WO2021082922A1 - 一种检测屏幕显示断线的方法及设备 - Google Patents

一种检测屏幕显示断线的方法及设备 Download PDF

Info

Publication number
WO2021082922A1
WO2021082922A1 PCT/CN2020/120879 CN2020120879W WO2021082922A1 WO 2021082922 A1 WO2021082922 A1 WO 2021082922A1 CN 2020120879 W CN2020120879 W CN 2020120879W WO 2021082922 A1 WO2021082922 A1 WO 2021082922A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
pixel
disconnection
extension map
target extension
Prior art date
Application number
PCT/CN2020/120879
Other languages
English (en)
French (fr)
Inventor
徐鹏
沈圣远
常树林
姚巨虎
Original Assignee
上海悦易网络信息技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 上海悦易网络信息技术有限公司 filed Critical 上海悦易网络信息技术有限公司
Publication of WO2021082922A1 publication Critical patent/WO2021082922A1/zh

Links

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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • 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
    • G06T2207/30121—CRT, LCD or plasma display

Definitions

  • This application relates to the field of screen detection, and in particular to a method and device for detecting disconnection of a screen display.
  • the screen display problems of smart devices include display disconnection, dead pixels, etc.
  • the existing disconnection detection methods usually use classification methods to obtain disconnection location information, which consumes a lot of computing resources and generates redundant calculations. Process, and it is difficult to obtain the precise disconnection position, and it is also impossible to automatically obtain the point of the disconnection.
  • An object of the present application is to provide a method and device for detecting disconnection of a screen display, so as to solve the problems of low efficiency in detecting the disconnection of the screen display, difficulty in automatically detecting the disconnection position, and inaccurate judgment of the disconnection position in the prior art.
  • a method for detecting disconnection of a screen display including:
  • the target extension map is determined, and the position of the disconnection is determined according to the determination result.
  • the using the convolutional neural network to obtain the information of the target point in the disconnection includes:
  • the using the convolutional neural network to obtain the pixel value of the target point in the broken line includes:
  • the pixel value of the target point is determined according to the number of the multiple pixel points and the pixel value of the multiple pixel points.
  • the using the convolutional neural network to obtain the coordinate information of the target point in the broken line includes:
  • the coordinate information of the target point is determined according to the ratio of the cumulative sum of the coordinate information corresponding to the multiple pixel points to the number of the multiple pixel points.
  • the performing area extension according to the information of the target point to obtain a target extension map includes:
  • the determining the target extension map and determining the position of the disconnection according to the determination result includes:
  • the target extension map is allowed to be extended by the region, and if so, the target extension map is continued to be regionally extended; if not, the location of the disconnection is determined according to the target extension map.
  • determining whether the target extension map is allowed to be extended by the region if yes, continue the region extension of the target extension map; if not, determining the location of the disconnection according to the target extension map, including:
  • determining whether the target extension map is allowed to be extended by the region if yes, continue the region extension of the target extension map; if not, determining the location of the disconnection according to the target extension map, including:
  • the convolutional neural network is a segmentation neural network u-net network.
  • a computer-readable medium having computer-readable instructions stored thereon, and the computer-readable instructions can be executed by a processor to implement the aforementioned method for detecting disconnection of a screen display.
  • a device for detecting disconnection of a screen display wherein the device includes:
  • One or more processors are One or more processors.
  • a memory storing computer-readable instructions, which when executed, cause the processor to perform the operations of the aforementioned method for detecting disconnection of a screen display.
  • the present application obtains the information of the target point in the broken line by using the convolutional neural network; performs area extension according to the information of the target point to obtain the target extension map; judges the target extension map, The location of the disconnection is determined according to the determination result. So as to automatically detect whether the screen has a display disconnection and accurately determine the location of the screen disconnection.
  • Fig. 1 shows a schematic flow chart of a method for detecting a screen display disconnection according to an aspect of the present application.
  • the terminal, the equipment of the service network, and the trusted party all include one or more processors (CPU), input/output interfaces, network interfaces, and memory.
  • processors CPU
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-permanent memory in a computer readable medium, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer readable media.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash memory
  • Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology.
  • the information can be computer-readable instructions, data structures, program modules, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices.
  • computer-readable media does not include non-transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.
