[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2021082918A1 - 屏幕外观瑕疵检测方法及设备 - Google Patents

屏幕外观瑕疵检测方法及设备 Download PDF

Info

Publication number
WO2021082918A1
WO2021082918A1 PCT/CN2020/120874 CN2020120874W WO2021082918A1 WO 2021082918 A1 WO2021082918 A1 WO 2021082918A1 CN 2020120874 W CN2020120874 W CN 2020120874W WO 2021082918 A1 WO2021082918 A1 WO 2021082918A1
Authority
WO
WIPO (PCT)
Prior art keywords
electronic device
screen
defect
image
model
Prior art date
Application number
PCT/CN2020/120874
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 WO2021082918A1 publication Critical patent/WO2021082918A1/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
    • 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
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques

Definitions

  • the present invention relates to the field of computers, and in particular to a method and equipment for detecting screen appearance defects.
  • the traditional image processing method is based on the selection of the threshold to a large extent, and the appearance of the screen of second-hand electronic equipment such as mobile phones has different degrees of difference in various aspects such as color, appearance, aging, etc., it is difficult to give The determined threshold is therefore not applicable in the detection of screen appearance defects based on traditional image processing methods.
  • An object of the present invention is to provide a method and device for detecting defects in the appearance of a screen.
  • a method for detecting screen appearance defects including:
  • the defect detection result of the screen appearance area of the electronic device received and output from the FPN network combined with the backbone network model includes: the type of the defect of the electronic device's screen, the position of the defect in the screen of the electronic device, and the defect The confidence level of the test result.
  • extracting the screen appearance area image of the electronic device from the appearance image of the electronic device includes:
  • the Unet instance segmentation method is used to extract the screen appearance area image of the electronic device from the appearance image of the electronic device.
  • the first two layers of the backbone network adopt a res structure
  • the last two layers of the network adopt an inception structure
  • the method after receiving the output defect detection result of the screen appearance area of the electronic device from the model of the FPN network combined with the backbone network, the method further includes:
  • the method before inputting the screen appearance area image into the FPN network combined with the backbone network model, the method further includes:
  • Step one preset the FPN network combined with the backbone network model and its initial model parameters
  • Step 2 Input the image of the screen appearance area of the sample electronic device into the model of the FPN network combined with the backbone network with the current model parameters to obtain the defect prediction result of the screen of the sample electronic device.
  • the defect prediction result includes: The type of screen defect, the position of the defect on the screen of the sample electronic device, and the confidence level of the defect detection result;
  • Step 3 Calculate the difference between the defect prediction result and the real defect result of the sample electronic device based on a preset objective function, and identify whether the difference is greater than a second preset threshold,
  • step 4 after updating the model parameters of the FPN network combined with the backbone network based on the difference, restart execution from step 2;
  • step 5 the FPN network combined with the backbone network model with the current model parameters is used as the model of the FPN network combined with the backbone network after the training.
  • a screen appearance defect detection device which includes:
  • the first device is used to obtain the appearance image of the electronic device
  • the second device is used to extract the screen appearance area image of the electronic device from the appearance image of the electronic device;
  • the third device is used to input the image of the screen appearance area into the model of the FPN network combined with the backbone network after the training;
  • the fourth device is used to receive and output the defect detection result of the screen appearance area of the electronic device from the model of the FPN network combined with the backbone network.
  • the defect detection result includes: the defect type of the screen of the electronic device, and the defect in the electronic device The position on the screen and the confidence level of the defect detection result.
  • the second device is used to extract the screen appearance area image of the electronic device from the appearance image of the electronic device by using the Unet instance segmentation method.
  • the first two layers of the backbone network adopt a res structure
  • the last two layers of the network adopt an inception structure
  • the fourth device is also used to identify whether the confidence level of the defect detection result is greater than a first preset threshold, and if it is greater than the first preset threshold, output the screen including the electronic device The result information of the defect type and the position of the defect on the screen of the electronic device.
  • the above-mentioned equipment further includes a fifth device, including:
  • the fifth device is used to preset the FPN network combined with the backbone network model and its initial model parameters
  • the fifth and second device is used to input the screen appearance area image of the sample electronic device into the FPN network with current model parameters combined with the backbone network model to obtain the defect prediction result of the screen of the sample electronic device, and the defect prediction result includes: The type of defect on the screen of the sample electronic device, the position of the defect on the screen of the sample electronic device, and the confidence level of the defect detection result;
  • the fifty-third device is configured to calculate the difference between the defect prediction result and the actual defect result of the sample electronic device based on a preset objective function, and to identify whether the difference is greater than a second preset threshold, if the difference is If it is greater than the second preset threshold, execute the fifth and fourth device for updating the model parameters of the FPN network combined with the backbone network based on the difference, and then restart execution from the fifth and second device;
  • the fifth and fifth device is executed, and the model of the FPN network combined with the backbone network with the current model parameters is used as the model of the FPN network combined with the backbone network after the training is completed.
