WO2017096946A1 - Procédé et dispositif permettant de localiser des informations haute fréquence d'une image - Google Patents

Procédé et dispositif permettant de localiser des informations haute fréquence d'une image Download PDF

Info

Publication number
WO2017096946A1
WO2017096946A1 PCT/CN2016/095998 CN2016095998W WO2017096946A1 WO 2017096946 A1 WO2017096946 A1 WO 2017096946A1 CN 2016095998 W CN2016095998 W CN 2016095998W WO 2017096946 A1 WO2017096946 A1 WO 2017096946A1
Authority
WO
WIPO (PCT)
Prior art keywords
sub
block
threshold
image
dark
Prior art date
Application number
PCT/CN2016/095998
Other languages
English (en)
Chinese (zh)
Inventor
杨帆
刘阳
蔡砚刚
白茂生
魏伟
Original Assignee
乐视控股（北京）有限公司
乐视云计算有限公司
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 乐视控股（北京）有限公司, 乐视云计算有限公司 filed Critical 乐视控股（北京）有限公司
Publication of WO2017096946A1 publication Critical patent/WO2017096946A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • 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
    • 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
    • G06T2207/30168—Image quality inspection

Definitions

  • the present application belongs to the field of Internet video technologies, and in particular, to a method and an apparatus for positioning image high frequency information.
  • the human eye is more sensitive to low frequency information, in the case where the image quality is relatively high and stable, the high frequency information further determines the quality of the image. Especially in places where high-frequency information is dense, such as people's hair, beards, and clothes with dense patterns, etc., in these places to enhance the clarity, the human eye will feel the image quality has been significantly improved.
  • the present application provides a method and apparatus for positioning image high-frequency information, which can quickly locate a high-frequency information area in an image, so as to perform targeted image processing on the high-frequency information area and improve image quality.
  • the present application also provides a positioning electronic device for image high frequency information, a non-transitory computer storage medium, and a computer program product.
  • An embodiment of the present application provides a method for locating high frequency information of an image, including:
  • Whether the sub-block belongs to the image high-frequency information area is determined according to the number of bright pixel points or the number of dark pixel points in the sub-block.
  • the method before determining whether the dark area in each sub-block is more than the bright area, the method includes:
  • a grayscale threshold for each sub-block is preset, the grayscale threshold being a threshold for distinguishing the grayscale of the image of the sub-block.
  • the gray threshold of each sub-block is preset, including:
  • the average gray value is calculated as the grayscale threshold of the sub-block based on the gray value of each pixel in each sub-block.
  • determining whether the dark area in each sub-block is more than a bright area includes:
  • Determining if it is determined that the number of pixels in the sub-block whose gray value is greater than the gray threshold exceeds the number of pixels whose gray value is less than the gray threshold reaches a predetermined first number threshold, determining the sub-block There are more bright areas in the block than dark areas.
  • the determining whether the sub-block belongs to the image high-frequency information area according to the number of bright pixel points or the number of dark pixel points in the sub-block includes:
  • the sub-block is determined to be an image high-frequency information area.
  • the application also provides a positioning device for image high frequency information, comprising:
  • a segmentation module configured to divide the image to be processed into a plurality of N*N sub-blocks
  • a judging module configured to determine whether a dark area in each sub-block is more than a bright area
  • Obtaining a module if yes, using a hat algorithm to obtain a bright pixel in the sub-block; otherwise, using a black hat algorithm to obtain a dark pixel in the sub-block;
  • a determining module configured to determine, according to the number of bright pixel points or the number of dark pixel points in the sub-block, whether the sub-block belongs to an image high-frequency information area.
  • the device described therein further includes:
  • a setting module configured to preset a grayscale threshold of each sub-block, wherein the grayscale threshold is a threshold for distinguishing image grayscale of the sub-block.
  • the setting module is specifically configured to:
  • the average gray value is calculated as the grayscale threshold of the sub-block based on the gray value of each pixel in each sub-block.
  • the determining module is specifically configured to:
  • Determining if it is determined that the number of pixels in the sub-block whose gray value is greater than the gray threshold exceeds the number of pixels whose gray value is less than the gray threshold reaches a predetermined first number threshold, determining the sub-block There are more bright areas in the block than dark areas.
  • the determining module is specifically configured to:
  • the sub-block is determined to be an image high-frequency information area.
  • the present application also provides a non-transitory computer storage medium storing computer executable instructions for performing a method for locating high frequency information of any of the above images of the present application.