  • Fig. 1 shows a schematic flow chart of a method for detecting a broken line in a screen display according to an aspect of the present application.
  • the method includes: steps S11 to S13, wherein, in step S11, a convolutional neural network is used to obtain a target point in the broken line Step S12, perform area extension based on the information of the target point to obtain a target extension map; step S13, determine the target extension map, and determine the location of the disconnection according to the determination result. So as to automatically detect whether the screen has a display disconnection and accurately determine the location of the screen disconnection.
  • a convolutional neural network is used to obtain the information of the target point in the disconnection.
  • the trained convolutional neural network is used to detect the broken line, and the information of multiple points in the broken line can be obtained, such as the position coordinate information and the corresponding pixel value corresponding to the multiple points.
  • the trained The convolutional neural network is obtained by training using the labeled disconnection data; then, the information of the target point is obtained after calculation based on the information of the above multiple points, where the information of the target point includes but is not limited to the target point The position coordinate information and the pixel value of the target point.
  • the process of obtaining the target point information becomes simple and fast, the obtained result is intuitive, no complicated verification process is required, and the accuracy is high.
  • step S12 area extension is performed according to the information of the target point to obtain a target extension map.
  • the horizontal and vertical extensions are performed according to the position coordinate information of the target point and the pixel value of the target point.
  • the pixel points whose neighboring pixel values do not exceed a preset threshold are captured by The area extension is completed, and the target extension map is determined in combination with the target point.
  • step S13 the target extension map is determined, and the position of the disconnection is determined according to the determination result.
  • it is determined whether the obtained target extension map can be further extended if yes, then the target extension map is further extended; if not, the target extension map is the broken line, and the result is obtained according to the position coordinate information corresponding to the target extension map. Describe the position coordinate information of the broken line
  • a convolutional neural network is used to obtain the pixel value of the target point in the disconnection; and the convolutional neural network is used to obtain the coordinate information of the target point in the disconnection.
  • the information of the target point in the disconnection includes but is not limited to pixel value and coordinate information, and the information of the target point in the disconnection can be accurately obtained through the convolutional neural network.
  • a convolutional neural network is used to obtain the pixel values of multiple pixels in the broken line; the number of the multiple pixels and the pixel values of the multiple pixels are used to determine the value of the target point Pixel values.
  • the ratio of the cumulative sum of the pixel values of the multiple pixel points to the number of the multiple pixel points may be used to determine the pixel value of the target point.
  • a convolutional neural network is used to obtain coordinate information corresponding to multiple pixels in the broken line; determine the number of the multiple pixels and calculate the cumulative sum of coordinate information corresponding to the multiple pixels;
  • the coordinate information of the target point is determined according to the ratio of the cumulative sum of the coordinate information corresponding to the multiple pixel points to the number of the multiple pixel points.
  • the use of the convolutional neural network can automatically and accurately obtain the coordinate information of multiple pixel points in the broken line, so as to accurately obtain the coordinate information of the target point.
  • the above method of determining the coordinate information of the target point is only an example, and other methods may also be included.
  • the coordinate information corresponding to multiple pixels may be accumulated and the number of the multiple pixels may be combined. To determine the coordinate information of the target point.
  • the first neighboring pixel is determined according to the coordinate information of the target point, and the pixel value of the first neighboring pixel is obtained; it is determined that the pixel value of the target point is the same as that of the first neighboring pixel. Whether the difference between the pixel values of is smaller than a first preset threshold, and if so, a target extension map is determined according to the first neighboring pixel and the target point.
  • the coordinate information of the target point is used to capture the surrounding pixels directly adjacent to each other to obtain a plurality of first adjacent pixels, and obtain the pixel values of the plurality of first adjacent pixels.
  • a first preset threshold is set, and when the absolute value of the difference between the pixel value of the target point and the pixel value of the first adjacent pixel is less than the first preset threshold, the first adjacent pixel is set Pixels are added to the target point in a preset manner to form a target extension map.
  • the preset manner includes but is not limited to: marking the first adjacent pixel and the target point in a preset manner, according to The marked pixels in a preset manner determine the target extension map.