  • the present invention also provides a computing-based device, which includes:
  • a memory arranged to store computer-executable instructions which, when executed, cause the processor to:
  • Step S1 obtaining an appearance image of the electronic device
  • Step S2 extracting an image of the screen appearance area of the electronic device from the appearance image of the electronic device
  • Step S3 input the image of the screen appearance area into the model of the FPN network combined with the backbone network after the training;
  • Step S4 receiving and outputting the defect detection result of the screen appearance area of the electronic device from the model of the FPN network combined with the backbone network. Confidence of location and defect detection results.
  • the present invention also provides a computer-readable storage medium on which computer-executable instructions are stored, wherein, when the computer-executable instructions are executed by a processor, the processor:
  • Step S1 obtaining an appearance image of the electronic device
  • Step S2 extracting an image of the screen appearance area of the electronic device from the appearance image of the electronic device
  • Step S3 input the image of the screen appearance area into the model of the FPN network combined with the backbone network after the training;
  • Step S4 receiving and outputting the defect detection result of the screen appearance area of the electronic device from the model of the FPN network combined with the backbone network. Confidence of location and defect detection results.
  • the present invention obtains the appearance image of the electronic device; extracts the screen appearance area image of the electronic device from the appearance image of the electronic device; and inputs the screen appearance area image into the FPN network after training.
  • the defect detection result includes: the type of the defect on the screen of the electronic device, and the defect. The position in the screen and the confidence level of the defect detection result can accurately identify the difference in the appearance of the defects of the screen of second-hand electronic equipment such as mobile phones.
  • FIG. 1 shows a flowchart of a method for detecting screen appearance defects according to an embodiment of the present invention
  • Fig. 2 shows a schematic diagram of a defect detection result according to an embodiment of the present invention
  • FIG. 3 shows a schematic diagram of a model of an FPN network combined with a backbone network according to an embodiment of the present invention.
  • 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.
  • the present invention provides a method for detecting screen appearance defects, the method including:
  • Step S1 obtaining an appearance image of the electronic device
  • Step S2 extracting an image of the screen appearance area of the electronic device from the appearance image of the electronic device
  • Step S3 input the image of the screen appearance area into the model of the FPN network combined with the backbone network after the training;
  • Step S4 receiving and outputting the defect detection result of the screen appearance area of the electronic device from the model of the FPN network combined with the backbone network. Confidence of location and defect detection results.
  • the model of the FPN network combined with the backbone network can be shown in FIG. 3.
  • each defect detection result includes cls, x1, y1, x2, y2, score ,
  • cls is the defect type
  • x1, y1, x2, y2 are the 4 coordinates of the position of the defect in the image of the screen appearance area
  • score is the confidence level of this defect.
  • the present invention mainly utilizes the improved feature pyramid (FPN) network combined with the deep learning model of the backbone network, which can accurately identify the difference in the appearance of second-hand electronic devices such as mobile phones.
  • FPN improved feature pyramid
  • step S2 extracting the screen appearance area image of the electronic device from the appearance image of the electronic device includes:
  • the Unet instance segmentation method is used to extract the screen appearance area image of the electronic device from the appearance image of the electronic device.
  • the screen appearance area image can be quickly and efficiently obtained.
  • the first two layers of the backbone network adopt a res structure
  • the last two layers of the network adopt an inception structure
  • step S4 after receiving the output defect detection result of the screen appearance area of the electronic device from the FPN network combined with the backbone network model, the method further includes:
  • the types of defects of the screen may sequentially include the types of shallow scratches, hard scratches, and chipping with increasing levels.
  • step S3 before inputting the screen appearance area image into the FPN network combined with the backbone network model further includes:
  • Step one preset the FPN network combined with the backbone network model and its initial model parameters
  • Step 2 Input the image of the screen appearance area of the sample electronic device into the FPN network combined with the backbone network model with the current model parameters to obtain the defect prediction result of the screen of the sample electronic device.
  • the defect prediction result includes: The type of screen defect, the position of the defect on the screen of the sample electronic device, and the confidence level of the defect detection result;
  • Step 3 Calculate the difference between the defect prediction result and the real defect result of the sample electronic device based on a preset objective function, and identify whether the difference is greater than a second preset threshold,
  • step 4 after updating the model parameters of the FPN network combined with the backbone network based on the difference, restart execution from step 2;
  • step 5 the FPN network combined with the backbone network model with the current model parameters is used as the model of the FPN network combined with the backbone network after the training.
  • the model of the FPN network combined with the backbone network is cyclically trained to obtain a reliable model.
  • the present invention provides a device for detecting defects in the appearance of a screen, the device including:
  • the first device is used to obtain the appearance image of the electronic device
  • the second device is used to extract the screen appearance area image of the electronic device from the appearance image of the electronic device;
  • the third device is used to input the image of the screen appearance area into the model of the FPN network combined with the backbone network after the training;