  • the application also provides a positioning electronic device for image high frequency information, comprising: at least one processor;
  • the memory stores instructions executable by the one processor, the instructions being executed by the at least one processor to enable the at least one processor to:
  • Whether the sub-block belongs to the image high-frequency information area is determined according to the number of bright pixel points or the number of dark pixel points in the sub-block.
  • the embodiment of the present application further provides a computer program product, the computer program product comprising a computing program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer
  • the computer is caused to perform the method of locating the high frequency information of any of the above images of the present application.
  • the embodiment of the present application divides a to-be-processed image into a plurality of N*N sub-blocks; determines whether a dark area in each sub-block is more than a bright area; if yes, uses a hat-hat algorithm to obtain a bright pixel in the sub-block, otherwise The dark pixel points in the sub-block are obtained using a black hat algorithm.
  • the high-frequency information area in one image can be quickly located, so that the image processing of the high-frequency information area can be performed in a targeted manner to improve the image quality.
  • FIG. 1 is a schematic flowchart diagram of a method for positioning image high frequency information according to an embodiment of the present application
  • 3 is a brightness histogram of an embodiment of the present application.
  • Figure 4 is an original data of an image
  • FIG. 6 is data after gradation expansion based on the gradation corrosion data shown in FIG. 5;
  • Figure 7 is a bright pixel obtained by the hat hat algorithm
  • Figure 8 is an original data of an image
  • FIG. 10 is data after gradation corrosion based on the data after the gray scale expansion shown in FIG. 9;
  • Figure 11 is a dark pixel obtained by the black hat algorithm
  • Figure 12 is an image to be processed adopted in the embodiment of the present application.
  • FIG. 13 is a high frequency information area obtained by the image high frequency information positioning method according to the embodiment of the present application.
  • FIG. 14 is a structural diagram of a positioning apparatus for image high-frequency information according to an embodiment of the present application.
  • FIG. 15 is a structural diagram of a positioning electronic device for image high frequency information according to an embodiment of the present application.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, 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, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device.
  • computer readable media does not include non-transitory computer readable media, such as modulated data signals and carrier waves.
  • first device if a first device is coupled to a second device, the first device can be directly electrically coupled to the second device, or electrically coupled indirectly through other devices or coupling means. Connected to the second device.
  • the description of the specification is intended to be illustrative of the preferred embodiments of the invention. The scope of protection of the application is subject to the definition of the appended claims.
  • the present application first determines whether the dark area in each sub-block is more than a bright area, and according to different judgment results, one of the hat hat algorithm or the black hat algorithm may be used for each sub-block.
  • FIG. 1 is a schematic flowchart of a method for positioning image high-frequency information according to an embodiment of the present application. As shown in FIG. 1 , the method includes:
  • an image is usually divided into several sub-blocks, one sub-block consisting of one luma pixel block and two additional chroma pixel blocks.
  • the luma block is a 16x16 pixel block
  • the size of the two chroma image block is determined according to the sampling format of the image. For example, for the YUV420 sampled image, the chroma block is an 8x8 pixel block.
  • Each image processing algorithm is processed in sub-blocks, sub-blocks.
  • the image is divided into a plurality of N*N sub-blocks.
  • N can be taken as 16.
  • step 102 determining whether the dark area in each sub-block is more than a bright area; if yes, executing step 103, otherwise performing step 104;
  • the method before determining whether the dark area in each sub-block is more than the bright area, the method includes:
  • a grayscale threshold for each sub-block is preset, the grayscale threshold being a threshold for distinguishing the grayscale of the image of the sub-block.
  • the gray threshold of each sub-block is preset in the embodiment of the present application, including but not limited to the following methods:
  • the average gray value is calculated as the grayscale threshold of the sub-block based on the gray value of each pixel in each sub-block.
  • determining whether the dark area in each sub-block is more than a bright area includes:
  • Determining if it is determined that the number of pixels in the sub-block whose gray value is greater than the gray threshold exceeds the number of pixels whose gray value is less than the gray threshold reaches a predetermined first number threshold, determining the sub-block There are more bright areas in the block than dark areas.
  • Both the top hat algorithm and the black hat algorithm are based on an image grayscale algorithm - grayscale erosion and grayscale expansion.