  • step S13 it is determined whether the target extension map is allowed to be extended by the region, if so, the target extension map is continued to be regionally extended; if not, the location of the disconnection is determined according to the target extension map .
  • the area extension includes horizontal extension and vertical extension.
  • the target extension drawing is a broken line, according to the position of the target extension drawing. Determine the location of the disconnection.
  • the target stretch map reaches the current last horizontal position after horizontally extending, and the pixel value of the neighboring pixel at the current last horizontal position is compared with the pixel average value, wherein the current last horizontal position Adjacent pixels are not in the target extension map.
  • a second preset threshold is set, and when the difference between the pixel value of the adjacent pixel at the current last horizontal position and the average value of the pixel is less than the second preset threshold, the target extension map allows Is extended by the region, the adjacent pixels at the current last horizontal position are included in the target extension map and continue to extend the target extension map horizontally; when the pixel value of the pixel at the current last horizontal position and the pixel
  • the target extension map is not allowed to extend to the last current horizontal position, and the horizontal position of the target extension map is the horizontal position of the broken line, To accurately confirm the horizontal position of the broken wire.
  • the target extension map reaches the current last vertical position after being vertically extended, and the pixel value of the neighboring pixel at the current last vertical position is compared with the average value of the pixels, wherein the current last vertical position Adjacent pixels are not in the target extension map.
  • a third preset threshold is set, and when the difference between the pixel value of the adjacent pixel at the current last vertical position and the average value of the pixel is less than the third preset threshold, the target extension map allows By area extension, the adjacent pixel at the current last vertical position is included in the target extension image and the target extension image is continued to be extended vertically; when the pixel value of the adjacent pixel at the current last vertical position is the same as that of the target extension image.
  • the target extension image is not allowed to extend to the current last vertical position, and the vertical position of the target extension image is the vertical position of the broken line Position to accurately confirm the vertical position of the broken wire.
  • the convolutional neural network is a segmented neural network u-net network.
  • the broken line area and the normal display area of the broken line picture can be displayed on the screen manually, and the marked picture is used to train the segmented neural network u-net network to obtain the broken line detection model, and use the broken line
  • the detection model detects the picture to be detected, and when a broken line is detected, multiple pixels in the broken line are obtained, and the target point can be accurately obtained after the calculation in the foregoing manner.
  • an embodiment of the present application also provides a computer-readable medium having computer-readable instructions stored thereon, and the computer-readable instructions can be executed by a processor to implement the aforementioned method for detecting a screen display disconnection.
  • a device for detecting disconnection of a screen display wherein the device includes:
  • One or more processors are One or more processors.
  • a memory storing computer-readable instructions, which when executed, cause the processor to perform the operations of the aforementioned method for detecting disconnection of a screen display.
  • the one or more processors use the convolutional neural network to obtain the information of the target point in the disconnection; perform area extension according to the information of the target point to obtain the target extension map ; Judge the target extension map, and determine the location of the disconnection according to the determination result.
  • this application can be implemented in software and/or a combination of software and hardware.
  • it can be implemented by an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device.
  • the software program of the present application may be executed by a processor to realize the steps or functions described above.
  • the software program (including related data structure) of the present application can be stored in a computer-readable recording medium, such as RAM memory, magnetic or optical drive or floppy disk and similar devices.
  • some steps or functions of the present application may be implemented by hardware, for example, as a circuit that cooperates with a processor to execute each step or function.
  • a part of this application can be applied as a computer program product, such as a computer program instruction, when it is executed by a computer, through the operation of the computer, the method and/or technical solution according to this application can be invoked or provided.
  • the program instructions for calling the method of the present application may be stored in a fixed or removable recording medium, and/or be transmitted through a data stream in a broadcast or other signal-bearing medium, and/or be stored in accordance with the Said program instructions run in the working memory of the computer equipment.
  • an embodiment according to the present application includes a device that includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the device triggers
  • the operation of the device is based on the aforementioned methods and/or technical solutions according to multiple embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