  • the fourth device is used to receive and output the defect detection result of the screen appearance area of the electronic device from the model of the FPN network combined with the backbone network.
  • the defect detection result includes: the type of the defect of the screen of the electronic device, and the type of the defect in the electronic device The position on the screen and the confidence level of the defect detection result.
  • each defect detection result includes cls, x1, y1, x2, y2, score, where cls is a defect Type, x1, y1, x2, y2 are the 4 coordinates of the position of the defect in the image of the screen appearance area, and score is the confidence level of this defect.
  • the present invention mainly utilizes the improved feature pyramid (FPN) network combined with the deep learning model of the backbone network to accurately identify the difference in the appearance of the screen of second-hand electronic devices such as mobile phones.
  • FPN improved feature pyramid
  • the second device is used to extract the screen appearance area image of the electronic device from the appearance image of the electronic device by using the Unet instance segmentation method.
  • the screen appearance area image can be quickly and efficiently obtained.
  • the first two layers of the backbone network adopt a res structure
  • the last two layers of the network adopt an inception structure
  • the fourth device is also used to identify whether the confidence level of the defect detection result is greater than a first preset threshold, and if it is greater than the first preset threshold, then The output includes the result information of the defect type of the screen of the electronic device and the position of the defect on the screen of the electronic device.
  • the types of defects of the screen may sequentially include the types of shallow scratches, hard scratches, and chipping with increasing levels.
  • a fifth device including:
  • the fifth device is used to preset the FPN network combined with the backbone network model and its initial model parameters
  • the fifth and second device is used to input the screen appearance area image of the sample electronic device into the FPN network with current model parameters combined with the backbone network model to obtain the defect prediction result of the screen of the sample electronic device, and the defect prediction result includes: The type of defect on the screen of the sample electronic device, the position of the defect on the screen of the sample electronic device, and the confidence level of the defect detection result;
  • the fifty-third device is configured to calculate the difference between the defect prediction result and the actual defect result of the sample electronic device based on a preset objective function, and to identify whether the difference is greater than a second preset threshold, and if the difference is If it is greater than the second preset threshold, execute the fifth and fourth device for updating the model parameters of the FPN network combined with the backbone network based on the difference, and then restart execution from the fifth and second device;
  • the fifth and fifth device is executed, and the model of the FPN network combined with the backbone network with the current model parameters is used as the model of the FPN network combined with the backbone network after the training is completed.
  • the model of the FPN network combined with the backbone network is cyclically trained to obtain a reliable model.
  • the present invention also provides a computing-based device, which includes:
  • a memory arranged to store computer-executable instructions which, when executed, cause the processor to:
  • Step S1 obtaining an appearance image of the electronic device
  • Step S2 extracting an image of the screen appearance area of the electronic device from the appearance image of the electronic device
  • Step S3 input the image of the screen appearance area into the model of the FPN network combined with the backbone network after the training;
  • Step S4 receiving and outputting the defect detection result of the screen appearance area of the electronic device from the model of the FPN network combined with the backbone network.
  • the defect detection result includes: the type of the defect of the screen of the electronic device, and the number of defects in the screen of the electronic device. Confidence of location and defect detection results.
  • the present invention also provides a computer-readable storage medium on which computer-executable instructions are stored, wherein, when the computer-executable instructions are executed by a processor, the processor:
  • Step S1 obtaining an appearance image of the electronic device
  • Step S2 extracting an image of the screen appearance area of the electronic device from the appearance image of the electronic device
  • Step S3 input the image of the screen appearance area into the model of the FPN network combined with the backbone network after the training;
  • Step S4 receiving and outputting the defect detection result of the screen appearance area of the electronic device from the model of the FPN network combined with the backbone network.
  • the defect detection result includes: the type of the defect of the screen of the electronic device, and the number of defects in the screen of the electronic device. Confidence of location and defect detection results.
  • the present invention 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 invention may be executed by a processor to realize the above-mentioned steps or functions.
  • the software program (including related data structure) of the present invention can be stored in a computer-readable recording medium, such as a RAM memory, a magnetic or optical drive or a floppy disk and similar devices.
  • some steps or functions of the present invention may be implemented by hardware, for example, as a circuit that cooperates with a processor to execute each step or function.
  • a part of the present invention 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 the present invention can be invoked or provided.
  • the program instructions for invoking the method of the present invention may be stored in a fixed or removable recording medium, and/or transmitted through a data stream in a broadcast or other signal-bearing medium, and/or stored in accordance with the Said program instructions run in the working memory of the computer equipment.
  • an embodiment according to the present invention includes a device including 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, trigger
  • the operation of the device is based on the aforementioned methods and/or technical solutions according to multiple embodiments of the present invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Quality & Reliability (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Signal Processing (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
  • Image Analysis (AREA)