  • the hat algorithm first performs grayscale erosion on the image, then performs grayscale expansion, and finally subtracts the expanded value from the original data.
  • the black hat algorithm first performs grayscale expansion on the image, performs grayscale erosion, and finally subtracts the original data. This application does not limit this.
  • the method further includes:
  • the sub-block is determined to be an image high-frequency information area if the number of bright pixel points in the sub-block is greater than a preset second threshold, determining that the sub-block is an image high-frequency information area; if the sub-block is dark pixels If the number of points is greater than the preset second threshold number, the sub-block is determined to be an image high-frequency information area.
  • the embodiment of the present application divides a to-be-processed image into a plurality of N*N sub-blocks; determines whether a dark area in each sub-block is more than a bright area; if yes, uses a hat-hat algorithm to obtain a bright pixel in the sub-block, otherwise The dark pixel points in the sub-block are obtained using a black hat algorithm.
  • the high-frequency information area in one image can be quickly located, so that the image processing of the high-frequency information area can be performed in a targeted manner to improve the image quality.
  • a luminance histogram of the grayscale image can be obtained by using a Photoshop program, as shown in the luminance histograms shown in FIG. 2 and FIG. 3, for a region where the grayscale changes frequently, the general grayscale A mutation will occur and will soon change back.
  • the maximum inter-class variance method (OTSU) or the mean division method is used to preset the gray threshold corresponding to each sub-block.
  • the OTSU maximum inter-class variance method can select a threshold in the sub-block that best distinguishes the gray level of the image.
  • the specific algorithm is not discussed, the main principle is to choose Taking a pixel to maximize the variance of the left (dark) portion and the right (light) portion, the gray value corresponding to the selected pixel is the gray threshold of the sub-block.
  • the mean division method is relatively simple, and it is only necessary to use the average value of the gradation of each pixel in the sub-block as the gradation threshold.
  • the OTSU maximum inter-class variance method is more accurate, and the average segmentation method is faster.
  • the top hat algorithm mainly extracts pixels that are bright in the darker areas. Instead, the black hat algorithm extracts dark pixels in brighter areas. Therefore, in areas where a hat hat algorithm is required, the darker grayscale should occupy the majority, and in the region where the black hat algorithm is required, the bright grayscale should be the majority.
  • the grayscale threshold corresponding to each sub-block is preset, if the number of pixels in the sub-block that is smaller than the gray threshold exceeds the threshold of the gray threshold, the number of pixels reaches a predetermined first threshold. If there are many dark areas, the hat algorithm is used; if the number of pixels in the sub-block larger than the gray threshold exceeds the threshold of the gray threshold, the number of pixels reaches a predetermined first threshold, indicating a bright region. More, use the black hat algorithm.
  • the hat algorithm and the black hat algorithm are combined based on the basic image grayscale algorithm - grayscale erosion and grayscale expansion.
  • the hat algorithm first performs grayscale erosion on the image, then performs grayscale expansion, and finally subtracts the expanded value from the original data.
  • the black hat algorithm first performs grayscale expansion on the image, performs grayscale erosion, and finally subtracts the original data.
  • FIG. 4 is the original data of an image
  • FIG. 5 is the data after the grayscale etching based on the original data shown in FIG. 4, as shown in FIG. 4 and FIG. 5, the example adopts a core with a width of 3, and the core The center is in the middle position.
  • the grayscale expansion is different from the grayscale corrosion in that the maximum value in the kernel is taken.
  • FIG. 6 is the data after the grayscale expansion based on the grayscale corrosion shown in FIG. 5, as shown in FIG.
  • the isolated bright spots have been eliminated.
  • the combination of grayscale erosion and grayscale expansion in these two steps is called grayscale opening operation.
  • the isolated bright spots can be used. Extracted, you can get bright pixels, as shown in Figure 7,
  • Figure 7 is the bright pixel points obtained by the hat algorithm.
  • FIG. 9 is the data after the gray scale expansion based on the original data shown in FIG. 8; based on the data of FIG.
  • the etch operation obtains the data shown in FIG. 10, and FIG. 10 shows the gradation-corroded data based on the gray-scale expanded data shown in FIG. 9; it can be seen that the isolated dark value has been "filled in” and used again.
  • the grayscale etched data shown in Fig. 10 is subtracted from the original data to obtain dark pixel points, as shown in Fig. 11, and Fig. 11 is a dark pixel point obtained by the black hat algorithm.
  • each sub-block can be determined by a preset second number threshold (T).
  • T second number threshold
  • the conditions of the high-frequency information area are satisfied, and subsequent operations such as sharpening, contrast adjustment, and the like can be performed to improve the definition.