一种检测屏幕显示断线的方法及设备，通过利用卷积神经网络获取断线中的目标点的信息(S11)；根据所述目标点的信息进行区域延伸，得到目标延伸图(S12)；对所述目标延伸图进行判定，根据判定结果确定所述断线的位置(S13)。从而高效地自动检测屏幕是否产生显示断线并精确确定屏幕断线位置。

Description

一种检测屏幕显示断线的方法及设备 技术领域
本申请涉及屏幕检测领域，尤其涉及一种检测屏幕显示断线的方法及设备。
背景技术
智能设备的屏幕显示出现的问题包含显示断线、坏点等，为了排查屏幕显示是否正常，现有的断线检测方式通常运用分类法得到断线位置信息，耗费大量运算资源，产生冗余计算过程，且难以得到精确断线位置，也无法自动获取断线上的点。
发明内容
本申请的一个目的是提供一种检测屏幕显示断线的方法及设备，解决现有技术中检测屏幕显示断线效率低下、难以自动检测断线位置以及断线位置判断不准确的问题。
根据本申请的一个方面，提供了一种检测屏幕显示断线的方法，该方法包括：
利用卷积神经网络获取断线中的目标点的信息；
根据所述目标点的信息进行区域延伸，得到目标延伸图；
对所述目标延伸图进行判定，根据判定结果确定所述断线的位置。
进一步地，所述利用卷积神经网络获取断线中的目标点的信息，包括：
利用卷积神经网络获取断线中的目标点的像素值；
利用卷积神经网络获取断线中的目标点的坐标信息。
进一步地，所述利用卷积神经网络获取断线中的目标点的像素值，包括：
利用卷积神经网络获取断线中的多个像素点的像素值；
根据所述多个像素点的数量以及所述多个像素点的像素值确定所述目标 点的像素值。
进一步地，所述利用卷积神经网络获取断线中的目标点的坐标信息，包括：
利用卷积神经网络获取断线中的多个像素点对应的坐标信息；
确定所述多个像素点的数量并计算所述多个像素点对应的坐标信息累加和；
根据所述多个像素点对应的坐标信息的累加和与所述多个像素点的数量的比值确定所述目标点的坐标信息。
进一步地，所述根据所述目标点的信息进行区域延伸，得到目标延伸图，包括：
根据所述目标点的坐标信息确定第一相邻像素，获取所述第一相邻像素的像素值；
判断所述目标点的像素值与所述第一相邻像素的像素值的差值是否小于第一预设阈值，若是，则根据所述第一相邻像素与所述目标点确定目标延伸图。
进一步地，所述对所述目标延伸图进行判定，根据判定结果确定所述断线的位置，包括：
判定所述目标延伸图是否允许被区域延伸，若是，则对所述目标延伸图继续进行区域延伸；若否，则根据所述目标延伸图确定所述断线的位置。
进一步地，判定所述目标延伸图是否允许被区域延伸，若是，则对所述目标延伸图继续进行区域延伸；若否，则根据所述目标延伸图确定所述断线的位置，包括：
确定所述目标延伸图水平方向延伸到当前最后一个水平位置时的所有像素点的像素平均值；
获取所述当前最后一个水平位置处相邻像素的像素值，根据所述当前最后一个水平位置处相邻像素的像素值及所述像素平均值判断所述目标延伸图 是否允许被区域延伸，若是，则对所述目标延伸图继续进行区域延伸；若否，则将所述目标延伸图作为所述断线的位置。
进一步地，判定所述目标延伸图是否允许被区域延伸，若是，则对所述目标延伸图继续进行区域延伸；若否，则根据所述目标延伸图确定所述断线的位置，包括：
确定所述目标延伸图垂直方向延伸到当前最后一个垂直位置时的所有像素点的像素平均值；
获取所述当前最后一个垂直位置处相邻像素的像素值，根据所述当前最后一个垂直位置处相邻像素的像素值及所述像素平均值判断所述目标延伸图是否允许被区域延伸，若是，则对所述目标延伸图继续进行区域延伸；若否，则将所述目标延伸图作为所述断线的位置。
进一步地，所述卷积神经网络为分割神经网络u-net网络。
根据本申请另一个方面，还提供了一种计算机可读介质，其上存储有计算机可读指令，所述计算机可读指令可被处理器执行以实现前述一种检测屏幕显示断线的方法。
根据本申请再一个方面，还提供了一种检测屏幕显示断线的设备，其中，所述设备包括：
一个或多个处理器；以及
存储有计算机可读指令的存储器，所述计算机可读指令在被执行时使所述处理器执行前述一种检测屏幕显示断线的方法的操作。
与现有技术相比，本申请通过利用卷积神经网络获取断线中的目标点的信息；根据所述目标点的信息进行区域延伸，得到目标延伸图；对所述目标延伸图进行判定，根据判定结果确定所述断线的位置。从而高效地自动检测屏幕是否产生显示断线并精确确定屏幕断线位置。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本申请的其它特征、目的和优点将会变得更明显：
图1示出根据本申请的一个方面提供的一种检测屏幕显示断线的方法流程示意图。
附图中相同或相似的附图标记代表相同或相似的部件。
具体实施方式
下面结合附图对本申请作进一步详细描述。