Abstract

本发明的目的是提供一种屏幕外观瑕疵检测方法及设备，本发明通过获取电子设备的外观图像；从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结果的置信度，能够准确地识别二手电子设备如手机的屏幕外观的瑕疵差异。

Description

屏幕外观瑕疵检测方法及设备 技术领域
本发明涉及计算机领域，尤其涉及一种屏幕外观瑕疵检测方法及设备。
背景技术
由于基于传统图像处理方式在很大程度上依赖于阈值的选取，而二手电子设备如手机等的屏幕外观由于在成色、外观、老化程度等各个方面都有不同程度的差异，故很难给出确定的阈值，因此基于传统图像处理方式的在本屏幕外观瑕疵检测中不适用。
发明内容
本发明的一个目的是提供一种屏幕外观瑕疵检测方法及设备。
根据本发明的一个方面，提供了一种屏幕外观瑕疵检测方法，该方法包括：
获取电子设备的外观图像；
从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；
将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；
从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结果的置信度。
进一步的，上述方法中，从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像，包括：
采用Unet实例分割的方式，从所述电子设备的外观图像中提取该电 子设备的屏幕外观区域图像。
进一步的，上述方法中，所述backbone网络的前2层采用res结构，网络的后2层采用inception结构。
进一步的，上述方法中，从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果之后，还包括：
识别所述瑕疵检测结果的置信度是否大于第一预设阈值，
若大于所述第一预设阈值，则输出包括电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置的结果信息。
进一步的，上述方法中，将所述屏幕外观区域图像输入FPN网络结合backbone网络的模型之前，还包括：
步骤一，预设FPN网络结合backbone网络的模型及其初始的模型参数；
步骤二，将样本电子设备的屏幕外观区域图像输入带有当前的模型参数的FPN网络结合backbone网络的模型，得到样本电子设备的屏幕的瑕疵预测结果，所述瑕疵预测结果包括：样本电子设备的屏幕的瑕疵种类、瑕疵在样本电子设备的屏幕中的位置和瑕疵检测结果的置信度；
步骤三，基于预设目标函数计算所述瑕疵预测结果与样本电子设备的真实瑕疵结果之间的差值，识别所述差值是否大于第二预设阈，
若所述差值大于第二预设阈值，则步骤四，基于所述差值更新所述FPN网络结合backbone网络的模型参数后，重新从步骤二开始执行；
若所述差值小于等于第二预设阈值，则步骤五，将带有当前的模型参数的FPN网络结合backbone网络的模型作为训练结束后的FPN网络结合backbone网络的模型。
根据本发明的另一方面，还提供了一种屏幕外观瑕疵检测设备，该设备包括：
第一装置，用于获取电子设备的外观图像；
第二装置，用于从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；
第三装置，用于将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；
第四装置，用于从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结果的置信度。
进一步的，上述设备中，所述第二装置，用于采用Unet实例分割的方式，从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像。
进一步的，上述设备中，所述backbone网络的前2层采用res结构，网络的后2层采用inception结构。
进一步的，上述设备中，所述第四装置，还用于识别所述瑕疵检测结果的置信度是否大于第一预设阈值，若大于所述第一预设阈值，则输出包括电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置的结果信息。
进一步的，上述设备中，还包括第五装置，包括：
第五一装置，用于预设FPN网络结合backbone网络的模型及其初始的模型参数；
第五二装置，用于将样本电子设备的屏幕外观区域图像输入带有当前的模型参数的FPN网络结合backbone网络的模型，得到样本电子设备的屏幕的瑕疵预测结果，所述瑕疵预测结果包括：样本电子设备的屏幕的瑕疵种类、瑕疵在样本电子设备的屏幕中的位置和瑕疵检测结果的置信度；
第五三装置，用于基于预设目标函数计算所述瑕疵预测结果与样本电 子设备的真实瑕疵结果之间的差值，识别所述差值是否大于第二预设阈，若所述差值大于第二预设阈值，则执行第五四装置，用于基于所述差值更新所述FPN网络结合backbone网络的模型参数后，重新从第五二装置开始执行；
若所述差值小于等于第二预设阈值，则执行第五五装置，将带有当前的模型参数的FPN网络结合backbone网络的模型作为训练结束后的FPN网络结合backbone网络的模型。
本发明还提供一种基于计算的设备，其中，包括：
处理器；以及
被安排成存储计算机可执行指令的存储器，所述可执行指令在被执行时使所述处理器：
步骤S1，获取电子设备的外观图像；
步骤S2，从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；
步骤S3，将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；
步骤S4，从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结果的置信度。
本发明还提供一种计算机可读存储介质，其上存储有计算机可执行指令，其中，该计算机可执行指令被处理器执行时使得该处理器：
步骤S1，获取电子设备的外观图像；
步骤S2，从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；
步骤S3，将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；
步骤S4，从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结果的置信度。
与现有技术相比，本发明通过获取电子设备的外观图像；从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结果的置信度，能够准确地识别二手电子设备如手机的屏幕外观的瑕疵差异。
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，本发明的其它特征、目的和优点将会变得更明显：
图1示出本发明一实施例的屏幕外观瑕疵检测方法的流程图；
图2示出本发明一实施例的瑕疵检测结果的示意图；
图3示出本发明一实施例的FPN网络结合backbone网络的模型的示意图。
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
下面结合附图对本发明作进一步详细描述。
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。
本发明提供一种屏幕外观瑕疵检测方法，所述方法包括：
步骤S1，获取电子设备的外观图像；
步骤S2，从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；
步骤S3，将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；
步骤S4，从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结果的置信度。
所述FPN网络结合backbone网络的模型可如图3所示。
在此，从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，如图2所示，每个瑕疵检测结果包含cls,x1,y1,x2,y2,score，其中，cls是缺陷类型，x1,y1,x2,y2是屏幕外观区域图像中瑕疵所在位置的4个坐标，score为这个瑕疵的置信度。
本发明主要利用改进的特征金字塔(FPN)网络结合backbone网络的深度学习模型，能够准确地识别二手电子设备如手机的屏幕外观的瑕疵差异。