  • FIG. 12 is an image to be processed used in the embodiment of the present application
  • FIG. 13 is a high-frequency information region obtained by the image high-frequency information positioning method according to the embodiment of the present application.
  • FIG. 14 is a structural diagram of a device for positioning high-frequency information of an image according to an embodiment of the present invention. As shown in FIG. 14, the method includes:
  • a segmentation module 21 configured to divide the image to be processed into a plurality of N*N sub-blocks
  • the determining module 22 is configured to determine whether the dark area in each sub-block is more than a bright area
  • the determining module 24 is configured to determine, according to the number of bright pixel points or the number of dark pixel points in the sub-block, whether the sub-block belongs to an image high-frequency information area.
  • the device further includes:
  • the setting module 25 is configured to preset a gray threshold of each sub-block, where the gray threshold is a threshold for distinguishing the image gray of the sub-block.
  • the setting module 25 is specifically configured to:
  • the determining module 22 is specifically configured to:
  • Determining if it is determined that the number of pixels in the sub-block whose gray value is greater than the gray threshold exceeds the number of pixels whose gray value is less than the gray threshold reaches a predetermined first number threshold, determining the sub-block There are more bright areas in the block than dark areas.
  • the determining module 24 is specifically configured to:
  • the sub-block is determined to be an image high-frequency information area.
  • the apparatus shown in FIG. 14 can perform the method shown in FIG. 1, and its implementation principle and technical effects will not be described again.
  • the embodiment of the present application provides a non-transitory computer storage medium, where the computer storage medium stores computer executable instructions, and the computer executable instructions can perform the method for locating high frequency information of the image in any of the foregoing method embodiments.
  • FIG. 15 is a structural diagram of a positioning electronic device for image high frequency information according to an embodiment of the present application, including:
  • processors 31 and memory 32 one processor 31 is exemplified in FIG.
  • the apparatus for locating the image high frequency information may further include: an input device 33 and an output device 34.
  • the processor 31, the memory 32, the input device 33, and the output device 34 may be connected by a bus or other means, as exemplified by a bus connection in FIG.
  • the memory 32 is used as a non-transitory computer readable storage medium, and can be used for storing a non-transitory software program, a non-transitory computer executable program, and a module, such as a program corresponding to the method for locating image high frequency information in the embodiment of the present application. Instruction/module.
  • the processor 31 executes various functional applications and data processing of the server by running non-transitory software programs, instructions and modules stored in the memory 32, that is, a method for positioning image high-frequency information in the above method embodiment.
  • the memory 32 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function; and the storage data area may store data created by use of the positioning device according to the image high frequency information. Wait.
  • memory 32 can include high speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device.
  • memory 32 may optionally include memory remotely located relative to processor 31, which may be coupled to the positioning device of the image high frequency information over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the input device 33 can receive input digital or character information, and generate key signal inputs related to user settings and function control of the positioning device of the image high frequency information.
  • Output device 34 can include a display device such as a display screen.
  • the one or more modules are stored in the memory 32, and when executed by the one or more processors 31, perform a method of locating image high frequency information in any of the above method embodiments.
  • the electronic device of the embodiment of the present application exists in various forms, including but not limited to:
  • Mobile communication devices These devices are characterized by mobile communication functions and are mainly aimed at providing voice and data communication.
  • Such terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.
  • Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has mobile Internet access. Such terminals include: PDA, MID and UMPC Wait, such as the iPad.
  • Portable entertainment devices These devices can display and play multimedia content. Such devices include: audio, video players (such as iPod), handheld game consoles, e-books, and smart toys and portable car navigation devices.
  • the server consists of a processor, a hard disk, a memory, a system bus, etc.
  • the server is similar to a general-purpose computer architecture, but because of the need to provide highly reliable services, processing power and stability High reliability in terms of reliability, security, scalability, and manageability.
  • the storage medium may be a magnetic disk, an optical disk, a read only memory (ROM), or a random access memory (RAM).

