WO2020052083A1 - 侵权图片的识别方法、装置和计算机可读存储介质 - Google Patents

侵权图片的识别方法、装置和计算机可读存储介质 Download PDF

Info

Publication number
WO2020052083A1
WO2020052083A1 PCT/CN2018/117712 CN2018117712W WO2020052083A1 WO 2020052083 A1 WO2020052083 A1 WO 2020052083A1 CN 2018117712 W CN2018117712 W CN 2018117712W WO 2020052083 A1 WO2020052083 A1 WO 2020052083A1
Authority
WO
WIPO (PCT)
Prior art keywords
picture
infringing
image block
copyright information
identified
Prior art date
Application number
PCT/CN2018/117712
Other languages
English (en)
French (fr)
Inventor
周多友
王长虎
Original Assignee
北京字节跳动网络技术有限公司
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 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Publication of WO2020052083A1 publication Critical patent/WO2020052083A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/22Matching criteria, e.g. proximity measures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques

Definitions

  • the present disclosure relates to the technical field of image recognition, and in particular, to a method, a device, and a computer-readable storage medium for identifying an infringing picture.
  • OCR optical character recognition
  • OCR is used to identify the entire picture. On the one hand, it requires more computing resources and low recognition efficiency. On the other hand, OCR can only perform text recognition. It cannot recognize non-text copyright information, and judges by text It may not be an infringing picture, for example, if the picture contains a banner with a company logo, it will also be recognized as an infringing picture, and the recognition accuracy is low.
  • the technical problem solved by the present disclosure is to provide a method for identifying infringing pictures, to at least partially solve the technical problems of low identification efficiency and low accuracy of infringing pictures.
  • an infringing picture identification device, an infringing picture identification hardware device, a computer-readable storage medium, and an infringing picture identification terminal are also provided.
  • a method for identifying infringing pictures including:
  • the step of determining whether the picture to be identified is an infringing picture according to the infringement recognition result of the image block includes:
  • the method further includes:
  • the step of identifying infringement on each image block includes:
  • the method further includes:
  • the step of identifying infringement on each image block includes:
  • the step of determining whether the picture to be identified is an infringing picture according to the image block containing the copyright information includes:
  • the copyright position information is at least one of four corners of the picture to be identified.
  • the copyright information is formed by combining at least one of text, graphics, letters, numbers, three-dimensional signs, and colors.
  • a device for identifying infringing pictures includes:
  • a picture block module which is used to block the identified pictures according to preset copyright position information to obtain image blocks that may contain copyright information
  • the infringing picture determination module is configured to determine whether the picture to be identified is an infringing picture according to an infringing recognition result on the image block.
  • the infringing picture determination module includes:
  • An image block identification unit configured to identify infringement on each image block
  • the infringing picture determination unit is configured to determine whether the image to be identified is an infringing picture according to the image block containing the copyright information if it is identified that any image block contains the copyright information.
  • the device further includes:
  • a classifier training module configured to train an image classifier according to at least one original picture containing preset copyright information
  • the image block identification unit is specifically configured to: input the image block to the image classifier, and determine whether the image block contains copyright information according to a classification result of the image classifier.
  • the device further includes:
  • a logo icon acquisition module configured to acquire at least one logo icon associated with the preset copyright information from a pre-established database for storing logo icons
  • the image block identification unit is specifically configured to match the logo icon with a logo icon included in each image block; and determine whether the image block contains copyright information according to a matching result.
  • the infringing picture determination unit is specifically configured to: if it is identified that any image block contains copyright information, determine that the picture to be identified is an infringing picture.
  • the copyright position information is at least one of four corners of the picture to be identified.
  • the copyright information is formed by combining at least one of text, graphics, letters, numbers, three-dimensional signs, and colors.
  • a hardware device for identifying infringing pictures including:
  • Memory for storing non-transitory computer-readable instructions
  • a processor configured to run the computer-readable instructions, so that the processor, when executed, implements the steps described in any one of the technical solutions of the method for identifying infringing pictures.
  • a computer-readable storage medium is configured to store non-transitory computer-readable instructions, and when the non-transitory computer-readable instructions are executed by a computer, cause the computer to execute any one of the methods for identifying infringing pictures described above. Described steps.
  • An infringing picture identification terminal includes any of the foregoing infringing picture identification devices.
  • Embodiments of the present disclosure provide a method for identifying an infringing picture, an infringing picture identifying device, an infringing picture identifying hardware device, a computer-readable storage medium, and an infringing picture identifying terminal.
  • the method for identifying infringing pictures includes segmenting the pictures to be identified according to preset copyright location information to obtain image blocks that may contain copyright information; and determining whether the pictures to be identified are based on the infringement recognition results of the image blocks. Is an infringing picture.
  • the embodiment of the present disclosure first divides an identified picture into blocks according to preset copyright location information, and obtains an image block that may contain copyright information; determines whether the to-be-recognized picture is an infringing picture according to an infringement recognition result of the image block, Not only can reduce the amount of calculation and improve the recognition efficiency, but also can carry out targeted recognition of image block infringement and improve the recognition accuracy.
  • FIG. 1a is a schematic flowchart of a method for identifying an infringing picture according to an embodiment of the present disclosure
  • FIG. 1b is a schematic flowchart of a method for identifying an infringing picture according to another embodiment of the present disclosure
  • 1c is a schematic flowchart of a method for identifying an infringing picture according to another embodiment of the present disclosure
  • 1d is a schematic flowchart of a method for identifying an infringing picture according to another embodiment of the present disclosure
  • FIG. 2a is a schematic structural diagram of a device for identifying infringing pictures according to an embodiment of the present disclosure
  • FIG. 2b is a schematic structural diagram of an infringing picture identification device according to another embodiment of the present disclosure.
  • FIG. 2c is a schematic structural diagram of an infringing picture identification device according to another embodiment of the present disclosure.
  • 2d is a schematic structural diagram of an infringing picture identification device according to another embodiment of the present disclosure.
  • FIG. 3 is a schematic structural diagram of a hardware device for identifying infringing pictures according to an embodiment of the present disclosure
  • FIG. 4 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present disclosure.
  • FIG. 5 is a schematic structural diagram of an infringing picture identification terminal according to an embodiment of the present disclosure.
  • an embodiment of the present disclosure provides a method for identifying infringing pictures.
  • the method for identifying infringing pictures mainly includes the following steps S1 to S2. among them:
  • Step S1 According to the preset copyright position information, the image to be identified is divided into blocks to obtain image blocks that may contain copyright information.
  • the copyright location information is location information where the copyright information is located, including but not limited to at least one of the four corners of the picture, or the center position of the picture, or other set positions.
  • the copyright information is usually set at a fixed position of the picture, for example, any one of the four corners of the picture, so that the copyright position information of the picture to be identified can be counted in advance, and then treated according to the preset copyright position information.
  • the image is identified and divided into blocks, and image blocks that may contain copyright information are obtained.