在本申请一个典型的配置中，终端、服务网络的设备和可信方均包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括非暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
图1示出根据本申请的一个方面提供的一种检测屏幕显示断线的方法流程示意图,该方法包括：步骤S11～S13，其中，步骤S11，利用卷积神经网 络获取断线中的目标点的信息；步骤S12，根据所述目标点的信息进行区域延伸，得到目标延伸图；步骤S13，对所述目标延伸图进行判定，根据判定结果确定所述断线的位置。从而高效地自动检测屏幕是否产生显示断线并精确确定屏幕断线位置。
具体地，在步骤S11中，利用卷积神经网络获取断线中的目标点的信息。在此，利用训练好的卷积神经网络对断线进行检测，可得到断线中的多个点的信息，比如多个点对应的位置坐标信息以及对应的像素值等，其中，训练好的卷积神经网络由使用标注过的断线数据进行训练得到；接着，根据上述多个点的信息经过计算后得到所述目标点的信息，其中，所述目标点的信息包括但不限于目标点的位置坐标信息以及目标点的像素值。根据卷积神经网络使得获取所述目标点信息的过程变得简便、快捷，得到的结果直观，无需复杂的校验流程，且准确度高。
在步骤S12中，根据所述目标点的信息进行区域延伸，得到目标延伸图。在此，根据所述目标点的位置坐标信息以及所述目标点的像素值进行水平方向以及垂直方向的延伸，优选地，通过捕捉周围邻近的像素值不超过某一预设阈值的像素点以完成区域延伸，结合所述目标点来确定目标延伸图。
在步骤S13中，对所述目标延伸图进行判定，根据判定结果确定所述断线的位置。在此，判定得到的目标延伸图是否能够进一步进行延伸，若是，则进一步延伸该目标延伸图；若否，该目标延伸图即为所述断线，根据目标延伸图对应的位置坐标信息得到所述断线的位置坐标信息。
优选地，步骤S11中，利用卷积神经网络获取断线中的目标点的像素值；利用卷积神经网络获取断线中的目标点的坐标信息。在此，断线中目标点的信息包括但不限于像素值以及坐标信息，通过卷积神经网络能够精确获取断线中目标点的信息。
优选地，步骤S11中，利用卷积神经网络获取断线中的多个像素点的像素值；根据所述多个像素点的数量以及所述多个像素点的像素值确定所述目 标点的像素值。在此，可利用多个像素点的像素值的累加和与所述多个像素点的数量的比值确定所述目标点的像素值。
优选地，步骤S11中，利用卷积神经网络获取断线中的多个像素点对应的坐标信息；确定所述多个像素点的数量并计算所述多个像素点对应的坐标信息累加和；根据所述多个像素点对应的坐标信息的累加和与所述多个像素点的数量的比值确定所述目标点的坐标信息。在此，利用卷积神经网络能够自动并精确地获取到断线中多个像素点的坐标信息，以精确地获取到所述目标点的坐标信息。需要说明的是，以上确定所述目标点的坐标信息的方式仅为举例，还可以包括其他方式，比如还可以通过多个像素点对应的坐标信息的累加和与所述多个像素点的数量的加权平均数来确定所述目标点的坐标信息。
优选地，步骤S12中，根据所述目标点的坐标信息确定第一相邻像素，获取所述第一相邻像素的像素值；判断所述目标点的像素值与所述第一相邻像素的像素值的差值是否小于第一预设阈值，若是，则根据所述第一相邻像素与所述目标点确定目标延伸图。在此，利用所述目标点的坐标信息对周围直接相邻的像素进行捕捉，得到多个第一相邻像素，并获取到多个所述第一相邻像素的像素值。接着，设置第一预设阈值，当所述目标点的像素值与所述第一相邻像素的像素值的差值绝对值小于所述第一预设阈值时，将所述第一相邻像素通过预设方式加入所述目标点后组成目标延伸图，优选地，所述预设方式包括但不限于：将所述第一相邻像素和所述目标点进行预设方式的标记，根据预设方式的标记后的像素点确定所述目标延伸图。
优选地，步骤S13中，判定所述目标延伸图是否允许被区域延伸，若是，则对所述目标延伸图继续进行区域延伸；若否，则根据所述目标延伸图确定所述断线的位置。在此，所述区域延伸包括水平方向的延伸和垂直方向的延伸，当所述目标延伸图不能够继续进行区域延伸时，所述目标延伸图即为断线，根据所述目标延伸图的位置确定所述断线的位置。
接上述实施例，确定所述目标延伸图水平方向延伸到当前最后一个水平位置时的所有像素点的像素平均值；获取所述当前最后一个水平位置处相邻像素的像素值，根据所述当前最后一个水平位置处相邻像素的像素值及所述像素平均值判断所述目标延伸图是否允许被区域延伸，若是，则对所述目标延伸图继续进行区域延伸；若否，则将所述目标延伸图作为所述断线的位置。在此，所述目标延伸图进行水平延伸后到达当前最后一个水平位置，比较所述当前最后一个水平位置处相邻像素的像素值与所述像素平均值，其中，所述当前最后一个水平位置处相邻像素不在所述目标延伸图内。优选地，设置第二预设阈值，当所述当前最后一个水平位置处相邻像素的像素值与所述像素平均值的差值小于所述第二预设阈值时，所述目标延伸图允许被区域延伸，将所述当前最后一个水平位置处相邻像素纳入所述目标延伸图内并继续水平延伸所述目标延伸图；当所述当前最后一个水平位置处像素的像素值与所述像素平均值的差值大于等于所述第二预设阈值时，所述目标延伸图不被允许延伸至当前最后一个水平位置，所述目标延伸图的水平位置即为所述断线的水平位置，以精确地确认所述断线的水平位置。
