CN107248151B - A method and system for intelligent detection of liquid crystal sheets based on machine vision - Google Patents
A method and system for intelligent detection of liquid crystal sheets based on machine vision Download PDFInfo
- Publication number
- CN107248151B CN107248151B CN201710260493.6A CN201710260493A CN107248151B CN 107248151 B CN107248151 B CN 107248151B CN 201710260493 A CN201710260493 A CN 201710260493A CN 107248151 B CN107248151 B CN 107248151B
- Authority
- CN
- China
- Prior art keywords
- liquid crystal
- image
- detected
- crystal panel
- binarized
- 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.)
- Active
Links
- 239000004973 liquid crystal related substance Substances 0.000 title claims abstract description 321
- 238000001514 detection method Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000011218 segmentation Effects 0.000 claims description 22
- 238000001914 filtration Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000007261 regionalization Effects 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 description 7
- 230000003993 interaction Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011089 mechanical engineering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30148—Semiconductor; IC; Wafer
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Testing Of Optical Devices Or Fibers (AREA)
- Liquid Crystal (AREA)
Abstract
本发明公开了一种基于机器视觉的液晶片智能检测方法及系统，方法包括分别获取标准的液晶片和待检测液晶片在夹持装置未夹紧状态下的图像和在夹紧状态下的图像，并将两者图像通过投影算法进行配准，最后将两者图像作差，得出两者图像的不同区域，从而对其进行检测判断。系统包括标准图像获取单元、标准图像二值化单元、待检测图像获取单元、待检测图像二值化单元、图像配准单元和检测判断单元。本发明通过对待检测液晶片二值化图像与标准液晶片二值化模板图像进行像素点的对比从而检测液晶片的质量，有效提高液晶片检测过程中的检测效率，降低漏检误检率并降低人工成本，提高生产节拍。本发明可广泛应用于液晶片检测中。
The invention discloses a method and a system for intelligent detection of liquid crystal sheets based on machine vision. The method comprises respectively acquiring images of a standard liquid crystal sheet and a liquid crystal sheet to be detected in the unclamped state and the clamped state of the clamping device. , and register the two images through the projection algorithm, and finally make a difference between the two images to obtain different areas of the two images, so as to detect and judge them. The system includes a standard image acquisition unit, a standard image binarization unit, a to-be-detected image acquisition unit, a to-be-detected image binarization unit, an image registration unit and a detection and judgment unit. The invention detects the quality of the liquid crystal sheet by comparing the pixel points between the binarized image of the liquid crystal sheet to be detected and the binarized template image of the standard liquid crystal sheet, thereby effectively improving the detection efficiency in the liquid crystal sheet detection process, reducing the rate of missed detection and false detection, and reducing the false detection rate. Reduce labor costs and increase production tact. The invention can be widely used in liquid crystal plate detection.
Description
技术领域technical field
本发明涉及液晶片检测技术领域，尤其涉及一种基于机器视觉的液晶片智能检测方法及系统。The invention relates to the technical field of liquid crystal sheet detection, in particular to a liquid crystal sheet intelligent detection method and system based on machine vision.
背景技术Background technique
机器视觉是一项综合技术，包括图像处理、机械工程技术、控制、电光源照明、光学成像、传感器、模拟与数字视频技术、计算机软硬件技术(图像增强和分析算法、图像卡、I/O卡等)。一个典型的机器视觉应用系统包括图像捕捉、光源系统、图像数字化模块、数字图像处理模块、智能判断决策模块和机械控制执行模块。Machine vision is a comprehensive technology, including image processing, mechanical engineering technology, control, electric light source lighting, optical imaging, sensors, analog and digital video technology, computer software and hardware technology (image enhancement and analysis algorithms, image cards, I/O card, etc.). A typical machine vision application system includes image capture, light source system, image digitization module, digital image processing module, intelligent judgment decision module and mechanical control execution module.
机器视觉系统的特点是提高生产的柔性和自动化程度。在一些不适合于人工作业的危险工作环境或人工视觉难以满足要求的场合，常用机器视觉来替代人工视觉；同时在大批量工业生产过程中，用人工视觉检查产品质量效率低且精度不高，用机器视觉检测方法可以大大提高生产效率和生产的自动化程度。而且机器视觉易于实现信息集成，是实现计算机集成制造的基础技术。The feature of machine vision system is to improve the flexibility and automation of production. In some dangerous working environments that are not suitable for manual work or where artificial vision is difficult to meet the requirements, machine vision is often used to replace artificial vision; at the same time, in the process of mass industrial production, using artificial vision to check product quality is inefficient and not accurate. , The use of machine vision detection methods can greatly improve production efficiency and production automation. Moreover, machine vision is easy to realize information integration, which is the basic technology to realize computer integrated manufacturing.
液晶片智能检测技术现代亟需的一种检测技术，在传统的检测方法中，液晶片的质量检测主要依赖工人人眼检测，但是由于工人自身的主观性和视觉疲劳性，就使得这种检测方法存在着检测标准受个人主观因素影响，漏检误检率高，人工成本高等缺点。The intelligent detection technology of LCD panels is a detection technology that is urgently needed in modern times. In the traditional detection methods, the quality detection of LCD panels mainly relies on the detection of workers' eyes. However, due to the subjectivity and visual fatigue of workers themselves, this detection method The method has the disadvantages that the detection standard is affected by individual subjective factors, the rate of missed detection and false detection is high, and the labor cost is high.
发明内容SUMMARY OF THE INVENTION
为了解决上述技术问题，本发明的目的是提供一种能提高检测效率，且能降低漏检误检率的一种基于机器视觉的液晶片智能检测方法及系统。In order to solve the above technical problems, the purpose of the present invention is to provide a liquid crystal panel intelligent detection method and system based on machine vision, which can improve the detection efficiency and reduce the rate of missed detection and false detection.