  • the copyright information is composed of at least one type of information including text, graphics, letters, numbers, three-dimensional signs, and colors, and the form may be a variety of logo patterns.
  • Step S2 Determine whether the picture to be identified is an infringing picture according to the infringing recognition result of the image block.
  • an image block that may contain copyright information is obtained by dividing the to-be-recognized picture according to preset copyright location information; determining whether the to-be-recognized picture is an infringing picture according to the infringement recognition result of the image block can not only reduce the calculation amount , Improve recognition efficiency, can also be targeted for image block infringement recognition, improve recognition accuracy.
  • step S2 includes:
  • the image to be identified is divided into blocks according to preset copyright position information, image blocks that may contain copyright information are obtained, and infringement identification is performed on each image block. If it is identified that any image block contains copyright information, The image block containing the copyright information determines whether the picture to be identified is an infringing picture, which not only reduces the amount of calculation and improves the recognition efficiency, but also can perform intensive recognition of the image block infringement and improve the recognition accuracy rate.
  • the method in this embodiment further includes:
  • S3 training an image classifier based on at least one original picture containing preset copyright information.
  • the copyright information may include multiple styles or multiple logo icons.
  • all styles or logo icons are considered.
  • At least one original picture containing preset copyright information is used as training material, and a machine learning classification algorithm is used to train it to obtain an image classifier.
  • machine learning classification algorithms that can be used include, but are not limited to, any of the following: Naive Bayes algorithm, artificial neural network algorithm, genetic algorithm, K-Nearest Neighbor (KNN) classification algorithm, clustering algorithm, and the like.
  • Step S21 includes:
  • the image block is input to an image classifier, and whether the image block contains copyright information is determined according to the classification result of the image classifier.
  • the classification result of the image classifier may be a score, or a text result may be directly provided. If it is a score, determine whether the image block contains copyright information according to the score. For example, when the score is greater than a preset score, the image block contains copyright information. When the score is less than or equal to the preset score, the character Image blocks do not contain copyright information. If the text result is directly provided, the image classifier directly outputs an image block containing copyright information, or an image block does not contain copyright information.
  • the method in this embodiment further includes:
  • S4 Obtain at least one logo icon associated with the preset copyright information from a pre-established database for storing the logo icon.
  • Step S21 includes:
  • an image feature extraction algorithm may be used to extract the feature points of the obtained logo icon and the feature points of the logo icon included in each image block, and then match the extracted feature points.
  • the obtained logo icon matches a logo icon contained in an image block with a degree greater than a preset degree of matching, it is determined that the image block contains copyright information, otherwise it is determined that the image block does not contain copyright information.
  • step S22 includes:
  • the following is a device embodiment of the present disclosure.
  • the device embodiment of the present disclosure can be used to perform the steps implemented by the method embodiments of the present disclosure.
  • Only parts related to the embodiments of the present disclosure are shown. Specific technical details are not disclosed. Reference is made to the method embodiments of the present disclosure.
  • an embodiment of the present disclosure provides a device for identifying infringing pictures.
  • the device can perform the steps in the embodiment of the method for identifying infringing pictures.
  • the device mainly includes: a picture block module 21 and an infringing picture determination module 22; wherein, the picture block module 21 is configured to divide a picture to be identified according to preset copyright location information, and obtain a picture that may contain The image block of the copyright information; the infringing picture determination module 22 is configured to determine whether the picture to be identified is an infringing picture according to the infringement recognition result of the image block.
  • the copyright location information is location information where the copyright information is located, including but not limited to at least one of the four corners of the picture, or the center position of the picture, or other set positions.
  • the copyright information is usually set at a fixed position of the picture, for example, any one of the four corners of the picture.
  • the copyright position information of the picture to be identified can be counted in advance, and then the picture block module 21 can
  • the determined copyright position information is divided into blocks to be identified, and image blocks that may contain copyright information are obtained.
  • the copyright information is composed of at least one type of information including text, graphics, letters, numbers, three-dimensional signs, and colors, and the form may be a variety of logo patterns.
  • the infringing picture determination module 22 there is no need to identify the pictures to be identified, only the image blocks that may contain copyright information can be identified, which is more targeted and can reduce the amount of calculation. If it is identified that infringing content exists in an image block, it is determined that the picture to be identified is an infringing picture.
  • the picture segmentation module 21 is used to segment the to-be-recognized picture according to the preset copyright location information to obtain an image block that may contain copyright information.
  • the infringing picture determination module 22 determines the to-be-recognized based on the infringement recognition result of the image block. Whether the picture is an infringing picture can not only reduce the amount of calculation and improve the recognition efficiency, but also perform targeted infringement recognition of the image block to improve the recognition accuracy.
  • the infringing picture determining module 22 includes: an image block identifying unit 221 and an infringing picture determining unit 222.
  • the image block identifying unit 221 is configured to perform infringement identification on each image block.
  • the infringing picture determination unit 222 is configured to determine whether any image block contains copyright information, and then determine whether the picture to be identified is an infringing picture according to the image block containing the copyright information.
  • the picture segmentation module 21 divides the pictures to be identified according to preset copyright location information, obtains image blocks that may contain copyright information, and then performs infringement identification on each image block through the image block identification unit 221.
  • the infringing picture determination unit 222 recognizes that any image block contains copyright information, and then determines whether the picture to be identified is an infringing picture according to the image block containing the copyright information, which can not only reduce the calculation amount, improve the recognition efficiency, but also perform targeted image blocks. Identification of infringements to improve identification accuracy.
  • the device further includes: a classifier training module 23; wherein the classifier training module 23 is configured to obtain an image classifier based on at least one original picture containing preset copyright information; and an image block
  • the identifying unit 221 is specifically configured to input an image block into an image classifier, and determine whether the image block contains copyright information according to a classification result of the image classifier.
  • the copyright information may include multiple styles or multiple logo icons.
  • all styles or logo icons are considered.
  • At least one original picture containing preset copyright information is used as training material, and a machine learning classification algorithm is used to train it to obtain an image classifier.
  • machine learning classification algorithms include, but are not limited to, any of the following: Naive Bayes algorithm, artificial neural network algorithm, genetic algorithm, K-Nearest Neighbor (KNN) classification algorithm, clustering algorithm, and the like.
  • the classification result of the image classifier may be a score, or a text result may be directly provided. If it is a score, it is determined whether the image block contains copyright information according to the score. For example, when the score is greater than a preset score, the image block contains copyright information. When the score is less than or equal to the preset score, the characterization Image blocks do not contain copyright information. If the text result is given directly, the image classifier directly outputs an image block that contains copyright information, or an image block that does not contain copyright information.