本发明的屏幕外观瑕疵检测方法一实施例中，步骤S2，从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像，包括：
采用Unet实例分割的方式，从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像。
在此，通过Unet实例分割，能够快速高效的得到屏幕外观区域图像。
本发明的屏幕外观瑕疵检测方法一实施例中，所述backbone网络的前2层采用res结构，网络的后2层采用inception结构。
本发明的屏幕外观瑕疵检测方法一实施例中，步骤S4，从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果之后，还包括：
识别所述瑕疵检测结果的置信度是否大于第一预设阈值，
若大于所述第一预设阈值，则输出包括电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置的结果信息。
在此，屏幕的瑕疵种类可以依次包括等级依次增加的浅划痕、硬划痕和碎裂种类。
本实施例通过识别所述瑕疵检测结果的置信度，可以从瑕疵检测结果中筛选出可靠的结果进行输出。
本发明的屏幕外观瑕疵检测方法一实施例中，步骤S3，将所述屏幕外 观区域图像输入FPN网络结合backbone网络的模型之前，还包括：
步骤一，预设FPN网络结合backbone网络的模型及其初始的模型参数；
步骤二，将样本电子设备的屏幕外观区域图像输入带有当前的模型参数的FPN网络结合backbone网络的模型，得到样本电子设备的屏幕的瑕疵预测结果，所述瑕疵预测结果包括：样本电子设备的屏幕的瑕疵种类、瑕疵在样本电子设备的屏幕中的位置和瑕疵检测结果的置信度；
步骤三，基于预设目标函数计算所述瑕疵预测结果与样本电子设备的真实瑕疵结果之间的差值，识别所述差值是否大于第二预设阈，
若所述差值大于第二预设阈值，则步骤四，基于所述差值更新所述FPN网络结合backbone网络的模型参数后，重新从步骤二开始执行；
若所述差值小于等于第二预设阈值，则步骤五，将带有当前的模型参数的FPN网络结合backbone网络的模型作为训练结束后的FPN网络结合backbone网络的模型。
在此，通过识别所述差值是否大于第二预设阈，来循环训练FPN网络结合backbone网络的模型，能够得到可靠的模型。
本发明提供一种屏幕外观瑕疵检测设备，所述设备包括：
第一装置，用于获取电子设备的外观图像；
第二装置，用于从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；
第三装置，用于将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；
第四装置，用于从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结 果的置信度。
在此，从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，每个瑕疵检测结果包含cls,x1,y1,x2,y2,score，其中，cls是缺陷类型，x1,y1,x2,y2是屏幕外观区域图像中瑕疵所在位置的4个坐标，score为这个瑕疵的置信度。
本发明主要利用改进的特征金字塔(FPN)网络结合backbone网络的深度学习模型，能够准确地识别二手电子设备如手机的屏幕外观差异。
本发明的屏幕外观瑕疵检测方法一实施例中，所述第二装置，用于采用Unet实例分割的方式，从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像。
在此，通过Unet实例分割，能够快速高效的得到屏幕外观区域图像。
本发明的屏幕外观瑕疵检测方法一实施例中，所述backbone网络的前2层采用res结构，网络的后2层采用inception结构。
本发明的屏幕外观瑕疵检测方法一实施例中，所述第四装置，还用于识别所述瑕疵检测结果的置信度是否大于第一预设阈值，若大于所述第一预设阈值，则输出包括电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置的结果信息。
在此，屏幕的瑕疵种类可以依次包括等级依次增加的浅划痕、硬划痕和碎裂种类。
本实施例通过识别所述瑕疵检测结果的置信度，可以从瑕疵检测结果中筛选出可靠的结果进行输出。
本发明的屏幕外观瑕疵检测方法一实施例中，还包括第五装置，包括：
第五一装置，用于预设FPN网络结合backbone网络的模型及其初始的模型参数；
第五二装置，用于将样本电子设备的屏幕外观区域图像输入带有当前的模型参数的FPN网络结合backbone网络的模型，得到样本电子设备的 屏幕的瑕疵预测结果，所述瑕疵预测结果包括：样本电子设备的屏幕的瑕疵种类、瑕疵在样本电子设备的屏幕中的位置和瑕疵检测结果的置信度；
第五三装置，用于基于预设目标函数计算所述瑕疵预测结果与样本电子设备的真实瑕疵结果之间的差值，识别所述差值是否大于第二预设阈，若所述差值大于第二预设阈值，则执行第五四装置，用于基于所述差值更新所述FPN网络结合backbone网络的模型参数后，重新从第五二装置开始执行；
若所述差值小于等于第二预设阈值，则执行第五五装置，将带有当前的模型参数的FPN网络结合backbone网络的模型作为训练结束后的FPN网络结合backbone网络的模型。
在此，通过识别所述差值是否大于第二预设阈，来循环训练FPN网络结合backbone网络的模型，能够得到可靠的模型。
本发明还提供一种基于计算的设备，其中，包括：
处理器；以及
被安排成存储计算机可执行指令的存储器，所述可执行指令在被执行时使所述处理器：
步骤S1，获取电子设备的外观图像；
步骤S2，从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；
步骤S3，将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；
步骤S4，从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结果的置信度。
本发明还提供一种计算机可读存储介质，其上存储有计算机可执行指令，其中，该计算机可执行指令被处理器执行时使得该处理器：
步骤S1，获取电子设备的外观图像；
步骤S2，从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；
步骤S3，将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；
步骤S4，从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结果的置信度。
本发明的各设备和存储介质实施例的详细内容，具体可参见各方法实施例的对应部分，在此，不再赘述。
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，本发明可在软件和/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，本发明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，本发明的软件程序(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，本发明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，本发明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发明的方法和/或技术方案。而调用本发明的方法的程序指令，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，根据本发明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发明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，显然本发明不限于上述示范性实施例的细节，而且在不背离本发明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发明。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，本发明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发明内。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 (12)

