method and detection system thereof |
CN110781888A (en) * | 2019-10-25 | 2020-02-11 | 北京字节跳动网络技术有限公司 | Method and device for regressing screen in video picture, readable medium and electronic equipment |
CN111260612A (en) * | 2020-01-09 | 2020-06-09 | 北京良业环境技术股份有限公司 | LED screen fault diagnosis method on street lamp |
CN111340795A (en) * | 2020-03-09 | 2020-06-26 | 珠海格力智能装备有限公司 | Method and device for determining quality of article |
CN111340795B (en) * | 2020-03-09 | 2023-11-10 | 珠海格力智能装备有限公司 | Method and device for determining quality of article |
CN111598869A (en) * | 2020-04-03 | 2020-08-28 | 惠州高视科技有限公司 | Method, equipment and storage medium for detecting Mura of display screen |
CN114879388A (en) * | 2021-02-05 | 2022-08-09 | 合肥统旭智慧科技有限公司 | Intelligent detection method for monitoring display picture of liquid crystal display |
CN114879388B (en) * | 2021-02-05 | 2023-07-11 | 合肥统旭智慧科技有限公司 | Intelligent detection method for monitoring display picture of liquid crystal display |
CN114136981A (en) * | 2021-11-26 | 2022-03-04 | 广东速美达自动化股份有限公司 | Detection method and detection system for Mylar film of lithium battery pack |
CN117152103A (en) * | 2023-09-08 | 2023-12-01 | 深圳市明昌光电科技有限公司 | Display screen point defect, line defect and Mura defect judging method, system and device |
CN117152103B (en) * | 2023-09-08 | 2024-06-07 | 深圳市明昌光电科技有限公司 | Display screen point defect, line defect and Mura defect judging method, system and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108844966A (en) | Screen detection method and system | |
CN102928441B (en) | A kind of scanned type automatic optical detection system | |
CN110216080A (en) | Quality monitoring system of PCB processing production line based on image contrast | |
CN108318853A (en) | A kind of detection method for sorting and device for tearing back electric energy meter open | |
CN110108726A (en) | A fully automatic optical inspection system for chip inspection | |
CN104570411A (en) | Multistation light-on AOI (automatic optical inspection) system | |
CN204602651U (en) | A kind of AOI checkout equipment | |
CN113588653A (en) | System and method for detecting and tracking quality of aluminum anode carbon block | |
CN118448292B (en) | Wafer microscopic detection system based on machine vision and automation technology | |
CN110335239A (en) | Defects detection training machine and its application method based on deep learning | |
CN107238955A (en) | Liquid crystal module screen detecting system | |
CN112718552A (en) | Automatic quality defect inspection device for LED circuit board and working method thereof | |
CN106645185A (en) | Method and device for intelligently detecting surface quality of industrial parts | |
CN118305101A (en) | Automatic bearing defect detection system and method | |
WO2023045037A1 (en) | Automatic sorting system and method | |
CN108972556A (en) | Conducting wire grasping system and method on small and special electric machine production line under complex illumination environment | |
CN112730442A (en) | Automatic online product surface defect detection device and system based on machine vision | |
CN119023577A (en) | A visual inspection system and method for production line of intelligent factory | |
CN112213081A (en) | Screen body detection equipment | |
CN209680599U (en) | An automatic detection device for auto parts | |
CN106526448A (en) | Automatic detecting system and detection method for power supply drive board | |
CN207198050U (en) | A kind of PLC outward appearances and LED status detection means based on machine vision | |
CN217385266U (en) | Stitch detection device for special-shaped component | |
CN213364197U (en) | Screen body detection equipment | |
CN105699385B (en) | The other detecting system of the defect layer of spatial light modulator and detection method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: Room 201, building 4, 780 xiecao Road, Xiegang Town, Dongguan City, Guangdong Province 523000 Applicant after: GUANGDONG SUMIDA AUTOMATION Co.,Ltd. Address before: 523000 Guangdong province Dongguan city Changan town Xiaobian Plainvim industrial center building two floor A District Applicant before: GUANGDONG SUMIDA AUTOMATION Co.,Ltd. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181120 |