接上述实施例，确定所述目标延伸图垂直方向延伸到当前最后一个垂直位置时的所有像素点的像素平均值；获取所述当前最后一个垂直位置处相邻像素的像素值，根据所述当前最后一个垂直位置处相邻像素的像素值及所述像素平均值判断所述目标延伸图是否允许被区域延伸，若是，则对所述目标延伸图继续进行区域延伸；若否，则将所述目标延伸图作为所述断线的位置。在此，所述目标延伸图进行垂直延伸后到达当前最后一个垂直位置，比较所述当前最后一个垂直位置处相邻像素的像素值与所述像素平均值，其中，所述当前最后一个垂直位置处相邻像素不在所述目标延伸图内。优选地，设置第三预设阈值，当所述当前最后一个垂直位置处相邻像素的像素值与所述像素平均值的差值小于所述第三预设阈值时，所述目标延伸图允许被区域延伸，将所述当前最后一个垂直位置处相邻像素纳入所述目标延伸图内并继续垂直 延伸所述目标延伸图；当所述当前最后一个垂直位置处相邻像素的像素值与所述像素平均值的差值大于等于所述第三预设阈值时，所述目标延伸图不被允许延伸至当前最后一个垂直位置，所述目标延伸图的垂直位置即为所述断线的垂直位置，以精确地确认所述断线的垂直位置。
优选地，所述卷积神经网络为分割神经网络u-net网络。在本优选实施例中，可通过人工标注屏幕显示断线图片的断线区域和正常显示区域，利用标注后的图片训练分割神经网络u-net网络后得到断线检测模型，使用所述断线检测模型检测待检测图片，当检测到断线时，得到断线内的多个像素点，通过前述方式进行计算后能够精确地得到目标点。
此外，本申请实施例还提供了一种计算机可读介质，其上存储有计算机可读指令，所述计算机可读指令可被处理器执行以实现前述一种检测屏幕显示断线的方法。
根据本申请再一个方面，还提供了一种检测屏幕显示断线的设备，其中，所述设备包括：
一个或多个处理器；以及
存储有计算机可读指令的存储器，所述计算机可读指令在被执行时使所述处理器执行前述一种检测屏幕显示断线的方法的操作。
例如，计算机可读指令在被执行时使所述一个或多个处理器：利用卷积神经网络获取断线中的目标点的信息；根据所述目标点的信息进行区域延伸，得到目标延伸图；对所述目标延伸图进行判定，根据判定结果确定所述断线的位置。
显然，本领域的技术人员可以对本申请进行各种改动和变型而不脱离本申请的精神和范围。这样，倘若本申请的这些修改和变型属于本申请权利要求及其等同技术的范围之内，则本申请也意图包含这些改动和变型在内。
需要注意的是，本申请可在软件和/或软件与硬件的组合体中被实施，例 如，可采用专用集成电路(ASIC)、通用目的计算机或任何其他类似硬件设备来实现。在一个实施例中，本申请的软件程序可以通过处理器执行以实现上文所述步骤或功能。同样地，本申请的软件程序(包括相关的数据结构)可以被存储到计算机可读记录介质中，例如，RAM存储器，磁或光驱动器或软磁盘及类似设备。另外，本申请的一些步骤或功能可采用硬件来实现，例如，作为与处理器配合从而执行各个步骤或功能的电路。
另外，本申请的一部分可被应用为计算机程序产品，例如计算机程序指令，当其被计算机执行时，通过该计算机的操作，可以调用或提供根据本申请的方法和/或技术方案。而调用本申请的方法的程序指令，可能被存储在固定的或可移动的记录介质中，和/或通过广播或其他信号承载媒体中的数据流而被传输，和/或被存储在根据所述程序指令运行的计算机设备的工作存储器中。在此，根据本申请的一个实施例包括一个装置，该装置包括用于存储计算机程序指令的存储器和用于执行程序指令的处理器，其中，当该计算机程序指令被该处理器执行时，触发该装置运行基于前述根据本申请的多个实施例的方法和/或技术方案。
对于本领域技术人员而言，显然本申请不限于上述示范性实施例的细节，而且在不背离本申请的精神或基本特征的情况下，能够以其他的具体形式实现本申请。因此，无论从哪一点来看，均应将实施例看作是示范性的，而且是非限制性的，本申请的范围由所附权利要求而不是上述说明限定，因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附图标记视为限制所涉及的权利要求。此外，显然“包括”一词不排除其他单元或步骤，单数不排除复数。装置权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第一，第二等词语用来表示名称，而并不表示任何特定的顺序。