  1. 一种屏幕外观瑕疵检测方法，其中，该方法包括：
    获取电子设备的外观图像；
    从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；
    将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；
    从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结果的置信度。
  2. 根据权利要求1所述的方法，其中，从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像，包括：
    采用Unet实例分割的方式，从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像。
  3. 根据权利要求1所述的方法，其中，所述backbone网络的前2层采用res结构，网络的后2层采用inception结构。
  4. 根据权利要求1所述的方法，其中，从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果之后，还包括：
    识别所述瑕疵检测结果的置信度是否大于第一预设阈值，
    若大于所述第一预设阈值，则输出包括电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置的结果信息。
  5. 根据权利要求1所述的方法，其中，将所述屏幕外观区域图像输入FPN网络结合backbone网络的模型之前，还包括：
    步骤一，预设FPN网络结合backbone网络的模型及其初始的模型参数；
    步骤二，将样本电子设备的屏幕外观区域图像输入带有当前的模型参数的FPN网络结合backbone网络的模型，得到样本电子设备的屏幕的瑕疵预测结果，所述瑕疵预测结果包括：样本电子设备的屏幕的瑕疵种类、瑕疵在样本电子设备的屏幕中的位置和瑕疵检测结果的置信度；
    步骤三，基于预设目标函数计算所述瑕疵预测结果与样本电子设备的真实瑕疵结果之间的差值，识别所述差值是否大于第二预设阈，
    若所述差值大于第二预设阈值，则步骤四，基于所述差值更新所述FPN网络结合backbone网络的模型参数后，重新从步骤二开始执行；
    若所述差值小于等于第二预设阈值，则步骤五，将带有当前的模型参数的FPN网络结合backbone网络的模型作为训练结束后的FPN网络结合backbone网络的模型。
  6. 一种屏幕外观瑕疵检测设备，其中，该设备包括：
    第一装置，用于获取电子设备的外观图像；
    第二装置，用于从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；
    第三装置，用于将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；
    第四装置，用于从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结果的置信度。
  7. 根据权利要求6所述的装置，其中，所述第二装置，用于采用Unet实例分割的方式，从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像。
  8. 根据权利要求6所述的装置，其中，所述backbone网络的前2层采用res结构，网络的后2层采用inception结构。
  9. 根据权利要求6所述的装置，其中，所述第四装置，还用于识别所述瑕疵检测结果的置信度是否大于第一预设阈值，若大于所述第一预设阈值，则输出包括电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置的结果信息。
  10. 根据权利要求6所述的装置，其中，还包括第五装置，包括：
    第五一装置，用于预设FPN网络结合backbone网络的模型及其初始的模型参数；
    第五二装置，用于将样本电子设备的屏幕外观区域图像输入带有当前的模型参数的FPN网络结合backbone网络的模型，得到样本电子设备的屏幕的瑕疵预测结果，所述瑕疵预测结果包括：样本电子设备的屏幕的瑕疵种类、瑕疵在样本电子设备的屏幕中的位置和瑕疵检测结果的置信度；
    第五三装置，用于基于预设目标函数计算所述瑕疵预测结果与样本电子设备的真实瑕疵结果之间的差值，识别所述差值是否大于第二预设阈，若所述差值大于第二预设阈值，则执行第五四装置，用于基于所述差值更新所述FPN网络结合backbone网络的模型参数后，重新从第五二装置开始执行；
    若所述差值小于等于第二预设阈值，则执行第五五装置，将带有当前的模型参数的FPN网络结合backbone网络的模型作为训练结束后的FPN网络结合backbone网络的模型。
  11. 一种基于计算的设备，其中，包括：
    处理器；以及
    被安排成存储计算机可执行指令的存储器，所述可执行指令在被执行 时使所述处理器：
    获取电子设备的外观图像；
    从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；
    将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；
    从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结果的置信度。
  12. 一种计算机可读存储介质，其上存储有计算机可执行指令，其中，该计算机可执行指令被处理器执行时使得该处理器：
    获取电子设备的外观图像；
    从所述电子设备的外观图像中提取该电子设备的屏幕外观区域图像；
    将所述屏幕外观区域图像输入训练结束后的FPN网络结合backbone网络的模型；
    从所述FPN网络结合backbone网络的模型接收输出的电子设备的屏幕外观区域的瑕疵检测结果，所述瑕疵检测结果包括：电子设备的屏幕的瑕疵种类、瑕疵在电子设备的屏幕中的位置和瑕疵检测结果的置信度。
PCT/CN2020/120874 2019-10-28 2020-10-14 屏幕外观瑕疵检测方法及设备 WO2021082918A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911032898.X 2019-10-28
CN201911032898.XA CN110675399A (zh) 2019-10-28 2019-10-28 屏幕外观瑕疵检测方法及设备