  • the device further includes: a logo icon acquisition module 24; wherein the logo icon acquisition module 24 is configured to acquire and set copyright information from a database established in advance for storing logo icons Associated at least one logo icon;
  • the image block identification unit 221 is specifically configured to: match the logo icon with the logo icon included in each image block; and determine whether the image block contains copyright information according to the matching result.
  • the image block recognition unit 221 may use an image feature extraction algorithm to extract the feature points of the logo icon and the feature points of the logo icon included in each image block, and then match the extracted feature points. If the matching degree between the logo icon obtained by the image block identification unit 221 and the logo icon contained in an image block is greater than a preset matching degree, it is determined that the image block contains copyright information, otherwise it is determined that the image block does not contain copyright information.
  • the infringing picture determination unit 222 is specifically configured to: if it is identified that any image block contains copyright information, determine that the picture to be identified is an infringing picture.
  • FIG. 3 is a hardware block diagram illustrating a hardware device for identifying infringing pictures according to an embodiment of the present disclosure.
  • a hardware device 30 for identifying infringing pictures according to an embodiment of the present disclosure includes a memory 31 and a processor 32.
  • the memory 31 is configured to store non-transitory computer-readable instructions.
  • the memory 31 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory.
  • the volatile memory may include, for example, a random access memory (RAM) and / or a cache memory.
  • the non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, and the like.
  • the processor 32 may be a central processing unit (CPU) or other form of processing unit having data processing capability and / or instruction execution capability, and may control other components in the identification hardware device 30 of the infringing picture to perform a desired function.
  • the processor 32 is configured to execute the computer-readable instructions stored in the memory 31, so that the hardware device 30 for identifying the infringing picture performs the identification of the infringing picture in the foregoing embodiments of the present disclosure. All or part of the steps of a method.
  • this embodiment may also include well-known structures such as a communication bus and an interface. These well-known structures should also be included in the protection scope of the present disclosure. within.
  • FIG. 4 is a schematic diagram illustrating a computer-readable storage medium according to an embodiment of the present disclosure.
  • a computer-readable storage medium 40 according to an embodiment of the present disclosure stores non-transitory computer-readable instructions 41 thereon.
  • the non-transitory computer-readable instruction 41 is executed by a processor, all or part of the steps of the method for comparing video features of the foregoing embodiments of the present disclosure are performed.
  • the computer-readable storage medium 40 includes, but is not limited to, optical storage media (for example, CD-ROM and DVD), magneto-optical storage media (for example, MO), magnetic storage media (for example, magnetic tape or mobile hard disk), Non-volatile memory rewritable media (for example: memory card) and media with built-in ROM (for example: ROM box).
  • optical storage media for example, CD-ROM and DVD
  • magneto-optical storage media for example, MO
  • magnetic storage media for example, magnetic tape or mobile hard disk
  • Non-volatile memory rewritable media for example: memory card
  • media with built-in ROM for example: ROM box
  • FIG. 5 is a schematic diagram illustrating a hardware structure of a terminal according to an embodiment of the present disclosure.
  • the identification terminal 50 for the infringing picture includes the foregoing embodiment of an apparatus for identifying an infringing picture.
  • the terminal may be implemented in various forms, and the terminal in the present disclosure may include, but is not limited to, such as a mobile phone, a smart phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP ( Portable multimedia players), navigation devices, on-board terminals, on-board display terminals, on-board electronic rear-view mirrors, and other mobile terminals, and fixed terminals such as digital TVs, desktop computers, and the like.
  • a mobile phone such as a mobile phone, a smart phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP ( Portable multimedia players), navigation devices, on-board terminals, on-board display terminals, on-board electronic rear-view mirrors, and other mobile terminals, and fixed terminals such as digital TVs, desktop computers, and the like.
  • PDA personal digital assistant
  • PAD tablet computer
  • PMP Portable multimedia players
  • navigation devices
  • the terminal may further include other components.
  • the infringing picture identification terminal 50 may include a power supply unit 51, a wireless communication unit 52, an A / V (audio / video) input unit 53, a user input unit 54, a sensing unit 55, an interface unit 56, The controller 57, the output unit 58 and the memory 59 and so on.
  • FIG. 5 shows a terminal with various components, but it should be understood that it is not required to implement all the illustrated components, and more or fewer components may be implemented instead.
  • the wireless communication unit 52 allows radio communication between the terminal 50 and a wireless communication system or network.
  • the A / V input unit 53 is used to receive audio or video signals.
  • the user input unit 54 may generate key input data according to a command input by the user to control various operations of the terminal.
  • the sensing unit 55 detects the current state of the terminal 50, the position of the terminal 50, the presence or absence of a user's touch input to the terminal 50, the orientation of the terminal 50, the acceleration or deceleration movement and direction of the terminal 50, and the like, and generates a signal for controlling the terminal 50 commands or signals for operation.
  • the interface unit 56 functions as an interface through which at least one external device can be connected to the terminal 50.
  • the output unit 58 is configured to provide an output signal in a visual, audio, and / or tactile manner.
  • the memory 59 may store software programs and the like for processing and control operations performed by the controller 55, or may temporarily store data that has been output or is to be output.
  • the memory 59 may include at least one type of storage medium.
  • the terminal 50 may cooperate with a network storage device that performs a storage function of the memory 59 through a network connection.
  • the controller 57 generally controls the overall operation of the terminal.
  • the controller 57 may include a multimedia module for reproducing or playing back multimedia data.
  • the controller 57 may perform a pattern recognition process to recognize a handwriting input or a picture drawing input performed on the touch screen as characters or images.
  • the power supply unit 51 receives external power or internal power under the control of the controller 57 and provides appropriate power required to operate each element and component.
  • Various embodiments of the video feature comparison method proposed by the present disclosure may be implemented in a computer-readable medium using, for example, computer software, hardware, or any combination thereof.
  • various embodiments of the video feature comparison method proposed in the present disclosure can be implemented by using an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), and a programmable logic device. (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, electronic unit designed to perform the functions described herein, and in some cases implemented
  • ASIC application-specific integrated circuit
  • DSP digital signal processor
  • DSPD digital signal processing device
  • PLD programmable logic device
  • FPGA field programmable gate array
  • processor controller
  • microcontroller microprocessor
  • electronic unit designed to perform the functions described herein and in some cases implemented
  • Various embodiments of the video feature comparison method proposed in the present disclosure may be implemented in the controller 57.
  • various embodiments of the video feature comparison method proposed by the present disclosure can be implemented with a separate software module that allows at least one function or operation to be performed.
  • the software codes may be implemented by a software application (or program) written in any suitable programming language, and the software codes may be stored in the memory 59 and executed by the controller 57.
  • an "or” used in an enumeration of items beginning with “at least one” indicates a separate enumeration such that, for example, an "at least one of A, B, or C” enumeration means A or B or C, or AB or AC or BC, or ABC (ie A and B and C).
  • the word "exemplary” does not mean that the described example is preferred or better than other examples.
  • each component or each step can be disassembled and / or recombined.