Claims (11)

  1. 一种检测屏幕显示断线的方法，其中，所述方法包括：
    利用卷积神经网络获取断线中的目标点的信息；
    根据所述目标点的信息进行区域延伸，得到目标延伸图；
    对所述目标延伸图进行判定，根据判定结果确定所述断线的位置。
  2. 根据权利要求1所述的方法，其中，所述利用卷积神经网络获取断线中的目标点的信息，包括：
    利用卷积神经网络获取断线中的目标点的像素值；
    利用卷积神经网络获取断线中的目标点的坐标信息。
  3. 根据权利要求2所述的方法，其中，所述利用卷积神经网络获取断线中的目标点的像素值，包括：
    利用卷积神经网络获取断线中的多个像素点的像素值；
    根据所述多个像素点的数量以及所述多个像素点的像素值确定所述目标点的像素值。
  4. 根据权利要求2所述的方法，其中，所述利用卷积神经网络获取断线中的目标点的坐标信息，包括：
    利用卷积神经网络获取断线中的多个像素点对应的坐标信息；
    确定所述多个像素点的数量并计算所述多个像素点对应的坐标信息累加和；
    根据所述多个像素点对应的坐标信息的累加和与所述多个像素点的数量的比值确定所述目标点的坐标信息。
  5. 根据权利要求2所述的方法，其中，所述根据所述目标点的信息进行区域延伸，得到目标延伸图，包括：
    根据所述目标点的坐标信息确定第一相邻像素，获取所述第一相邻像素的像素值；
    判断所述目标点的像素值与所述第一相邻像素的像素值的差值是否小于第一预设阈值，若是，则根据所述第一相邻像素与所述目标点确定目标延伸图。
  6. 根据权利要求1所述的方法，其中，所述对所述目标延伸图进行判定，根据判定结果确定所述断线的位置，包括：
    判定所述目标延伸图是否允许被区域延伸，若是，则对所述目标延伸图继续进行区域延伸；若否，则根据所述目标延伸图确定所述断线的位置。
  7. 根据权利要求6所述的方法，其中，判定所述目标延伸图是否允许被区域延伸，若是，则对所述目标延伸图继续进行区域延伸；若否，则根据所述目标延伸图确定所述断线的位置，包括：
    确定所述目标延伸图水平方向延伸到当前最后一个水平位置时的所有像素点的像素平均值；
    获取所述当前最后一个水平位置处相邻像素的像素值，根据所述当前最后一个水平位置处相邻像素的像素值及所述像素平均值判断所述目标延伸图是否允许被区域延伸，若是，则对所述目标延伸图继续进行区域延伸；若否，则将所述目标延伸图作为所述断线的位置。
  8. 根据权利要求6所述的方法，其中，判定所述目标延伸图是否允许被区域延伸，若是，则对所述目标延伸图继续进行区域延伸；若否，则根据所述目标延伸图确定所述断线的位置，包括：
    确定所述目标延伸图垂直方向延伸到当前最后一个垂直位置时的所 有像素点的像素平均值；
    获取所述当前最后一个垂直位置处相邻像素的像素值，根据所述当前最后一个垂直位置处相邻像素的像素值及所述像素平均值判断所述目标延伸图是否允许被区域延伸，若是，则对所述目标延伸图继续进行区域延伸；若否，则将所述目标延伸图作为所述断线的位置。
  9. 根据权利要求1所述的方法，其中，所述卷积神经网络为分割神经网络u-net网络。
  10. 一种检测屏幕显示断线的设备，其中，所述设备包括：
    一个或多个处理器；以及
    存储有计算机可读指令的存储器，所述计算机可读指令在被执行时使所述处理器执行如权利要求1至9中任一项所述方法的操作。
  11. 一种计算机可读介质，其上存储有计算机可读指令，所述计算机可读指令可被处理器执行以实现如权利要求1至9中任一项所述的方法。
PCT/CN2020/120879 2019-10-28 2020-10-14 一种检测屏幕显示断线的方法及设备 WO2021082922A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911032867.4 2019-10-28
CN201911032867.4A CN110827245A (zh) 2019-10-28 2019-10-28 一种检测屏幕显示断线的方法及设备

Publications (1)

Publication Number Publication Date
WO2021082922A1 true WO2021082922A1 (zh) 2021-05-06

Family

ID=69551074

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/120879 WO2021082922A1 (zh) 2019-10-28 2020-10-14 一种检测屏幕显示断线的方法及设备

Country Status (2)

Country Link
CN (1) CN110827245A (zh)
WO (1) WO2021082922A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11798250B2 (en) 2019-02-18 2023-10-24 Ecoatm, Llc Neural network based physical condition evaluation of electronic devices, and associated systems and methods
US11843206B2 (en) 2019-02-12 2023-12-12 Ecoatm, Llc Connector carrier for electronic device kiosk
US11922467B2 (en) 2020-08-17 2024-03-05 ecoATM, Inc. Evaluating an electronic device using optical character recognition
US11989710B2 (en) 2018-12-19 2024-05-21 Ecoatm, Llc Systems and methods for vending and/or purchasing mobile phones and other electronic devices

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110827245A (zh) * 2019-10-28 2020-02-21 上海悦易网络信息技术有限公司 一种检测屏幕显示断线的方法及设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140041917A1 (en) * 2012-08-10 2014-02-13 Beijing Boe Optoelectronics Technology Co., Ltd. Display panel
CN105677280A (zh) * 2016-01-05 2016-06-15 广东威创视讯科技股份有限公司 一种拼接显示屏拼缝画线处理方法及装置
CN108762568A (zh) * 2018-05-31 2018-11-06 广东美的制冷设备有限公司 触摸屏的断线修复方法、装置和家用电器
CN110827245A (zh) * 2019-10-28 2020-02-21 上海悦易网络信息技术有限公司 一种检测屏幕显示断线的方法及设备