本发明所采取的技术方案是：The technical scheme adopted by the present invention is:
一种基于机器视觉的液晶片智能检测方法，包括以下步骤：An intelligent detection method for liquid crystal sheets based on machine vision, comprising the following steps:
获取标准液晶片在夹持装置未夹紧状态下的图像和在夹紧状态下的图像，得到标准液晶片未夹紧图像和标准液晶片夹紧图像；Obtain the image of the standard liquid crystal sheet in the unclamped state of the clamping device and the image in the clamped state, and obtain the unclamped image of the standard liquid crystal sheet and the clamped image of the standard liquid crystal sheet;
对标准液晶片未夹紧图像和标准液晶片夹紧图像进行处理，得到标准液晶片二值化模板图像；Process the unclamped image of the standard liquid crystal sheet and the clamped image of the standard liquid crystal sheet to obtain the binarized template image of the standard liquid crystal sheet;
获取待检测液晶片在夹持装置未夹紧状态下的图像和在夹紧状态下的图像，得到待检测液晶片未夹紧图像和待检测液晶片夹紧图像；acquiring the image of the liquid crystal sheet to be detected in the unclamped state of the clamping device and the image in the clamped state, to obtain the unclamped image of the liquid crystal sheet to be detected and the clamped image of the liquid crystal sheet to be detected;
对待检测液晶片未夹紧图像和待检测液晶片夹紧图像进行处理，得到待检测液晶片二值化图像；The unclamped image of the liquid crystal sheet to be detected and the clamped image of the liquid crystal sheet to be detected are processed to obtain a binarized image of the liquid crystal sheet to be detected;
将待检测液晶片二值化图像与标准液晶片二值化模板图像通过投影算法进行配准；Register the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel through a projection algorithm;
将待检测液晶片二值化图像与标准液晶片二值化模板图像作差，得出两者图像的不同，并对其进行检测判断。The difference between the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel is obtained, and the difference between the two images is obtained and detected and judged.
作为所述的一种基于机器视觉的液晶片智能检测方法的进一步改进，所述的对标准液晶片未夹紧图像和标准液晶片夹紧图像进行处理，得到标准液晶片二值化模板图像，这一步骤具体包括：As a further improvement of the machine vision-based liquid crystal panel intelligent detection method, the standard liquid crystal panel unclamped image and the standard liquid crystal panel clamped image are processed to obtain a standard liquid crystal panel binarized template image, This step specifically includes:
对标准液晶片未夹紧图像和标准液晶片夹紧图像进行高斯滤波；Gaussian filtering is performed on the unclamped image of the standard liquid crystal sheet and the clamped image of the standard liquid crystal sheet;
对高斯滤波处理后得到的两个图像通过区域化自动阈值分割算法进行二值化处理，得到标准液晶片未夹紧二值化图像和标准液晶片夹紧二值化图像；The two images obtained after the Gaussian filtering process are binarized by the regionalized automatic threshold segmentation algorithm, and the standard liquid crystal panel unclamped binarized image and the standard liquid crystal panel clamped binarized image are obtained;
将标准液晶片未夹紧二值化图像和标准液晶片夹紧二值化图像作差，得到标准液晶片二值化模板图像。A difference is made between the un-clamped binarized image of the standard liquid crystal panel and the clamped binarized image of the standard liquid crystal panel to obtain a binarized template image of the standard liquid crystal panel.
作为所述的一种基于机器视觉的液晶片智能检测方法的进一步改进，所述的对待检测液晶片未夹紧图像和待检测液晶片夹紧图像进行处理，得到待检测液晶片二值化图像，这一步骤具体包括：As a further improvement of the method for intelligent detection of liquid crystal panels based on machine vision, the unclamped image of the liquid crystal panel to be detected and the clamped image of the liquid crystal panel to be detected are processed to obtain a binarized image of the liquid crystal panel to be detected , this step specifically includes:
对待检测液晶片未夹紧图像和待检测液晶片夹紧图像进行高斯滤波；Gaussian filtering is performed on the unclamped image of the liquid crystal sheet to be detected and the clamped image of the liquid crystal sheet to be detected;
对高斯滤波处理后得到的两个图像通过区域化自动阈值分割算法进行二值化处理，得到待检测液晶片未夹紧二值化图像和待检测液晶片夹紧二值化图像；Perform binarization processing on the two images obtained after the Gaussian filter processing through the regionalized automatic threshold segmentation algorithm, to obtain the un-clamped binarized image of the liquid crystal panel to be detected and the clamped binarized image of the liquid crystal panel to be detected;
将待检测液晶片未夹紧二值化图像和待检测液晶片夹紧二值化图像作差，得到待检测液晶片二值化图像。A difference is made between the unclamped binarized image of the liquid crystal sheet to be detected and the clamped binarized image of the liquid crystal sheet to be detected to obtain the binarized image of the liquid crystal sheet to be detected.
作为所述的一种基于机器视觉的液晶片智能检测方法的进一步改进，所述的将待检测液晶片二值化图像与标准液晶片二值化模板图像通过投影算法进行配准，这一步骤具体包括：As a further improvement of the method for intelligent detection of liquid crystal panels based on machine vision, the process of registering the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel through a projection algorithm, this step Specifically include:
对待检测液晶片二值化图像与标准液晶片二值化模板图像分别建立高斯金字塔，得到待检测液晶片多层金字塔图像和标准液晶片多层金字塔图像；A Gaussian pyramid is established respectively for the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel to obtain a multi-layer pyramid image of the liquid crystal panel to be detected and a multi-layer pyramid image of the standard liquid crystal panel;
对待检测液晶片多层金字塔图像和标准液晶片多层金字塔图像通过投影算法从上到下逐层进行配准。The multi-layer pyramid image of the liquid crystal panel to be tested and the multi-layer pyramid image of the standard liquid crystal panel are registered layer by layer from top to bottom through the projection algorithm.
作为所述的一种基于机器视觉的液晶片智能检测方法的进一步改进，所述的将待检测液晶片二值化图像与标准液晶片二值化模板图像作差，得出两者图像的不同，并对其进行检测判断，这一步骤具体包括：As a further improvement of the method for intelligent detection of liquid crystal panels based on machine vision, the difference between the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel is obtained to obtain the difference between the two images. , and detect and judge it. This step specifically includes:
将待检测液晶片二值化图像与标准液晶片二值化模板图像作差，得出差异点数量，并进行显示；Differentiate the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel to obtain the number of difference points and display them;
判断差异点数量是否大于预设的检测阈值，若是，则表示当前的待检测液晶片不合格；反之，则表示待检测液晶片合格。It is judged whether the number of difference points is greater than the preset detection threshold, and if so, it means that the current liquid crystal sheet to be tested is unqualified; otherwise, it means that the liquid crystal sheet to be tested is qualified.
作为所述的一种基于机器视觉的液晶片智能检测方法的进一步改进，所述的区域化自动阈值分割算法中最佳阈值的计算公式为：As a further improvement of the described liquid crystal panel intelligent detection method based on machine vision, the calculation formula of the optimal threshold in the described regionalized automatic threshold segmentation algorithm is:
其中，t表示分割的阈值，w0为背景比例，u0为背景均值，w1为前景比例，u1为前景均值，u为整幅图像的均值，当以上表达式值最大的t，即为分割图像的最佳阈值。Among them, t represents the threshold of segmentation, w 0 is the background ratio, u 0 is the background mean, w 1 is the foreground ratio, u 1 is the foreground mean, and u is the mean of the entire image. When the above expression has the largest t, that is is the best threshold for segmenting the image.