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Image Analysis (AREA)
  • Editing Of Facsimile Originals (AREA)

Abstract

一种侵权图片的识别方法、侵权图片的识别装置、侵权图片的识别硬件装置和计算机可读存储介质。其中,该侵权图片的识别方法包括根据预先设定的版权位置信息对待识别图片进行分块,获取可能包含版权信息的图像块(S1);根据对所述图像块的侵权识别结果确定所述待识别图片是否为侵权图片(S2)。该方法首先根据预先设定的版权位置信息对待识别图片进行分块,获取可能包含版权信息的图像块(S1);根据对所述图像块的侵权识别结果确定所述待识别图片是否为侵权图片(S2),不仅可以减少计算量,提高识别效率,还可以有针对的进行图像块侵权识别,提高识别准确率。

Description

侵权图片的识别方法、装置和计算机可读存储介质
交叉引用
本公开引用于2018年09月13日递交的名称为“侵权图片的识别方法、装置和计算机可读存储介质”的、申请号为201811065343.0的中国专利申请,其通过引用被全部并入本申请。
技术领域
本公开涉及一种图像识别技术领域,特别是涉及一种侵权图片的识别方法、装置和计算机可读存储介质。
背景技术
现阶段,我国对互联网环境下图片权益保护的认识及处置技术的研究还处于初级阶段,网络上的网站及公众号千千万万,大部分都没有版权意识,很多图片都是通过网络下载,例如:最常用的图片会在百度图片搜索,然后简单剪切就放入了自己的内容,但是很多图片都标注了版权信息,如果转载了就是侵权。
基于此类问题,利用技术手段对侵权图片进行识别,及时防止侵权图片进一步传播扩散对版权所有人或企业构成所有权侵犯,图片的保护显得尤为重要。在现有技术中,通常使用光学字符识别(Optical Character Recognition,OCR)技术对侵权图片的文字内容进行识别,根据识别出的文字信息来判断是否包含版权信息,进而判定图片是否为侵权图片。
但是,通过OCR是对整张图片进行识别,一方面需要比较多的计算资源,识别效率低;另一方面,OCR仅能进行文字识别,对于非文字的版权信息识别不出来,并且通过文字判定出来也未必是侵权图片,例如,图片中包含带有公司logo的横幅,这时也会被识别成侵权图片,识别准确率较低。
发明内容
本公开解决的技术问题是提供一种侵权图片的识别方法,以至少部分地解决侵权图片识别效率低和识别准确率低的技术问题。此外,还提供一种侵权图片的识别装置、侵权图片的识别硬件装置、计算机可读存储介质和侵权图片的识别终端。
为了实现上述目的,根据本公开的一个方面,提供以下技术方案:
一种侵权图片的识别方法,包括:
根据预先设定的版权位置信息对待识别图片进行分块,获取可能包含版权信息的图像块;
根据对所述图像块的侵权识别结果确定所述待识别图片是否为侵权图片。
进一步的,所述根据对所述图像块的侵权识别结果确定所述待识别图片是否为侵权图片的步骤,包括:
对各图像块进行侵权识别;
若识别出任一图像块中包含版权信息,则根据所述包含版权信息的图像块确定所述待识别图片是否为侵权图片。
进一步的,所述方法还包括:
根据至少一个包含预先设定的版权信息的原版图片训练得到图像分类器;
所述对各图像块进行侵权识别的步骤,包括:
将所述图像块输入所述图像分类器,根据所述图像分类器的分类结果确定所述图像块是否包含版权信息。
进一步的,所述方法还包括:
从预先建立的用于存储logo图标的数据库中获取与所述预先设定的的版权信息相关联的至少一种logo图标;
所述对各图像块进行侵权识别的步骤,包括:
将所述logo图标与各图像块中包含的logo图标进行匹配;
根据匹配结果确定所述图像块是否包含版权信息。
进一步的,所述若识别出任一图像块中包含版权信息,则根据所述包含版权信息的图像块确定所述待识别图片是否为侵权图片的步骤,包括:
若识别出任一图像块中包含版权信息,则确定所述待识别图片为侵权图片。
进一步的,所述版权位置信息为所述待识别图片的四角中的至少一角。
进一步的,所述版权信息由文字、图形、字母、数字、三维标志和颜色中的至少一种信息组合而成。
为了实现上述目的,根据本公开的又一个方面,还提供以下技术方案:
一种侵权图片的识别装置,包括:
图片分块模块,用于根据预先设定的版权位置信息对待识别图片进行分块,获取可能包含版权信息的图像块;
侵权图片判定模块,用于根据对所述图像块的侵权识别结果确定所述待识别图片是否为侵权图片。
进一步的,所述侵权图片判定模块包括:
图像块识别单元,用于对各图像块进行侵权识别;
侵权图片判定单元,用于若识别出任一图像块中包含版权信息,则根据所述包含版权信息的图像块确定所述待识别图片是否为侵权图片。
进一步的,所述装置还包括:
分类器训练模块,用于根据至少一个包含预先设定的版权信息的原版图片训练得到图像分类器;
所述图像块识别单元具体用于:将所述图像块输入所述图像分类器,根据所述图像分类器的分类结果确定所述图像块是否包含版权信息。
进一步的,所述装置还包括:
logo图标获取模块,用于从预先建立的用于存储logo图标的数据库中获取与所述预先设定的版权信息相关联的至少一种logo图标;
所述图像块识别单元具体用于:将所述logo图标与各图像块中包含的logo图标进行匹配;根据匹配结果确定所述图像块是否包含版权信息。
进一步的,所述侵权图片判定单元具体用于:若识别出任一图像块中包含版权信息,则确定所述待识别图片为侵权图片。
进一步的,所述版权位置信息为所述待识别图片的四角中的至少一角。
进一步的,所述版权信息由文字、图形、字母、数字、三维标志和颜色中的至少一种信息组合而成。
为了实现上述目的,根据本公开的又一个方面,还提供以下技术方案:
一种侵权图片的识别硬件装置,包括:
存储器,用于存储非暂时性计算机可读指令;以及
处理器,用于运行所述计算机可读指令,使得所述处理器执行时实现上述任一侵权图片的识别方法技术方案中所述的步骤。
为了实现上述目的,根据本公开的又一个方面,还提供以下技术方案:
一种计算机可读存储介质,用于存储非暂时性计算机可读指令,当所述非暂时性计算机可读指令由计算机执行时,使得所述计算机执行上述任一侵权图片的识别方法技术方案中所述的步骤。
为了实现上述目的,根据本公开的又一个方面,还提供以下技术方案:
一种侵权图片的识别终端,包括上述任一侵权图片的识别装置。
本公开实施例提供一种侵权图片的识别方法、侵权图片的识别装置、侵权图片的识别硬件装置、计算机可读存储介质和侵权图片的识别终端。其中,该侵权图片的识别方法包括根据预先设定的版权位置信息对待识别图片进行分块,获取可能包含版权信息的图像块;根据对所述图像块的侵权识别结果确定所述待识别图片是否为侵权图片。本公开实施例首先根据预先设定的版权位置信息对待识别图片进行分块,获取可能包含版权信息的图像块;根据对所述图像块的侵权识别结果确定所述待识别图片是否为侵权图片,不仅可以减少计算量,提高识别效率,还可以有针对的进行图像块侵权识别,提高识别准确率。