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

La présente invention concerne un procédé et un dispositif permettant de localiser des informations haute fréquence d'une image. Le procédé consiste : à diviser une image à traiter en une pluralité de N*N sous-blocs ; à déterminer si le nombre de régions sombres est supérieur au nombre de régions lumineuses dans chaque sous-bloc ; si c'est le cas, à acquérir des pixels lumineux dans le sous-bloc au moyen d'un algorithme top hat ; sinon, à acquérir des pixels sombres dans le sous-bloc au moyen d'un algorithme black hat. Une région d'informations haute fréquence dans une image peut être localisée rapidement, ce qui aide à effectuer un traitement d'image spécifique ultérieur sur la région d'informations haute fréquence, et la qualité de l'image en est améliorée.
PCT/CN2016/095998 2015-12-07 2016-08-19 Procédé et dispositif permettant de localiser des informations haute fréquence d'une image WO2017096946A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510890417.4 2015-12-07
CN201510890417.4A CN105894491A (zh) 2015-12-07 2015-12-07 图像高频信息的定位方法和装置

Publications (1)

Publication Number Publication Date
WO2017096946A1 true WO2017096946A1 (fr) 2017-06-15

Family

ID=57002595

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/095998 WO2017096946A1 (fr) 2015-12-07 2016-08-19 Procédé et dispositif permettant de localiser des informations haute fréquence d'une image

Country Status (2)

Country Link
CN (1) CN105894491A (fr)
WO (1) WO2017096946A1 (fr)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109993691A (zh) * 2019-04-02 2019-07-09 济南大学 基于分段式线性转换的非均匀图像转换方法及系统
CN110738603A (zh) * 2018-07-18 2020-01-31 中国商用飞机有限责任公司 一种图像灰度处理方法、装置、计算机设备及存储介质
CN110782454A (zh) * 2019-11-12 2020-02-11 上海电气集团股份有限公司 一种发电机定子铁心叠片的识别方法以及识别装置
CN111462157A (zh) * 2020-03-31 2020-07-28 西安工程大学 一种基于遗传优化阈值法的红外图像分割方法
CN111489395A (zh) * 2020-04-13 2020-08-04 展讯通信（上海）有限公司 图像信号的方向判断方法及相关设备
CN111598909A (zh) * 2020-05-08 2020-08-28 展讯通信（上海）有限公司 图像信号的频域特征判断方法及相关设备
CN111787310A (zh) * 2020-07-14 2020-10-16 南昌欧菲晶润科技有限公司 防抖性能测试方法、装置、计算机设备及存储介质
CN111951214A (zh) * 2020-06-24 2020-11-17 北京百度网讯科技有限公司 图像中可读区域的分割方法、装置、电子设备及存储介质
CN113570507A (zh) * 2020-04-29 2021-10-29 浙江宇视科技有限公司 一种图像降噪方法、装置、设备及存储介质
CN113763397A (zh) * 2021-09-03 2021-12-07 国网山东省电力公司电力科学研究院 复合绝缘子故障检测方法及系统