本发明所采用的另一技术方案是：Another technical scheme adopted by the present invention is:
一种基于机器视觉的液晶片智能检测系统，包括：A liquid crystal sheet intelligent detection system based on machine vision, comprising:
标准图像获取单元，用于获取标准液晶片在夹持装置未夹紧状态下的图像和在夹紧状态下的图像，得到标准液晶片未夹紧图像和标准液晶片夹紧图像；The standard image acquisition unit is used to acquire the image of the standard liquid crystal sheet in the unclamped state of the clamping device and the image in the clamped state, and obtain the unclamped image of the standard liquid crystal sheet and the clamped image of the standard liquid crystal sheet;
标准图像二值化单元，用于对标准液晶片未夹紧图像和标准液晶片夹紧图像进行处理，得到标准液晶片二值化模板图像；The standard image binarization unit is used to process the unclamped image of the standard liquid crystal panel and the clamped image of the standard liquid crystal panel to obtain a binarized template image of the standard liquid crystal panel;
待检测图像获取单元，用于获取待检测液晶片在夹持装置未夹紧状态下的图像和在夹紧状态下的图像，得到待检测液晶片未夹紧图像和待检测液晶片夹紧图像；The image acquisition unit to be detected is used to acquire the image of the liquid crystal sheet to be detected in the unclamped state of the clamping device and the image in the clamped state, and obtain the unclamped image of the liquid crystal sheet to be detected and the clamped image of the liquid crystal sheet to be detected ;
待检测图像二值化单元，用于对待检测液晶片未夹紧图像和待检测液晶片夹紧图像进行处理，得到待检测液晶片二值化图像；The to-be-detected image binarization unit is used to process the un-clamped image of the to-be-detected liquid crystal sheet and the clamped image of the to-be-detected liquid crystal sheet to obtain a binarized image of the to-be-detected liquid crystal sheet;
图像配准单元，用于将待检测液晶片二值化图像与标准液晶片二值化模板图像通过投影算法进行配准；The image registration unit is used for registering the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel through a projection algorithm;
检测判断单元，用于将待检测液晶片二值化图像与标准液晶片二值化模板图像作差，得出两者图像的不同，并对其进行检测判断。The detection and judgment unit is used for making a difference between the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel, to obtain the difference between the two images, and to perform detection and judgment.
作为所述的一种基于机器视觉的液晶片智能检测系统的进一步改进，所述的标准图像二值化单元包括：As a further improvement of the machine vision-based liquid crystal panel intelligent detection system, the standard image binarization unit includes:
滤波单元，用于对标准液晶片未夹紧图像和标准液晶片夹紧图像进行高斯滤波；The filtering unit is used to perform Gaussian filtering on the unclamped image of the standard liquid crystal sheet and the clamped image of the standard liquid crystal sheet;
自动阈值单元，用于对高斯滤波处理后得到的两个图像通过区域化自动阈值分割算法进行二值化处理，得到标准液晶片未夹紧二值化图像和标准液晶片夹紧二值化图像；The automatic threshold unit is used to binarize the two images obtained after Gaussian filtering processing through the regional automatic threshold segmentation algorithm to obtain the standard liquid crystal panel unclamped binarized image and the standard liquid crystal panel clamped binarized image ;
作差单元，用于将标准液晶片未夹紧二值化图像和标准液晶片夹紧二值化图像作差，得到标准液晶片二值化模板图像。The difference unit is used for making a difference between the standard liquid crystal panel unclamped binarized image and the standard liquid crystal panel clamped binarized image to obtain the standard liquid crystal panel binarized template image.
作为所述的一种基于机器视觉的液晶片智能检测系统的进一步改进，所述的图像配准单元包括：As a further improvement of the machine vision-based liquid crystal panel intelligent detection system, the image registration unit includes:
金字塔建立单元，用于对待检测液晶片二值化图像与标准液晶片二值化模板图像分别建立高斯金字塔，得到待检测液晶片多层金字塔图像和标准液晶片多层金字塔图像；The pyramid building unit is used to respectively establish Gaussian pyramids for the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel to obtain the multi-layer pyramid image of the liquid crystal panel to be detected and the multi-layer pyramid image of the standard liquid crystal panel;
投影配准单元，用于对待检测液晶片多层金字塔图像和标准液晶片多层金字塔图像通过投影算法从上到下逐层进行配准。The projection registration unit is used for registering the multi-layer pyramid image of the liquid crystal panel to be detected and the multi-layer pyramid image of the standard liquid crystal panel from top to bottom layer by layer through a projection algorithm.
作为所述的一种基于机器视觉的液晶片智能检测系统的进一步改进，所述的检测判断单元包括：As a further improvement of the machine vision-based liquid crystal panel intelligent detection system, the detection and judgment unit includes:
差异点计算单元，用于将待检测液晶片二值化图像与标准液晶片二值化模板图像作差，得出差异点数量，并进行显示；The difference point calculation unit is used to make a difference between the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel to obtain the number of difference points and display them;
差异判断单元，用于判断差异点数量是否大于预设的检测阈值，若是，则表示当前的待检测液晶片不合格；反之，则表示待检测液晶片合格。The difference judging unit is used for judging whether the number of difference points is greater than the preset detection threshold, if so, it means that the current liquid crystal sheet to be detected is unqualified;
本发明的有益效果是：The beneficial effects of the present invention are:
本发明一种基于机器视觉的液晶片智能检测方法及系统通过对待检测液晶片二值化图像与标准液晶片二值化模板图像进行像素点的对比从而检测液晶片的质量，有效提高液晶片检测过程中的检测效率，降低漏检误检率并降低人工成本，提高生产节拍。A method and system for intelligent detection of liquid crystal panels based on machine vision of the present invention detect the quality of liquid crystal panels by comparing the pixel points of the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel, thereby effectively improving the detection of liquid crystal panels. The detection efficiency in the process is reduced, the rate of missed detection and false detection is reduced, the labor cost is reduced, and the production tact is improved.