上述说明仅是本公开技术方案的概述,为了能更清楚了解本公开的技术手段,而可依照说明书的内容予以实施,并且为让本公开的上述和其他目的、特征和优点能够更明显易懂,以下特举较佳实施例,并配合附图,详细说明如下。
附图说明
图1a为根据本公开一个实施例的侵权图片的识别方法的流程示意图;
图1b为根据本公开另一个实施例的侵权图片的识别方法的流程示意图;
图1c为根据本公开另一个实施例的侵权图片的识别方法的流程示意图;
图1d为根据本公开另一个实施例的侵权图片的识别方法的流程示意图;
图2a为根据本公开一个实施例的侵权图片的识别的装置的结构示意图;
图2b为根据本公开另一个实施例的侵权图片的识别装置的结构示意图;
图2c为根据本公开另一个实施例的侵权图片的识别装置的结构示意图;
图2d为根据本公开另一个实施例的侵权图片的识别装置的结构示意图;
图3为根据本公开一个实施例的侵权图片的识别硬件装置的结构示意图;
图4为根据本公开一个实施例的计算机可读存储介质的结构示意图;
图5为根据本公开一个实施例的侵权图片的识别终端的结构示意图。
具体实施方式
以下通过特定的具体实例说明本公开的实施方式,本领域技术人员可由本说明书所揭露的内容轻易地了解本公开的其他优点与功效。显然,所描述的实施例仅仅是本公开一部分实施例,而不是全部的实施例。本公开还可以通过另外不同的具体实施方式加以实施或应用,本说明书中的各项细节也可以基于不同观点与应用,在没有背离本公开的精神下进行各种修饰或改变。需说明的是,在不冲突的情况下,以下实施例及实施例中的特征可以相互组合。基于本公开中的实施例,本领域普通技术人员在没有做出创造性 劳动前提下所获得的所有其他实施例,都属于本公开保护的范围。
需要说明的是,下文描述在所附权利要求书的范围内的实施例的各种方面。应显而易见,本文中所描述的方面可体现于广泛多种形式中,且本文中所描述的任何特定结构及/或功能仅为说明性的。基于本公开,所属领域的技术人员应了解,本文中所描述的一个方面可与任何其它方面独立地实施,且可以各种方式组合这些方面中的两者或两者以上。举例来说,可使用本文中所阐述的任何数目个方面来实施设备及/或实践方法。另外,可使用除了本文中所阐述的方面中的一或多者之外的其它结构及/或功能性实施此设备及/或实践此方法。
还需要说明的是,以下实施例中所提供的图示仅以示意方式说明本公开的基本构想,图式中仅显示与本公开中有关的组件而非按照实际实施时的组件数目、形状及尺寸绘制,其实际实施时各组件的型态、数量及比例可为一种随意的改变,且其组件布局型态也可能更为复杂。
另外,在以下描述中,提供具体细节是为了便于透彻理解实例。然而,所属领域的技术人员将理解,可在没有这些特定细节的情况下实践所述方面。
为了解决如何提高用户体验效果的技术问题,本公开实施例提供一种侵权图片的识别方法。如图1a所示,该侵权图片的识别方法主要包括如下步骤S1至步骤S2。其中:
步骤S1:根据预先设定的版权位置信息对待识别图片进行分块,获取可能包含版权信息的图像块。
其中,版权位置信息为版权信息所在的位置信息,包括但不限于图片的四角中的至少一角,或者图片的中心位置,或者其他设定的位置。
一般来说,版权信息通常设定在图片的某一固定位置,例如,图片的四角中的任意一角,这样就可以预先统计待识别图片的版权位置信息,然后根据预先设定的版权位置信息对待识别图片进行分块,获取到可能包含版权信息的图像块。
其中,图像块可能为一个或多个,这根据预先设定的版权位置信息中包含的位置个数来确定。如果预先设定的版权位置信息为图片的四角,则需要分割出待识别图片的四个角对应的图像块。具体图像块的大小可根据版权 信息占用面积的大小来确定。
其中,版权信息由文字、图形、字母、数字、三维标志和颜色中的至少一种信息组合而成,其形式可以为多种logo图案。
步骤S2:根据对图像块的侵权识别结果确定待识别图片是否为侵权图片。
在本步骤,无需对待识别图片进行识别,只需要对可能包含版权信息的图像块进行识别即可,这样比较有针对性,而且可以降低计算量。如果识别出某一个图像块存在侵权内容,则确定待识别图片即为侵权图片。
本实施例通过根据预先设定的版权位置信息对待识别图片进行分块,获取可能包含版权信息的图像块;根据对图像块的侵权识别结果确定待识别图片是否为侵权图片,不仅可以减少计算量,提高识别效率,还可以有针对的进行图像块侵权识别,提高识别准确率。
在一个可选的实施例中,如图1b所示,步骤S2包括:
S21:对各图像块进行侵权识别。
S22:若识别出任一图像块中包含版权信息,则根据包含版权信息的图像块确定述待识别图片是否为侵权图片。
本实施例通过根据预先设定的版权位置信息对待识别图片进行分块,获取可能包含版权信息的图像块,然后对各图像块进行侵权识别,若识别出任一图像块中包含版权信息,则根据包含版权信息的图像块确定述待识别图片是否为侵权图片,不仅可以减少计算量,提高识别效率,还可以有针对的进行图像块侵权识别,提高识别准确率。
进一步的,如图1c所示,本实施例的方法还包括:
S3:根据至少一个包含预先设定的版权信息的原版图片训练得到图像分类器。
其中,版权信息可能包含多种样式或多种logo图标,在训练图像分类器时为了提高对侵权图片的识别准确率,将所有样式或logo图标均考虑在内。
具体的,将至少一个包含预先设定的版权信息的原版图片作为训练材料,采用机器学习分类算法对其进行训练得到图像分类器。具体可采用的机 器学习分类算法包括但不限于以下任意一种:朴素贝叶斯算法、人工神经网络算法、遗传算法、K最近邻(K-NearestNeighbor,KNN)分类算法、聚类算法等。
步骤S21包括:
将图像块输入图像分类器,根据图像分类器的分类结果确定图像块是否包含版权信息。
具体的,图像分类器的分类结果可以为一个分值,或者是直接给出文字结果。如果是分值,则根据分值确定图像块是否包含版权信息,例如当分值大于预设分值时,则表征图像块包含版权信息,当分值小于或等于预设分值时,则表征图像块不包含版权信息。如果是直接给出文字结果,则图像分类器的直接输出某个图像块包含版权信息,或某个图像块不包含版权信息。
进一步的,如图1d所示,本实施例的方法还包括:
S4:从预先建立的用于存储logo图标的数据库中获取与预先设定的版权信息相关联的至少一种logo图标。
步骤S21包括:
S211:将logo图标与各图像块中包含的logo图标进行匹配。
具体的,可采用图像特征提取算法,分别提取获取的logo图标的特征点,及各图像块中包含的logo图标的特征点,然后将提取的特征点进行匹配。