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108053371B (zh) * 2017-11-30 2022-04-19 努比亚技术有限公司 一种图像处理方法、终端及计算机可读存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100040263A1 (en) * 2008-08-15 2010-02-18 Sti Medical Systems Llc Methods for enhancing vascular patterns in cervical imagery
CN101789080A (zh) * 2010-01-21 2010-07-28 上海交通大学 车辆车牌实时定位字符分割的检测方法
CN101989351A (zh) * 2010-11-16 2011-03-23 西安理工大学 一种肺部疑似结节图像增强方向尺度滤波方法
CN104602096A (zh) * 2014-12-26 2015-05-06 北京奇艺世纪科技有限公司 一种视频字幕区的检测方法和装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102378037A (zh) * 2010-08-04 2012-03-14 致伸科技股份有限公司 影像采集装置的影像测试方法与应用该方法的影像测试装置
CN103824257A (zh) * 2012-11-16 2014-05-28 无锡汉兴电子有限公司 一种二维码图像预处理方法
CN103247049A (zh) * 2013-05-15 2013-08-14 桂林电子科技大学 一种smt焊点图像分割方法
CN104346806A (zh) * 2013-08-09 2015-02-11 联想(北京)有限公司 一种图像处理方法及装置
US20150347862A1 (en) * 2014-05-30 2015-12-03 Fuji Xerox Co., Ltd. Image processing apparatus, image processing method, image processing system, and non-transitory computer readable medium storing program

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100040263A1 (en) * 2008-08-15 2010-02-18 Sti Medical Systems Llc Methods for enhancing vascular patterns in cervical imagery
CN101789080A (zh) * 2010-01-21 2010-07-28 上海交通大学 车辆车牌实时定位字符分割的检测方法
CN101989351A (zh) * 2010-11-16 2011-03-23 西安理工大学 一种肺部疑似结节图像增强方向尺度滤波方法
CN104602096A (zh) * 2014-12-26 2015-05-06 北京奇艺世纪科技有限公司 一种视频字幕区的检测方法和装置