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5664255B2 (ja) * 2011-01-14 2015-02-04 ソニー株式会社 画像処理装置、および画像処理方法、並びにプログラム
JP5699633B2 (ja) * 2011-01-28 2015-04-15 株式会社リコー 画像処理装置、画素補間方法およびプログラム
US9258555B2 (en) * 2012-08-29 2016-02-09 Hanwha Techwin Co., Ltd. Apparatus and method for determining defect pixel
CN103888690B (zh) * 2012-12-19 2018-08-03 韩华泰科株式会社 用于检测缺陷像素的设备和方法
US11210777B2 (en) * 2016-04-28 2021-12-28 Blancco Technology Group IP Oy System and method for detection of mobile device fault conditions
CN107452002A (zh) * 2016-05-31 2017-12-08 百度在线网络技术（北京）有限公司 一种图像分割方法及装置
CN107123111B (zh) * 2017-04-14 2020-01-24 惠州旭鑫智能技术有限公司 一种用于手机屏幕缺陷检测的深度残差网络构造方法
CN109726754A (zh) * 2018-12-25 2019-05-07 浙江大学昆山创新中心 一种lcd屏缺陷识别方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140041917A1 (en) * 2012-08-10 2014-02-13 Beijing Boe Optoelectronics Technology Co., Ltd. Display panel
CN105677280A (zh) * 2016-01-05 2016-06-15 广东威创视讯科技股份有限公司 一种拼接显示屏拼缝画线处理方法及装置
CN108762568A (zh) * 2018-05-31 2018-11-06 广东美的制冷设备有限公司 触摸屏的断线修复方法、装置和家用电器
CN110827245A (zh) * 2019-10-28 2020-02-21 上海悦易网络信息技术有限公司 一种检测屏幕显示断线的方法及设备

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11989710B2 (en) 2018-12-19 2024-05-21 Ecoatm, Llc Systems and methods for vending and/or purchasing mobile phones and other electronic devices
US11843206B2 (en) 2019-02-12 2023-12-12 Ecoatm, Llc Connector carrier for electronic device kiosk
US11798250B2 (en) 2019-02-18 2023-10-24 Ecoatm, Llc Neural network based physical condition evaluation of electronic devices, and associated systems and methods
US11922467B2 (en) 2020-08-17 2024-03-05 ecoATM, Inc. Evaluating an electronic device using optical character recognition

Also Published As

Publication number Publication date
CN110827245A (zh) 2020-02-21

Similar Documents

Publication Publication Date Title
WO2021082922A1 (zh) 一种检测屏幕显示断线的方法及设备
WO2021082923A1 (zh) 一种电子设备屏幕区域瑕疵检测方法与设备
EP3620981A1 (en) Object detection method, device, apparatus and computer-readable storage medium
US20180260963A1 (en) Apparatus, method and image processing device for smoke detection in image
WO2021147385A1 (zh) 屏幕检测方法及装置
CN108769776B (zh) 标题字幕检测方法、装置及电子设备
WO2021082920A1 (zh) 电子设备边框外观瑕疵检测方法及设备
US8442327B2 (en) Application of classifiers to sub-sampled integral images for detecting faces in images
JP6720694B2 (ja) 画像処理プログラム、画像処理方法および画像処理装置
TW201335892A (zh) 特殊邊界量測系統及方法
CN111666907B (zh) 一种视频中对象信息的识别方法、装置及服务器
CN111310759B (zh) 双模式协作的目标检测抑制优化方法及设备
WO2021147384A1 (zh) 相机抖动检测方法及装置
US9087272B2 (en) Optical match character classification
CN114359932B (zh) 文本检测方法、文本识别方法及装置
CN111553914A (zh) 基于视觉的货物检测方法、装置、终端及可读存储介质
CN112802104B (zh) 一种基于rgb-d相机的回环检测方法
US10965858B2 (en) Image processing apparatus, control method thereof, and non-transitory computer-readable storage medium for detecting moving object in captured image
WO2021147383A1 (zh) 相机模糊检测方法及装置
US9087378B2 (en) Scale changing detection and scaling ratio determination by using motion information
CN108133116B (zh) Cad户型图墙厚自动识别方法及系统
CN112036232B (zh) 一种图像表格结构识别方法、系统、终端以及存储介质
WO2019100616A1 (zh) 事件评价数据显示方法、装置、计算机设备及计算机存储介质
JP5983033B2 (ja) 位置関係判定プログラム、位置関係判定方法および位置関係判定装置
JP2015130166A (ja) 裏面透かしの検出方法及び裏面透かしの検出装置

Legal Events

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

Ref document number: 20883382

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20883382

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20883382

Country of ref document: EP

Kind code of ref document: A1

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

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 26.01.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20883382

Country of ref document: EP

Kind code of ref document: A1