S212:根据匹配结果确定图像块是否包含版权信息。
具体的,如果获取的logo图标与某个图像块中包含的logo图标的匹配度大于预设匹配度,则确定该图像块包含版权信息,否则确定该图像块不包含版权信息。
进一步的,步骤S22包括:
若识别出任一图像块中包含版权信息,则确定述待识别图片为侵权图片。
本领域技术人员应能理解,在上述各个实施例的基础上,还可以进行明显变型(例如,对所列举的模式进行组合)或等同替换。
在上文中,虽然按照上述的顺序描述了侵权图片的识别方法实施例中 的各个步骤,本领域技术人员应清楚,本公开实施例中的步骤并不必然按照上述顺序执行,其也可以倒序、并行、交叉等其他顺序执行,而且,在上述步骤的基础上,本领域技术人员也可以再加入其他步骤,这些明显变型或等同替换的方式也应包含在本公开的保护范围之内,在此不再赘述。
下面为本公开装置实施例,本公开装置实施例可用于执行本公开方法实施例实现的步骤,为了便于说明,仅示出了与本公开实施例相关的部分,具体技术细节未揭示的,请参照本公开方法实施例。
为了解决如何提高用户体验效果的技术问题,本公开实施例提供一种侵权图片的识别装置。该装置可以执行上述侵权图片的识别方法实施例中的步骤。如图2a所示,该装置主要包括:图片分块模块21和侵权图片判定模块22;其中,图片分块模块21用于根据预先设定的版权位置信息对待识别图片进行分块,获取可能包含版权信息的图像块;侵权图片判定模块22用于根据对图像块的侵权识别结果确定待识别图片是否为侵权图片。
其中,版权位置信息为版权信息所在的位置信息,包括但不限于图片的四角中的至少一角,或者图片的中心位置,或者其他设定的位置。
一般来说,版权信息通常设定在图片的某一固定位置,例如,图片的四角中的任意一角,这样就可以预先统计待识别图片的版权位置信息,然后通过图片分块模块21根据预先设定的版权位置信息对待识别图片进行分块,获取到可能包含版权信息的图像块。
其中,图像块可能为一个或多个,这根据预先设定的版权位置信息中包含的位置个数来确定。如果预先设定的版权位置信息为图片的四角,则需要分割出待识别图片的四个角对应的图像块。具体图像块的大小可根据版权信息占用面积的大小来确定。
其中,版权信息由文字、图形、字母、数字、三维标志和颜色中的至少一种信息组合而成,其形式可以为多种logo图案。
对于侵权图片判定模块22,无需对待识别图片进行识别,只需要对可能包含版权信息的图像块进行识别即可,这样比较有针对性,而且可以降低计算量。如果识别出某一个图像块存在侵权内容,则确定待识别图片即为侵权图片。
本实施例通过图片分块模块21根据预先设定的版权位置信息对待识别 图片进行分块,获取可能包含版权信息的图像块;通过侵权图片判定模块22根据对图像块的侵权识别结果确定待识别图片是否为侵权图片,不仅可以减少计算量,提高识别效率,还可以有针对的进行图像块侵权识别,提高识别准确率。
在一个可选的实施例中,如图2b所示,侵权图片判定模块22包括:图像块识别单元221和侵权图片判定单元222;其中,图像块识别单元221用于对各图像块进行侵权识别;侵权图片判定单元222用于若识别出任一图像块中包含版权信息,则根据包含版权信息的图像块确定待识别图片是否为侵权图片。
本实施例通过图片分块模块21根据预先设定的版权位置信息对待识别图片进行分块,获取可能包含版权信息的图像块,然后通过图像块识别单元221对各图像块进行侵权识别,若通过侵权图片判定单元222识别出任一图像块中包含版权信息,则根据包含版权信息的图像块确定待识别图片是否为侵权图片,不仅可以减少计算量,提高识别效率,还可以有针对的进行图像块侵权识别,提高识别准确率。
进一步,如图2c所示,所述装置还包括:分类器训练模块23;其中,分类器训练模块23用于根据至少一个包含预先设定的版权信息的原版图片训练得到图像分类器;图像块识别单元221具体用于:将图像块输入图像分类器,根据图像分类器的分类结果确定图像块是否包含版权信息。
其中,版权信息可能包含多种样式或多种logo图标,在训练图像分类器时为了提高对侵权图片的识别准确率,将所有样式或logo图标均考虑在内。
具体的,针对分类器训练模块23,将至少一个包含预先设定的版权信息的原版图片作为训练材料,采用机器学习分类算法对其进行训练得到图像分类器。具体可采用的机器学习分类算法包括但不限于以下任意一种:朴素贝叶斯算法、人工神经网络算法、遗传算法、K最近邻(K-NearestNeighbor,KNN)分类算法、聚类算法等。
具体的,针对图像块识别单元221,图像分类器的分类结果可以为一个分值,或者是直接给出文字结果。如果是分值,则根据分值确定图像块是否包含版权信息,例如当分值大于预设分值时,则表征图像块包含版权信息,当分值小于或等于预设分值时,则表征图像块不包含版权信息。如果是直接 给出文字结果,则图像分类器的直接输出某个图像块包含版权信息,或某个图像块不包含版权信息。
进一步的,如图2d所示,所述装置还包括:logo图标获取模块24;其中,logo图标获取模块24用于从预先建立的用于存储logo图标的数据库中获取与预先设定的版权信息相关联的至少一种logo图标;
图像块识别单元221具体用于:将logo图标与各图像块中包含的logo图标进行匹配;根据匹配结果确定图像块是否包含版权信息。
具体的,图像块识别单元221可采用图像特征提取算法,分别提取获取的logo图标的特征点,及各图像块中包含的logo图标的特征点,然后将提取的特征点进行匹配。如果图像块识别单元221获取的logo图标与某个图像块中包含的logo图标的匹配度大于预设匹配度,则确定该图像块包含版权信息,否则确定该图像块不包含版权信息。
进一步的,侵权图片判定单元222具体用于:若识别出任一图像块中包含版权信息,则确定待识别图片为侵权图片。
有关侵权图片的识别装置实施例的工作原理、实现的技术效果等详细说明可以参考前述侵权图片的识别方法实施例中的相关说明,在此不再赘述。
图3是图示根据本公开的实施例的侵权图片的识别硬件装置的硬件框图。如图3所示,根据本公开实施例的侵权图片的识别硬件装置30包括存储器31和处理器32。
该存储器31用于存储非暂时性计算机可读指令。具体地,存储器31可以包括一个或多个计算机程序产品,该计算机程序产品可以包括各种形式的计算机可读存储介质,例如易失性存储器和/或非易失性存储器。该易失性存储器例如可以包括随机存取存储器(RAM)和/或高速缓冲存储器(cache)等。该非易失性存储器例如可以包括只读存储器(ROM)、硬盘、闪存等。
该处理器32可以是中央处理单元(CPU)或者具有数据处理能力和/或指令执行能力的其它形式的处理单元,并且可以控制侵权图片的识别硬件装置30中的其它组件以执行期望的功能。在本公开的一个实施例中,该处 理器32用于运行该存储器31中存储的该计算机可读指令,使得该侵权图片的识别硬件装置30执行前述的本公开各实施例的侵权图片的识别方法的全部或部分步骤。