Publications (1)

Publication Number Publication Date
WO2021082918A1 true WO2021082918A1 (zh) 2021-05-06

Family

ID=69084568

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/120874 WO2021082918A1 (zh) 2019-10-28 2020-10-14 屏幕外观瑕疵检测方法及设备

Country Status (2)

Country Link
CN (1) CN110675399A (zh)
WO (1) WO2021082918A1 (zh)

Cited By (7)

* 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
US11836912B2 (en) * 2020-09-22 2023-12-05 Future Dial, Inc. Grading cosmetic appearance of a test object based on multi-region determination of cosmetic defects
US11843206B2 (en) 2019-02-12 2023-12-12 Ecoatm, Llc Connector carrier for electronic device kiosk
US11900581B2 (en) 2020-09-22 2024-02-13 Future Dial, Inc. Cosmetic inspection system
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
US12033454B2 (en) 2020-08-17 2024-07-09 Ecoatm, Llc Kiosk for evaluating and purchasing used electronic devices

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110827249A (zh) * 2019-10-28 2020-02-21 上海悦易网络信息技术有限公司 电子设备背板外观瑕疵检测方法及设备
CN110675399A (zh) * 2019-10-28 2020-01-10 上海悦易网络信息技术有限公司 屏幕外观瑕疵检测方法及设备
CN111325716B (zh) * 2020-01-21 2023-09-01 上海万物新生环保科技集团有限公司 屏幕划痕碎裂检测方法及设备
CN111325717B (zh) * 2020-01-21 2023-08-29 上海万物新生环保科技集团有限公司 手机缺陷位置识别方法及设备
CN111311556B (zh) * 2020-01-21 2023-02-03 上海万物新生环保科技集团有限公司 手机缺陷位置识别方法及设备
CN111539456B (zh) * 2020-04-02 2024-03-01 浙江华睿科技股份有限公司 一种目标识别方法及设备
CN113052798A (zh) * 2021-03-08 2021-06-29 广州绿怡信息科技有限公司 屏幕老化检测模型训练方法及屏幕老化检测方法
CN114885056B (zh) * 2022-05-06 2024-10-01 深圳市金得源科技有限公司 移动终端检测方法、系统、检测设备及存储介质

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090257350A1 (en) * 2008-04-09 2009-10-15 Embarq Holdings Company, Llc System and method for using network performance information to determine improved measures of path states
CN108846841A (zh) * 2018-07-02 2018-11-20 北京百度网讯科技有限公司 显示屏质量检测方法、装置、电子设备及存储介质
CN109461149A (zh) * 2018-10-31 2019-03-12 泰州市创新电子有限公司 喷漆表面缺陷的智能检测系统及方法
CN109711474A (zh) * 2018-12-24 2019-05-03 中山大学 一种基于深度学习的铝材表面缺陷检测算法
CN109886077A (zh) * 2018-12-28 2019-06-14 北京旷视科技有限公司 图像识别方法、装置、计算机设备和存储介质
CN110110661A (zh) * 2019-05-07 2019-08-09 西南石油大学 一种基于unet分割的岩石图像孔隙类型识别方法
CN110675399A (zh) * 2019-10-28 2020-01-10 上海悦易网络信息技术有限公司 屏幕外观瑕疵检测方法及设备
CN110796647A (zh) * 2019-10-28 2020-02-14 上海悦易网络信息技术有限公司 一种电子设备屏幕区域瑕疵检测方法与设备
CN110796646A (zh) * 2019-10-28 2020-02-14 上海悦易网络信息技术有限公司 一种电子设备屏幕区域瑕疵检测方法与设备
CN110827246A (zh) * 2019-10-28 2020-02-21 上海悦易网络信息技术有限公司 电子设备边框外观瑕疵检测方法及设备
CN110827244A (zh) * 2019-10-28 2020-02-21 上海悦易网络信息技术有限公司 一种用于电子设备外观瑕疵检测的方法与设备
CN110827249A (zh) * 2019-10-28 2020-02-21 上海悦易网络信息技术有限公司 电子设备背板外观瑕疵检测方法及设备