附图说明Description of drawings
下面结合附图对本发明的具体实施方式作进一步说明：The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings:
图1是本发明一种基于机器视觉的液晶片智能检测方法的步骤流程图；Fig. 1 is the step flow chart of a kind of liquid crystal sheet intelligent detection method based on machine vision of the present invention;
图2是本发明一种基于机器视觉的液晶片智能检测方法中标准液晶片图像二值化的步骤流程图；2 is a flow chart of the steps of binarizing a standard liquid crystal panel image in a liquid crystal panel intelligent detection method based on machine vision of the present invention;
图3是本发明一种基于机器视觉的液晶片智能检测方法中待检测液晶片图像二值化的步骤流程图；3 is a flow chart of the steps of binarizing an image of a liquid crystal panel to be detected in a liquid crystal panel intelligent detection method based on machine vision of the present invention;
图4是本发明一种基于机器视觉的液晶片智能检测方法中配准的步骤流程图；4 is a flow chart of the steps of registration in a machine vision-based liquid crystal panel intelligent detection method of the present invention;
图5是本发明一种基于机器视觉的液晶片智能检测方法中检测判断的步骤流程图；5 is a flow chart of the steps of detection and judgment in a liquid crystal panel intelligent detection method based on machine vision of the present invention;
图6是本发明一种基于机器视觉的液晶片智能检测系统的模块方框图。FIG. 6 is a block diagram of a module of a liquid crystal sheet intelligent detection system based on machine vision of the present invention.
具体实施方式Detailed ways
参考图1，本发明一种基于机器视觉的液晶片智能检测方法，包括以下步骤：Referring to Fig. 1, a method for intelligent detection of liquid crystal sheets based on machine vision of the present invention comprises the following steps:
获取标准液晶片在夹持装置未夹紧状态下的图像和在夹紧状态下的图像，得到标准液晶片未夹紧图像和标准液晶片夹紧图像；Obtain the image of the standard liquid crystal sheet in the unclamped state of the clamping device and the image in the clamped state, and obtain the unclamped image of the standard liquid crystal sheet and the clamped image of the standard liquid crystal sheet;
对标准液晶片未夹紧图像和标准液晶片夹紧图像进行处理，得到标准液晶片二值化模板图像；Process the unclamped image of the standard liquid crystal sheet and the clamped image of the standard liquid crystal sheet to obtain the binarized template image of the standard liquid crystal sheet;
获取待检测液晶片在夹持装置未夹紧状态下的图像和在夹紧状态下的图像，得到待检测液晶片未夹紧图像和待检测液晶片夹紧图像；acquiring the image of the liquid crystal sheet to be detected in the unclamped state of the clamping device and the image in the clamped state, to obtain the unclamped image of the liquid crystal sheet to be detected and the clamped image of the liquid crystal sheet to be detected;
对待检测液晶片未夹紧图像和待检测液晶片夹紧图像进行处理，得到待检测液晶片二值化图像；The unclamped image of the liquid crystal sheet to be detected and the clamped image of the liquid crystal sheet to be detected are processed to obtain a binarized image of the liquid crystal sheet to be detected;
将待检测液晶片二值化图像与标准液晶片二值化模板图像通过投影算法进行配准；Register the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel through a projection algorithm;
将待检测液晶片二值化图像与标准液晶片二值化模板图像作差，得出两者图像的不同，并对其进行检测判断。The difference between the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel is obtained, and the difference between the two images is obtained and detected and judged.
参考图2，进一步作为优选的实施方式，所述的对标准液晶片未夹紧图像和标准液晶片夹紧图像进行处理，得到标准液晶片二值化模板图像，这一步骤具体包括：Referring to FIG. 2 , as a further preferred embodiment, the unclamped image of the standard liquid crystal panel and the clamped image of the standard liquid crystal panel are processed to obtain a binarized template image of the standard liquid crystal panel. This step specifically includes:
对标准液晶片未夹紧图像和标准液晶片夹紧图像进行高斯滤波；Gaussian filtering is performed on the unclamped image of the standard liquid crystal sheet and the clamped image of the standard liquid crystal sheet;
对高斯滤波处理后得到的两个图像通过区域化自动阈值分割算法进行二值化处理，得到标准液晶片未夹紧二值化图像和标准液晶片夹紧二值化图像；The two images obtained after the Gaussian filtering process are binarized by the regionalized automatic threshold segmentation algorithm, and the standard liquid crystal panel unclamped binarized image and the standard liquid crystal panel clamped binarized image are obtained;
将标准液晶片未夹紧二值化图像和标准液晶片夹紧二值化图像作差，得到标准液晶片二值化模板图像。A difference is made between the un-clamped binarized image of the standard liquid crystal panel and the clamped binarized image of the standard liquid crystal panel to obtain a binarized template image of the standard liquid crystal panel.
参考图3，进一步作为优选的实施方式，所述的对待检测液晶片未夹紧图像和待检测液晶片夹紧图像进行处理，得到待检测液晶片二值化图像，这一步骤具体包括：Referring to FIG. 3 , as a further preferred embodiment, the unclamped image of the liquid crystal panel to be detected and the clamped image of the liquid crystal panel to be detected are processed to obtain a binarized image of the liquid crystal panel to be detected. This step specifically includes:
对待检测液晶片未夹紧图像和待检测液晶片夹紧图像进行高斯滤波；Gaussian filtering is performed on the unclamped image of the liquid crystal sheet to be detected and the clamped image of the liquid crystal sheet to be detected;
对高斯滤波处理后得到的两个图像通过区域化自动阈值分割算法进行二值化处理，得到待检测液晶片未夹紧二值化图像和待检测液晶片夹紧二值化图像；Perform binarization processing on the two images obtained after the Gaussian filter processing through the regionalized automatic threshold segmentation algorithm, to obtain the un-clamped binarized image of the liquid crystal panel to be detected and the clamped binarized image of the liquid crystal panel to be detected;
将待检测液晶片未夹紧二值化图像和待检测液晶片夹紧二值化图像作差，得到待检测液晶片二值化图像。A difference is made between the unclamped binarized image of the liquid crystal sheet to be detected and the clamped binarized image of the liquid crystal sheet to be detected to obtain the binarized image of the liquid crystal sheet to be detected.
参考图4，进一步作为优选的实施方式，所述的将待检测液晶片二值化图像与标准液晶片二值化模板图像通过投影算法进行配准，这一步骤具体包括：Referring to FIG. 4 , as a further preferred embodiment, the process of registering the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel by a projection algorithm specifically includes:
对待检测液晶片二值化图像与标准液晶片二值化模板图像分别建立高斯金字塔，得到待检测液晶片多层金字塔图像和标准液晶片多层金字塔图像；A Gaussian pyramid is established respectively for the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel to obtain a multi-layer pyramid image of the liquid crystal panel to be detected and a multi-layer pyramid image of the standard liquid crystal panel;
对待检测液晶片多层金字塔图像和标准液晶片多层金字塔图像通过投影算法从上到下逐层进行配准。The multi-layer pyramid image of the liquid crystal panel to be tested and the multi-layer pyramid image of the standard liquid crystal panel are registered layer by layer from top to bottom through the projection algorithm.