本领域技术人员应能理解,为了解决如何获得良好用户体验效果的技术问题,本实施例中也可以包括诸如通信总线、接口等公知的结构,这些公知的结构也应包含在本公开的保护范围之内。
有关本实施例的详细说明可以参考前述各实施例中的相应说明,在此不再赘述。
图4是图示根据本公开的实施例的计算机可读存储介质的示意图。如图4所示,根据本公开实施例的计算机可读存储介质40,其上存储有非暂时性计算机可读指令41。当该非暂时性计算机可读指令41由处理器运行时,执行前述的本公开各实施例的视频特征的比对方法的全部或部分步骤。
上述计算机可读存储介质40包括但不限于:光存储介质(例如:CD-ROM和DVD)、磁光存储介质(例如:MO)、磁存储介质(例如:磁带或移动硬盘)、具有内置的可重写非易失性存储器的媒体(例如:存储卡)和具有内置ROM的媒体(例如:ROM盒)。
有关本实施例的详细说明可以参考前述各实施例中的相应说明,在此不再赘述。
图5是图示根据本公开实施例的终端的硬件结构示意图。如图5所示,该侵权图片的识别终端50包括上述侵权图片的识别装置实施例。
该终端可以以各种形式来实施,本公开中的终端可以包括但不限于诸如移动电话、智能电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、导航装置、车载终端、车载显示终端、车载电子后视镜等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。
作为等同替换的实施方式,该终端还可以包括其他组件。如图5所示,该侵权图片的识别终端50可以包括电源单元51、无线通信单元52、A/V(音频/视频)输入单元53、用户输入单元54、感测单元55、接口单元56、控制器57、输出单元58和存储器59等等。图5示出了具有各种组件的终端,但是应理解的是,并不要求实施所有示出的组件,也可以替代地实施更多或 更少的组件。
其中,无线通信单元52允许终端50与无线通信系统或网络之间的无线电通信。A/V输入单元53用于接收音频或视频信号。用户输入单元54可以根据用户输入的命令生成键输入数据以控制终端的各种操作。感测单元55检测终端50的当前状态、终端50的位置、用户对于终端50的触摸输入的有无、终端50的取向、终端50的加速或减速移动和方向等等,并且生成用于控制终端50的操作的命令或信号。接口单元56用作至少一个外部装置与终端50连接可以通过的接口。输出单元58被构造为以视觉、音频和/或触觉方式提供输出信号。存储器59可以存储由控制器55执行的处理和控制操作的软件程序等等,或者可以暂时地存储己经输出或将要输出的数据。存储器59可以包括至少一种类型的存储介质。而且,终端50可以与通过网络连接执行存储器59的存储功能的网络存储装置协作。控制器57通常控制终端的总体操作。另外,控制器57可以包括用于再现或回放多媒体数据的多媒体模块。控制器57可以执行模式识别处理,以将在触摸屏上执行的手写输入或者图片绘制输入识别为字符或图像。电源单元51在控制器57的控制下接收外部电力或内部电力并且提供操作各元件和组件所需的适当的电力。
本公开提出的视频特征的比对方法的各种实施方式可以以使用例如计算机软件、硬件或其任何组合的计算机可读介质来实施。对于硬件实施,本公开提出的视频特征的比对方法的各种实施方式可以通过使用特定用途集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理装置(DSPD)、可编程逻辑装置(PLD)、现场可编程门阵列(FPGA)、处理器、控制器、微控制器、微处理器、被设计为执行这里描述的功能的电子单元中的至少一种来实施,在一些情况下,本公开提出的视频特征的比对方法的各种实施方式可以在控制器57中实施。对于软件实施,本公开提出的视频特征的比对方法的各种实施方式可以与允许执行至少一种功能或操作的单独的软件模块来实施。软件代码可以由以任何适当的编程语言编写的软件应用程序(或程序)来实施,软件代码可以存储在存储器59中并且由控制器57执行。
有关本实施例的详细说明可以参考前述各实施例中的相应说明,在此不再赘述。
以上结合具体实施例描述了本公开的基本原理,但是,需要指出的是,在本公开中提及的优点、优势、效果等仅是示例而非限制,不能认为这些优 点、优势、效果等是本公开的各个实施例必须具备的。另外,上述公开的具体细节仅是为了示例的作用和便于理解的作用,而非限制,上述细节并不限制本公开为必须采用上述具体的细节来实现。
本公开中涉及的器件、装置、设备、系统的方框图仅作为例示性的例子并且不意图要求或暗示必须按照方框图示出的方式进行连接、布置、配置。如本领域技术人员将认识到的,可以按任意方式连接、布置、配置这些器件、装置、设备、系统。诸如“包括”、“包含”、“具有”等等的词语是开放性词汇,指“包括但不限于”,且可与其互换使用。这里所使用的词汇“或”和“和”指词汇“和/或”,且可与其互换使用,除非上下文明确指示不是如此。这里所使用的词汇“诸如”指词组“诸如但不限于”,且可与其互换使用。
另外,如在此使用的,在以“至少一个”开始的项的列举中使用的“或”指示分离的列举,以便例如“A、B或C的至少一个”的列举意味着A或B或C,或AB或AC或BC,或ABC(即A和B和C)。此外,措辞“示例的”不意味着描述的例子是优选的或者比其他例子更好。
还需要指出的是,在本公开的系统和方法中,各部件或各步骤是可以分解和/或重新组合的。这些分解和/或重新组合应视为本公开的等效方案。
可以不脱离由所附权利要求定义的教导的技术而进行对在此所述的技术的各种改变、替换和更改。此外,本公开的权利要求的范围不限于以上所述的处理、机器、制造、事件的组成、手段、方法和动作的具体方面。可以利用与在此所述的相应方面进行基本相同的功能或者实现基本相同的结果的当前存在的或者稍后要开发的处理、机器、制造、事件的组成、手段、方法或动作。因而,所附权利要求包括在其范围内的这样的处理、机器、制造、事件的组成、手段、方法或动作。
提供所公开的方面的以上描述以使本领域的任何技术人员能够做出或者使用本公开。对这些方面的各种修改对于本领域技术人员而言是非常显而易见的,并且在此定义的一般原理可以应用于其他方面而不脱离本公开的范围。因此,本公开不意图被限制到在此示出的方面,而是按照与在此公开的原理和新颖的特征一致的最宽范围。
为了例示和描述的目的已经给出了以上描述。此外,此描述不意图将本公开的实施例限制到在此公开的形式。尽管以上已经讨论了多个示例方面 和实施例,但是本领域技术人员将认识到其某些变型、修改、改变、添加和子组合。