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110738603A (zh) * 2018-07-18 2020-01-31 中国商用飞机有限责任公司 一种图像灰度处理方法、装置、计算机设备及存储介质
CN109993691B (zh) * 2019-04-02 2022-11-11 济南大学 基于分段式线性转换的非均匀图像转换方法及系统
CN109993691A (zh) * 2019-04-02 2019-07-09 济南大学 基于分段式线性转换的非均匀图像转换方法及系统
CN110782454B (zh) * 2019-11-12 2022-04-26 上海电气集团股份有限公司 一种发电机定子铁心叠片的识别方法以及识别装置
CN110782454A (zh) * 2019-11-12 2020-02-11 上海电气集团股份有限公司 一种发电机定子铁心叠片的识别方法以及识别装置
CN111462157A (zh) * 2020-03-31 2020-07-28 西安工程大学 一种基于遗传优化阈值法的红外图像分割方法
CN111462157B (zh) * 2020-03-31 2023-04-07 西安工程大学 一种基于遗传优化阈值法的红外图像分割方法
CN111489395A (zh) * 2020-04-13 2020-08-04 展讯通信（上海）有限公司 图像信号的方向判断方法及相关设备
CN111489395B (zh) * 2020-04-13 2023-03-14 展讯通信（上海）有限公司 图像信号的方向判断方法及相关设备
CN113570507A (zh) * 2020-04-29 2021-10-29 浙江宇视科技有限公司 一种图像降噪方法、装置、设备及存储介质
CN113570507B (zh) * 2020-04-29 2024-03-26 浙江宇视科技有限公司 一种图像降噪方法、装置、设备及存储介质
CN111598909B (zh) * 2020-05-08 2023-03-14 展讯通信（上海）有限公司 图像信号的频域特征判断方法及相关设备
CN111598909A (zh) * 2020-05-08 2020-08-28 展讯通信（上海）有限公司 图像信号的频域特征判断方法及相关设备
CN111951214A (zh) * 2020-06-24 2020-11-17 北京百度网讯科技有限公司 图像中可读区域的分割方法、装置、电子设备及存储介质
CN111951214B (zh) * 2020-06-24 2023-07-28 北京百度网讯科技有限公司 图像中可读区域的分割方法、装置、电子设备及存储介质
CN111787310A (zh) * 2020-07-14 2020-10-16 南昌欧菲晶润科技有限公司 防抖性能测试方法、装置、计算机设备及存储介质
CN113763397A (zh) * 2021-09-03 2021-12-07 国网山东省电力公司电力科学研究院 复合绝缘子故障检测方法及系统
CN113763397B (zh) * 2021-09-03 2024-03-29 国网山东省电力公司电力科学研究院 复合绝缘子故障检测方法及系统

Also Published As

Publication number Publication date
CN105894491A (zh) 2016-08-24

Similar Documents

Publication Publication Date Title
WO2017096946A1 (fr) Procédé et dispositif permettant de localiser des informations haute fréquence d'une image
US11151712B2 (en) Method and apparatus for detecting image defects, computing device, and computer readable storage medium
US10803554B2 (en) Image processing method and device
EP3614334B1 (fr) Procédé de traitement d'images et dispositif électronique
US10896349B2 (en) Text detection method and apparatus, and storage medium
CN109272459B (zh) 图像处理方法、装置、存储介质及电子设备
US9483835B2 (en) Depth value restoration method and system
WO2018028306A1 (fr) Procédé et dispositif de reconnaissance d'un numéro de plaque d'immatriculation
US9262690B2 (en) Method and device for detecting glare pixels of image
WO2021082921A1 (fr) Procédé de détection de défaut d'aspect de couvercle arrière pour appareil électronique, et appareil
US20200066024A1 (en) Scene-based foveated rendering of graphics content
WO2015085790A1 (fr) Procédé et appareil de traitement d'image
CN111192190B (zh) 消除图像水印的方法、装置及电子设备
WO2014074959A1 (fr) Détection faciale en temps réel à l'aide de paires de pixels
WO2019000793A1 (fr) Procédé et dispositif de pixélisation pour diffusion en direct, dispositif électronique et support de stockage
KR20130115341A (ko) 제스쳐 인식 메커니즘을 제공하는 방법 및 장치
WO2018045789A1 (fr) Procédé et dispositif de réglage de valeurs d'échelle de gris d'une image
WO2020108010A1 (fr) Procédé et appareil de traitement vidéo, dispositif électronique et support d'enregistrement
JP2021119457A (ja) 背景なし画像の生成方法及び装置、電子機器、記憶媒体並びにコンピュータプログラム
JP2014535101A (ja) 画像中のテキストの検出を容易にする方法及び装置
US8824778B2 (en) Systems and methods for depth map generation
CN110689014B (zh) 感兴趣区域的检测方法、装置、电子设备及可读存储介质
US9836823B2 (en) Method and device for enhancing edge of image and digital camera
US9678991B2 (en) Apparatus and method for processing image
KR101853211B1 (ko) 모바일 gpu 환경에서 차영상 정보를 이용한 sift 알고리즘의 복잡도 감소 기법

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: 16872142

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: 16872142

Country of ref document: EP

Kind code of ref document: A1