参考图5，进一步作为优选的实施方式，所述的将待检测液晶片二值化图像与标准液晶片二值化模板图像作差，得出两者图像的不同，并对其进行检测判断，这一步骤具体包括：Referring to FIG. 5 , as a further preferred embodiment, the binarized image of the liquid crystal panel to be detected is compared with the binarized template image of the standard liquid crystal panel to obtain the difference between the two images, and the detection and judgment are carried out. This step specifically includes:
将待检测液晶片二值化图像与标准液晶片二值化模板图像作差，得出差异点数量，并进行显示；Differentiate the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel to obtain the number of difference points and display them;
判断差异点数量是否大于预设的检测阈值，若是，则表示当前的待检测液晶片不合格；反之，则表示待检测液晶片合格。It is judged whether the number of difference points is greater than the preset detection threshold, and if so, it means that the current liquid crystal sheet to be tested is unqualified; otherwise, it means that the liquid crystal sheet to be tested is qualified.
进一步作为优选的实施方式，所述的区域化自动阈值分割算法中最佳阈值的计算公式为：Further as a preferred embodiment, the calculation formula of the optimal threshold in the described regionalization automatic threshold segmentation algorithm is:
其中，t表示分割的阈值，w0为背景比例，u0为背景均值，w1为前景比例，u1为前景均值，u为整幅图像的均值，当以上表达式值最大的t，即为分割图像的最佳阈值。Among them, t represents the threshold of segmentation, w 0 is the background ratio, u 0 is the background mean, w 1 is the foreground ratio, u 1 is the foreground mean, and u is the mean of the entire image. When the above expression has the largest t, that is is the best threshold for segmenting the image.
参考图6，本发明一种基于机器视觉的液晶片智能检测系统，包括：Referring to FIG. 6 , a liquid crystal sheet intelligent detection system based on machine vision of the present invention includes:
标准图像获取单元，用于获取标准液晶片在夹持装置未夹紧状态下的图像和在夹紧状态下的图像，得到标准液晶片未夹紧图像和标准液晶片夹紧图像；The standard image acquisition unit is used to acquire the image of the standard liquid crystal sheet in the unclamped state of the clamping device and the image in the clamped state, and obtain the unclamped image of the standard liquid crystal sheet and the clamped image of the standard liquid crystal sheet;
标准图像二值化单元，用于对标准液晶片未夹紧图像和标准液晶片夹紧图像进行处理，得到标准液晶片二值化模板图像；The standard image binarization unit is used to process the unclamped image of the standard liquid crystal panel and the clamped image of the standard liquid crystal panel to obtain a binarized template image of the standard liquid crystal panel;
待检测图像获取单元，用于获取待检测液晶片在夹持装置未夹紧状态下的图像和在夹紧状态下的图像，得到待检测液晶片未夹紧图像和待检测液晶片夹紧图像；The image acquisition unit to be detected is used to acquire the image of the liquid crystal sheet to be detected in the unclamped state of the clamping device and the image in the clamped state, and obtain the unclamped image of the liquid crystal sheet to be detected and the clamped image of the liquid crystal sheet to be detected ;
待检测图像二值化单元，用于对待检测液晶片未夹紧图像和待检测液晶片夹紧图像进行处理，得到待检测液晶片二值化图像；The to-be-detected image binarization unit is used to process the un-clamped image of the to-be-detected liquid crystal sheet and the clamped image of the to-be-detected liquid crystal sheet to obtain a binarized image of the to-be-detected liquid crystal sheet;
图像配准单元，用于将待检测液晶片二值化图像与标准液晶片二值化模板图像通过投影算法进行配准；The image registration unit is used for registering the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel through a projection algorithm;
检测判断单元，用于将待检测液晶片二值化图像与标准液晶片二值化模板图像作差，得出两者图像的不同，并对其进行检测判断。The detection and judgment unit is used for making a difference between the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel, to obtain the difference between the two images, and to perform detection and judgment.
进一步作为优选的实施方式，所述的标准图像二值化单元包括：Further as a preferred embodiment, the standard image binarization unit includes:
滤波单元，用于对标准液晶片未夹紧图像和标准液晶片夹紧图像进行高斯滤波；The filtering unit is used to perform Gaussian filtering on the unclamped image of the standard liquid crystal sheet and the clamped image of the standard liquid crystal sheet;
自动阈值单元，用于对高斯滤波处理后得到的两个图像通过区域化自动阈值分割算法进行二值化处理，得到标准液晶片未夹紧二值化图像和标准液晶片夹紧二值化图像；The automatic threshold unit is used to binarize the two images obtained after Gaussian filtering processing through the regional automatic threshold segmentation algorithm to obtain the standard liquid crystal panel unclamped binarized image and the standard liquid crystal panel clamped binarized image ;
作差单元，用于将标准液晶片未夹紧二值化图像和标准液晶片夹紧二值化图像作差，得到标准液晶片二值化模板图像。The difference unit is used for making a difference between the standard liquid crystal panel unclamped binarized image and the standard liquid crystal panel clamped binarized image to obtain the standard liquid crystal panel binarized template image.
进一步作为优选的实施方式，所述的图像配准单元包括：Further as a preferred embodiment, the image registration unit includes:
金字塔建立单元，用于对待检测液晶片二值化图像与标准液晶片二值化模板图像分别建立高斯金字塔，得到待检测液晶片多层金字塔图像和标准液晶片多层金字塔图像；The pyramid building unit is used to respectively establish Gaussian pyramids for the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel to obtain the multi-layer pyramid image of the liquid crystal panel to be detected and the multi-layer pyramid image of the standard liquid crystal panel;
投影配准单元，用于对待检测液晶片多层金字塔图像和标准液晶片多层金字塔图像通过投影算法从上到下逐层进行配准。The projection registration unit is used for registering the multi-layer pyramid image of the liquid crystal panel to be detected and the multi-layer pyramid image of the standard liquid crystal panel from top to bottom layer by layer through a projection algorithm.