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106875381B (zh) * 2017-01-17 2020-04-28 同济大学 一种基于深度学习的手机外壳缺陷检测方法
US10621725B2 (en) * 2017-04-12 2020-04-14 Here Global B.V. Small object detection from a large image
CN109509172A (zh) * 2018-09-25 2019-03-22 无锡动视宫原科技有限公司 一种基于深度学习的液晶屏瑕疵检测方法及系统
CN109784181B (zh) * 2018-12-14 2024-03-22 平安科技（深圳）有限公司 图片水印识别方法、装置、设备及计算机可读存储介质
CN109859190B (zh) * 2019-01-31 2021-09-17 北京工业大学 一种基于深度学习的目标区域检测方法
CN110378420A (zh) * 2019-07-19 2019-10-25 Oppo广东移动通信有限公司 一种图像检测方法、装置及计算机可读存储介质

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090257350A1 (en) * 2008-04-09 2009-10-15 Embarq Holdings Company, Llc System and method for using network performance information to determine improved measures of path states
CN108846841A (zh) * 2018-07-02 2018-11-20 北京百度网讯科技有限公司 显示屏质量检测方法、装置、电子设备及存储介质
CN109461149A (zh) * 2018-10-31 2019-03-12 泰州市创新电子有限公司 喷漆表面缺陷的智能检测系统及方法
CN109711474A (zh) * 2018-12-24 2019-05-03 中山大学 一种基于深度学习的铝材表面缺陷检测算法
CN109886077A (zh) * 2018-12-28 2019-06-14 北京旷视科技有限公司 图像识别方法、装置、计算机设备和存储介质
CN110110661A (zh) * 2019-05-07 2019-08-09 西南石油大学 一种基于unet分割的岩石图像孔隙类型识别方法
CN110675399A (zh) * 2019-10-28 2020-01-10 上海悦易网络信息技术有限公司 屏幕外观瑕疵检测方法及设备
CN110796647A (zh) * 2019-10-28 2020-02-14 上海悦易网络信息技术有限公司 一种电子设备屏幕区域瑕疵检测方法与设备
CN110796646A (zh) * 2019-10-28 2020-02-14 上海悦易网络信息技术有限公司 一种电子设备屏幕区域瑕疵检测方法与设备
CN110827246A (zh) * 2019-10-28 2020-02-21 上海悦易网络信息技术有限公司 电子设备边框外观瑕疵检测方法及设备
CN110827244A (zh) * 2019-10-28 2020-02-21 上海悦易网络信息技术有限公司 一种用于电子设备外观瑕疵检测的方法与设备
CN110827249A (zh) * 2019-10-28 2020-02-21 上海悦易网络信息技术有限公司 电子设备背板外观瑕疵检测方法及设备

Cited By (7)

* 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
US12033454B2 (en) 2020-08-17 2024-07-09 Ecoatm, Llc Kiosk for evaluating and purchasing used electronic devices
US11836912B2 (en) * 2020-09-22 2023-12-05 Future Dial, Inc. Grading cosmetic appearance of a test object based on multi-region determination of cosmetic defects
US11900581B2 (en) 2020-09-22 2024-02-13 Future Dial, Inc. Cosmetic inspection system

Also Published As

Publication number Publication date
CN110675399A (zh) 2020-01-10

Similar Documents

Publication Publication Date Title
WO2021082918A1 (zh) 屏幕外观瑕疵检测方法及设备
WO2021082923A1 (zh) 一种电子设备屏幕区域瑕疵检测方法与设备
WO2021082919A1 (zh) 一种电子设备屏幕区域瑕疵检测方法与设备
WO2021082921A1 (zh) 电子设备背板外观瑕疵检测方法及设备
WO2021082920A1 (zh) 电子设备边框外观瑕疵检测方法及设备
US11941721B2 (en) Using watermark information and weight information to train an embedded neural network model
US10078502B2 (en) Verification of a model of a GUI-based application
WO2017096946A1 (zh) 图像高频信息的定位方法和装置
TWI750651B (zh) 基於對抗樣本的隱私資訊保護方法、裝置及電子設備
US20220189008A1 (en) Method for detecting data defects and computing device utilizing method
WO2021082922A1 (zh) 一种检测屏幕显示断线的方法及设备
CN111968625A (zh) 融合文本信息的敏感音频识别模型训练方法及识别方法
TWI803243B (zh) 圖像擴增方法、電腦設備及儲存介質
US9208404B2 (en) Object detection with boosted exemplars
US9684747B2 (en) Parameter modeling for semiconductor arrangements
US9978392B2 (en) Noisy signal identification from non-stationary audio signals
US10631050B2 (en) Determining and correlating visual context on a user device with user behavior using digital content on the user device
AU2021251463B2 (en) Generating performance predictions with uncertainty intervals
WO2021083110A1 (zh) 载体对象处理和水印嵌入方法、装置及电子设备
WO2023236044A1 (zh) 对象检测模型训练方法、装置、计算机设备和存储介质
CN114238968A (zh) 应用程序检测方法及装置、存储介质及电子设备
US20240362757A1 (en) Mask-robust image inpainting utilizing machine-learning models
CN115205555B (zh) 确定相似图像的方法、训练方法、信息确定方法及设备
JP7266075B2 (ja) データ選別支援装置、データ選別支援方法及びデータ選別支援プログラム
CN117274863A (zh) 图像绘制质量检测方法、装置、计算机设备、介质和产品

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: 20880935

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: 20880935

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20880935

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: 20880935

Country of ref document: EP

Kind code of ref document: A1