进一步作为优选的实施方式，所述的检测判断单元包括：Further as a preferred embodiment, the detection and judgment unit includes:
差异点计算单元，用于将待检测液晶片二值化图像与标准液晶片二值化模板图像作差，得出差异点数量，并进行显示；The difference point calculation unit is used to make a difference between the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel to obtain the number of difference points and display them;
差异判断单元，用于判断差异点数量是否大于预设的检测阈值，若是，则表示当前的待检测液晶片不合格；反之，则表示待检测液晶片合格。The difference judging unit is used for judging whether the number of difference points is greater than the preset detection threshold, if so, it means that the current liquid crystal sheet to be detected is unqualified;
本发明具体实施例中，搭建由检测柜、人机交互显示器、相机底架、1#相机、2#相机、相机架、1#液晶片夹具和2#液晶片夹具构成的检测平台。相机和液晶片夹具分别固定于平台之上，并保持相对位置固定，在检测柜上固定相机底架，相机支架；固定液晶片夹具使得两个夹具与检测柜中心线对齐；在相机底架末端固定计算机人机交互显示器；在相机支架上安装1#相机和2#相机，安装相机与计算机通讯连接线及夹具气路，调整相机位置和焦距使得1#相机视角完全覆盖1#夹具，2#相机视角完全覆盖2#夹具，夹具下方液晶片检测电路上电，并且使得图像最清晰，然后固定相机位置。In the specific embodiment of the present invention, a detection platform consisting of a detection cabinet, a human-computer interaction display, a camera chassis, a 1# camera, a 2# camera, a camera frame, a 1# liquid crystal sheet fixture and a 2# liquid crystal sheet fixture is built. The camera and the LCD film fixture are respectively fixed on the platform and keep their relative positions fixed, and the camera chassis and camera bracket are fixed on the inspection cabinet; the LCD film clamp is fixed so that the two clamps are aligned with the center line of the inspection cabinet; fixed at the end of the camera chassis Computer human-computer interaction display; install 1# camera and 2# camera on the camera bracket, install the camera and computer communication cable and the fixture air circuit, adjust the camera position and focal length so that the 1# camera angle of view completely covers the 1# fixture, 2# camera The viewing angle completely covers the 2# fixture, the liquid crystal detection circuit under the fixture is powered on, and the image is the clearest, and then the camera position is fixed.
S1、取一片标准液晶片产品，放入1#夹具，气动回路关闭保持夹具未夹紧状态，驱动1#相机获取此状态下图像，得到标准未夹紧图像，然后打开气动回路，1#夹具保持夹紧状态，同时检测电路通电，液晶片显示图像时1#驱动相机，获取标准夹紧图像。S1. Take a standard LCD product, put it into the 1# fixture, close the pneumatic circuit to keep the fixture unclamped, drive the 1# camera to obtain the image in this state, get the standard unclamped image, then open the pneumatic circuit, 1# fixture Keep the clamped state, and the detection circuit is powered on at the same time. When the LCD panel displays an image, 1# drives the camera to obtain a standard clamped image.
S2：将得到的两幅图像进行高斯滤波，然后运用区域化自动阈值分割算法进行对图片进行二值化处理获得二值化图片，最后对处理后的两幅图像作差得到标准液晶片二值化模板图像；S2: Perform Gaussian filtering on the two obtained images, and then use the regionalized automatic threshold segmentation algorithm to binarize the images to obtain a binarized image, and finally make a difference between the two processed images to obtain a standard liquid crystal panel binary value template image;
为适应图像处理的要求，消除图像数字化时所混入的噪声。在得到采集的图像时首先要对图像进行高斯滤波，二维高斯函数可以表达为：In order to meet the requirements of image processing, the noise mixed in the image digitization is eliminated. When the acquired image is obtained, Gaussian filtering is firstly performed on the image. The two-dimensional Gaussian function can be expressed as:
其中μ为峰值(峰值对应位置)，σ代表标准差(变量x和变量y各有一个均值，也各有一个标准差)；where μ is the peak value (the corresponding position of the peak value), and σ represents the standard deviation (variable x and variable y each have a mean and a standard deviation);
将图像滤波处理后，需要对图像进行二值化处理，具体实现方法为自动阈值分割算法，由于在工业实际应用过程中，采集到的图像可能会因为光源照射不均、外界环境干扰等因素的影响而导致亮度不均，本发明中的自动阈值分割算法可以根据图像亮度的不同将采集到的图像自动的划分为N个区域，然后在利用自动阈值分割的算法分别求每个区域的阈值，进而实现图像的二值化；After the image is filtered, the image needs to be binarized. The specific implementation method is the automatic threshold segmentation algorithm. In the process of practical industrial application, the collected image may be affected by factors such as uneven illumination of the light source and external environment interference. The automatic threshold segmentation algorithm in the present invention can automatically divide the collected image into N regions according to the difference of image brightness, and then use the automatic threshold segmentation algorithm to calculate the threshold of each region respectively, And then realize the binarization of the image;
设灰度图像灰度级是L，则灰度范围为[0,L-1]，利用自动阈值分割算法计算图像的最佳阈值为：Assuming that the gray level of the grayscale image is L, the grayscale range is [0, L-1], and the optimal threshold value of the image calculated by the automatic threshold segmentation algorithm is:
其中，t表示分割的阈值，w0为背景比例，u0为背景均值，w1为前景比例，u1为前景均值，u为整幅图像的均值，当以上表达式值最大的t，即为分割图像的最佳阈值。Among them, t represents the threshold of segmentation, w 0 is the background ratio, u 0 is the background mean, w 1 is the foreground ratio, u 1 is the foreground mean, and u is the mean of the entire image. When the above expression has the largest t, that is is the best threshold for segmenting the image.
S3：取待检测液晶片产品，放入1#夹具，气动回路关闭保持1#夹具未夹紧状态，驱动1#相机获取待检测未夹紧图像，然后打开气动回路，1#夹具保持夹紧状态，同时检测电路通电，液晶片显示图像时1#驱动相机，获取待检测夹紧图像；进行相同过程应用于2#夹具和2#相机。将所获取的图像数字化存储于计算机内，由计算机经过二值化处理，得到了待检测液晶片二值化图像，该过程和步骤S3的过程相同。S3: Take the liquid crystal sheet product to be tested, put it into the 1# fixture, close the pneumatic circuit to keep the 1# fixture unclamped, drive the 1# camera to obtain the unclamped image to be tested, and then open the pneumatic circuit, and the 1# fixture remains clamped state, and the detection circuit is powered on at the same time, when the LCD panel displays an image, 1# drives the camera to obtain the clamped image to be detected; the same process is applied to the 2# fixture and 2# camera. The acquired image is digitized and stored in the computer, and the computer undergoes binarization processing to obtain a binarized image of the liquid crystal sheet to be detected. The process is the same as that of step S3.
S4：将待检测液晶片二值化图像与标准液晶片二值化模板图像通过投影算法进行配准；S4: register the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel through a projection algorithm;
S41：对待检测液晶片二值化图像与标准液晶片二值化模板图像分别建立高斯金字塔，得到待检测液晶片多层金字塔图像和标准液晶片多层金字塔图像，获取低分辨率图像。本实施例中为了提高信息的识别率，利用高斯金字塔模型多尺度表达的特性，对输入的图片建立三层且平滑系数为0.5的高斯金字塔模型，高斯金字塔中不同组次上的图像具有不同的尺寸和分辨率，接近底层的图像尺寸相对较大，反映了图像中小尺度细节；而随着层次向上移动，图像的尺寸和分辨率都相对降低，这样仅描述了图像中目标的主要信息；S41 : respectively establishing Gaussian pyramids on the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel, obtaining a multi-layer pyramid image of the liquid crystal panel to be detected and a multi-layer pyramid image of the standard liquid crystal panel, and obtaining a low-resolution image. In this embodiment, in order to improve the recognition rate of information, a Gaussian pyramid model with three layers and a smoothing coefficient of 0.5 is established for the input image by using the multi-scale expression characteristics of the Gaussian pyramid model. The images in different groups in the Gaussian pyramid have different Size and resolution, the size of the image close to the bottom layer is relatively large, reflecting the small-scale details in the image; as the level moves up, the size and resolution of the image are relatively reduced, which only describes the main information of the target in the image;
S42：对待检测液晶片多层金字塔图像和标准液晶片多层金字塔图像通过投影算法从上到下逐层进行配准。首先对搜索金字塔的最上层即最粗糙层，对最粗糙层进行匹配，生成移动图像和固定图像的XY梯度图以及两者间的差分，然后利用最小二乘法配准拟合得到最佳变化系数。记录下当前搜索结果，在对下一层图像进行搜索时以这个结果为中心进行搜索，同时不停修正前一层高斯图像的结构，重复该步骤至原始图像即最大尺度层。S42: The multi-layer pyramid image of the liquid crystal panel to be detected and the multi-layer pyramid image of the standard liquid crystal panel are registered layer by layer from top to bottom through a projection algorithm. First, the top layer of the search pyramid is the roughest layer, and the roughest layer is matched to generate the XY gradient map of the moving image and the fixed image and the difference between the two, and then use the least squares method to register and fit to obtain the best coefficient of variation . Record the current search result, search the next layer of images with this result as the center, and keep correcting the structure of the Gaussian image of the previous layer, and repeat this step to the original image, that is, the largest scale layer.
S5：将待检测液晶片二值化图像与标准液晶片二值化模板图像作差，得出差异点数量，并显示在人机交互显示器界面。根据检测的精度要求的不同预设合理的检测阈值，判断差异点数量是否大于预设的检测阈值，若是，则表示当前的待检测液晶片不合格；反之，则表示待检测液晶片合格。S5: Differentiate the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel to obtain the number of difference points, and display them on the human-computer interaction display interface. According to different preset reasonable detection thresholds required by the detection accuracy, it is judged whether the number of difference points is greater than the preset detection threshold.
从上述内容可知，本发明一种基于机器视觉的液晶片智能检测方法及系统通过对待检测液晶片二值化图像与标准液晶片二值化模板图像进行像素点的对比从而检测液晶片的质量，有效提高液晶片检测过程中的检测效率，降低漏检误检率并降低人工成本，提高生产节拍。It can be seen from the above content that a method and system for intelligent detection of liquid crystal panels based on machine vision of the present invention detect the quality of liquid crystal panels by comparing the pixel points of the binarized image of the liquid crystal panel to be detected and the binarized template image of the standard liquid crystal panel. Effectively improve the detection efficiency in the process of liquid crystal sheet detection, reduce the rate of missed detection and false detection, reduce labor costs, and improve production tact.
以上是对本发明的较佳实施进行了具体说明，但本发明创造并不限于所述实施例，熟悉本领域的技术人员在不违背本发明精神的前提下还可做作出种种的等同变形或替换，这些等同的变形或替换均包含在本申请权利要求所限定的范围内。The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the described embodiments, and those skilled in the art can make various equivalent deformations or replacements without departing from the spirit of the present invention. , these equivalent modifications or substitutions are all included within the scope defined by the claims of the present application.
Claims (7)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710260493.6A CN107248151B (en) | 2017-04-20 | 2017-04-20 | A method and system for intelligent detection of liquid crystal sheets based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710260493.6A CN107248151B (en) | 2017-04-20 | 2017-04-20 | A method and system for intelligent detection of liquid crystal sheets based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107248151A CN107248151A (en) | 2017-10-13 |
| CN107248151B true CN107248151B (en) | 2020-12-22 |
Family
ID=60016405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710260493.6A Active CN107248151B (en) | 2017-04-20 | 2017-04-20 | A method and system for intelligent detection of liquid crystal sheets based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107248151B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960169A (en) * | 2018-07-12 | 2018-12-07 | 杭州电子科技大学 | Instrument and equipment state on_line monitoring method and system based on computer vision |
| CN113552136A (en) * | 2021-07-30 | 2021-10-26 | 广州中国科学院先进技术研究所 | High-temperature forging visual detection system with vibration isolation capability |
| CN113570605B (en) * | 2021-09-28 | 2021-12-31 | 深圳市绘晶科技有限公司 | Defect detection method and system based on liquid crystal display panel |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5038048A (en) * | 1988-12-23 | 1991-08-06 | Hitachi, Ltd. | Defect detection system and method for pattern to be inspected utilizing multiple-focus image signals |
| CN1678036A (en) * | 2004-03-31 | 2005-10-05 | 株式会社岛津制作所 | Radiographic apparatus and radiation detection signal processing method |
| CN1801433A (en) * | 2006-01-11 | 2006-07-12 | 彩虹集团电子股份有限公司 | Plasma display screen fault checking method |
| JP2010071892A (en) * | 2008-09-19 | 2010-04-02 | Toray Ind Inc | Pattern inspection method and pattern inspection device |
| CN102053093A (en) * | 2010-11-08 | 2011-05-11 | 北京大学深圳研究生院 | Method for detecting surface defects of chip cut from wafer surface |
| CN102095733A (en) * | 2011-03-02 | 2011-06-15 | 上海大学 | Machine vision-based intelligent detection method for surface defect of bottle cap |
| CN102509300A (en) * | 2011-11-18 | 2012-06-20 | 深圳市宝捷信科技有限公司 | Defect detection method and system |
| CN103439348A (en) * | 2013-08-16 | 2013-12-11 | 中国科学院半导体研究所 | Remote controller key defect detection method based on difference image method |
| CN104360501A (en) * | 2014-10-15 | 2015-02-18 | 西安交通大学 | Visual detection method and device for defects of liquid crystal display screen |
| CN104792794A (en) * | 2015-04-28 | 2015-07-22 | 武汉工程大学 | Machine vision based optical film surface defect detecting method |
| CN105069790A (en) * | 2015-08-06 | 2015-11-18 | 潍坊学院 | Rapid imaging detection method for gear appearance defect |
| CN105976389A (en) * | 2016-05-20 | 2016-09-28 | 南京理工大学 | Mobile phone baseboard connector defect detection method |
| CN106169431A (en) * | 2016-07-06 | 2016-11-30 | 江苏维普光电科技有限公司 | Mask plate based on GPU and wafer defect detection method |
| CN106204614A (en) * | 2016-07-21 | 2016-12-07 | 湘潭大学 | A kind of workpiece appearance defects detection method based on machine vision |
-
2017
- 2017-04-20 CN CN201710260493.6A patent/CN107248151B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5038048A (en) * | 1988-12-23 | 1991-08-06 | Hitachi, Ltd. | Defect detection system and method for pattern to be inspected utilizing multiple-focus image signals |
| CN1678036A (en) * | 2004-03-31 | 2005-10-05 | 株式会社岛津制作所 | Radiographic apparatus and radiation detection signal processing method |
| CN1801433A (en) * | 2006-01-11 | 2006-07-12 | 彩虹集团电子股份有限公司 | Plasma display screen fault checking method |
| JP2010071892A (en) * | 2008-09-19 | 2010-04-02 | Toray Ind Inc | Pattern inspection method and pattern inspection device |
| CN102053093A (en) * | 2010-11-08 | 2011-05-11 | 北京大学深圳研究生院 | Method for detecting surface defects of chip cut from wafer surface |
| CN102095733A (en) * | 2011-03-02 | 2011-06-15 | 上海大学 | Machine vision-based intelligent detection method for surface defect of bottle cap |
| CN102509300A (en) * | 2011-11-18 | 2012-06-20 | 深圳市宝捷信科技有限公司 | Defect detection method and system |
| CN103439348A (en) * | 2013-08-16 | 2013-12-11 | 中国科学院半导体研究所 | Remote controller key defect detection method based on difference image method |
| CN104360501A (en) * | 2014-10-15 | 2015-02-18 | 西安交通大学 | Visual detection method and device for defects of liquid crystal display screen |
| CN104792794A (en) * | 2015-04-28 | 2015-07-22 | 武汉工程大学 | Machine vision based optical film surface defect detecting method |
| CN105069790A (en) * | 2015-08-06 | 2015-11-18 | 潍坊学院 | Rapid imaging detection method for gear appearance defect |
| CN105976389A (en) * | 2016-05-20 | 2016-09-28 | 南京理工大学 | Mobile phone baseboard connector defect detection method |
| CN106169431A (en) * | 2016-07-06 | 2016-11-30 | 江苏维普光电科技有限公司 | Mask plate based on GPU and wafer defect detection method |
| CN106204614A (en) * | 2016-07-21 | 2016-12-07 | 湘潭大学 | A kind of workpiece appearance defects detection method based on machine vision |
Non-Patent Citations (4)
| Title |
|---|
| 《Design of Machine Vision Applications in Detection of Defects in High-Speed Bar Copper》;Lei Wang;《2010 International Conference on E-Product E-Service and E-Entertainment》;20101231;第1-4页 * |
| 《OLED panel defect detection using local inlier-outlier ratios and modified LBP》;Vishwanath A. Sindagi等;《2015 14th IAPR International Conference on Machine Vision Applications (MVA)》;20150522;第214-217页 * |
| 《一种基于线阵CCD技术印刷电路板胶片的尺寸及缺陷在线检测方法》;叶亭等;《光学与光电技术》;20080430;第6卷(第2期);第74-77页 * |
| 《基于机器视觉的磁钢片缺陷检测研究》;周江等;《机电工程》;20141231;第31卷(第12期);第1541-1546页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107248151A (en) | 2017-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104749184B (en) | Automatic optical detection method and system | |
| CN107014819A (en) | A kind of solar panel surface defects detection system and method | |
| CN110567976B (en) | Screen printing defect detection device and detection method for mobile phone cover plate based on machine vision | |
| TWI238366B (en) | Image processing method for appearance inspection | |
| CN108896547A (en) | Refractory brick measuring system based on machine vision | |
| CN108387516A (en) | Threading defects detection device and detection method based on CCD camera image processing technologies | |
| CN110108711A (en) | Visual inspection system for defects of side wall of circular ring | |
| CN104483320B (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| CN114494045A (en) | Large-scale straight gear geometric parameter measuring system and method based on machine vision | |
| CN105158268A (en) | Intelligent online detection method, system and device for defects of fine-blanked parts | |
| CN104792794A (en) | Machine vision based optical film surface defect detecting method | |
| CN111474179A (en) | Lens surface cleanliness detection device and method | |
| CN107248151B (en) | A method and system for intelligent detection of liquid crystal sheets based on machine vision | |
| CN101803364B (en) | Imaging device and method | |
| CN111665199A (en) | Wire and cable color detection and identification method based on machine vision | |
| KR20140075042A (en) | Apparatus for inspecting of display panel and method thereof | |
| CN110599404A (en) | Circuit board microscopic image splicing method and device and information data processing terminal | |
| CN112014407A (en) | Method for detecting surface defects of integrated circuit wafer | |
| CN109387524A (en) | Thread defect detection method and device based on linearly polarized photon | |
| CN110807763A (en) | Method and system for detecting ceramic tile surface bulge | |
| CN104749801B (en) | High Precision Automatic optical detecting method and system | |
| CN116681684A (en) | Tunnel disease monitoring method and system based on image recognition | |
| CN114964032B (en) | Blind hole depth measurement method and device based on machine vision | |
| CN106530230A (en) | PCB photoelectric image obtaining and pre-treating method | |
| CN111815705B (en) | Method and device for identifying pollution of filter protection lens of laser tracker and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20241203 Address after: B310, Key Laboratory Platform Building, Shenzhen Virtual University Park, No.1 Yuexing Second Road, Yuehai Street, Shenzhen, Guangdong Province 518057 Patentee after: Shenzhen Century Langshuo Technology Co.,Ltd. Country or region after: China Address before: Room 813, 8 / F, software building, No.9, Gaoxin Zhongyi Road, Nanshan District, Shenzhen City, Guangdong Province Patentee before: SHENZHEN ACADEMY OF ROBOTICS Country or region before: China |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20250310 Address after: Room 101-152, No. 10-6 Jincheng Street, Shenfu Demonstration Zone, Shenyang City, Liaoning Province, China 110000 Patentee after: Liaoning Shenfu Liaogang Intelligent Technology Innovation Research Institute Co.,Ltd. Country or region after: China Address before: B310, Key Laboratory Platform Building, Shenzhen Virtual University Park, No.1 Yuexing Second Road, Yuehai Street, Shenzhen, Guangdong Province 518057 Patentee before: Shenzhen Century Langshuo Technology Co.,Ltd. Country or region before: China |
|
| TR01 | Transfer of patent right |