Claims (16)

  1. 一种侵权图片的识别方法,其特征在于,包括:
    根据预先设定的版权位置信息对待识别图片进行分块,获取可能包含版权信息的图像块;
    根据对所述图像块的侵权识别结果确定所述待识别图片是否为侵权图片。
  2. 根据权利要求1所述的方法,其特征在于,所述根据对所述图像块的侵权识别结果确定所述待识别图片是否为侵权图片的步骤,包括:
    对各图像块进行侵权识别;
    若识别出任一图像块中包含版权信息,则根据所述包含版权信息的图像块确定所述待识别图片是否为侵权图片。
  3. 根据权利要求2所述的方法,其特征在于,所述方法还包括:
    根据至少一个包含预先设定的版权信息的原版图片训练得到图像分类器;
    所述对各图像块进行侵权识别的步骤,包括:
    将所述图像块输入所述图像分类器,根据所述图像分类器的分类结果确定所述图像块是否包含版权信息。
  4. 根据权利要求2所述的方法,其特征在于,所述方法还包括:
    从预先建立的用于存储logo图标的数据库中获取与所述预先设定的版权信息相关联的至少一种logo图标;
    所述对各图像块进行侵权识别的步骤,包括:
    将所述logo图标与各图像块中包含的logo图标进行匹配;
    根据匹配结果确定所述图像块是否包含版权信息。
  5. 根据权利要求2所述的方法,其特征在于,所述若识别出任一图像块中包含版权信息,则根据所述包含版权信息的图像块确定所述待识别图片是否为侵权图片的步骤,包括:
    若识别出任一图像块中包含版权信息,则确定所述待识别图片为侵权图片。
  6. 根据权利要求1-5任一项所述的方法,其特征在于,所述版权位置信息为所述待识别图片的四角中的至少一角。
  7. 根据权利要求1-5任一项所述的方法,其特征在于,所述版权信息由文字、图形、字母、数字、三维标志和颜色中的至少一种信息组合而成。
  8. 一种侵权图片的识别装置,其特征在于,包括:
    图片分块模块,用于根据预先设定的版权位置信息对待识别图片进行分块,获取可能包含版权信息的图像块;
    侵权图片判定模块,用于根据对所述图像块的侵权识别结果确定所述待识别图片是否为侵权图片。
  9. 根据权利要求8所述的装置,其特征在于,所述侵权图片判定模块包括:
    图像块识别单元,用于对各图像块进行侵权识别;
    侵权图片判定单元,用于若识别出任一图像块中包含版权信息,则根据所述包含版权信息的图像块确定所述待识别图片是否为侵权图片。
  10. 根据权利要求9所述的装置,其特征在于,所述装置还包括:
    分类器训练模块,用于根据至少一个包含预先设定的版权信息的原版图片训练得到图像分类器;
    所述图像块识别单元具体用于:将所述图像块输入所述图像分类器,根据所述图像分类器的分类结果确定所述图像块是否包含版权信息。
  11. 根据权利要求9所述的装置,其特征在于,所述装置还包括:
    logo图标获取模块,用于从预先建立的用于存储logo图标的数据库中获取与所述预先设定的版权信息相关联的至少一种logo图标;
    所述图像块识别单元具体用于:将所述logo图标与各图像块中包含的logo图标进行匹配;根据匹配结果确定所述图像块是否包含版权信息。
  12. 根据权利要求9所述的装置,其特征在于,所述侵权图片判定单元具体用于:若识别出任一图像块中包含版权信息,则确定所述待识别图片为侵权图片。
  13. 根据权利要求8-12任一项所述的装置,其特征在于,所述版权位置信息为所述待识别图片的四角中的至少一角。
  14. 根据权利要求8-12任一项所述的装置,其特征在于,所述版权信息由文字、图形、字母、数字、三维标志和颜色中的至少一种信息组合而成。
  15. 一种侵权图片的识别硬件装置,包括:
    存储器,用于存储非暂时性计算机可读指令;以及
    处理器,用于运行所述计算机可读指令,使得所述处理器执行时实现根据权利要求1-7中任意一项所述的侵权图片的识别方法。
  16. 一种计算机可读存储介质,用于存储非暂时性计算机可读指令,当所述非暂时性计算机可读指令由计算机执行时,使得所述计算机执行权利要求1-7中任意一项所述的侵权图片的识别方法。
PCT/CN2018/117712 2018-09-13 2018-11-27 侵权图片的识别方法、装置和计算机可读存储介质 WO2020052083A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811065343.0 2018-09-13
CN201811065343.0A CN109299734B (zh) 2018-09-13 2018-09-13 侵权图片的识别方法、装置和计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2020052083A1 true WO2020052083A1 (zh) 2020-03-19

Family

ID=65166802

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/117712 WO2020052083A1 (zh) 2018-09-13 2018-11-27 侵权图片的识别方法、装置和计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN109299734B (zh)
WO (1) WO2020052083A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111950360A (zh) * 2020-07-06 2020-11-17 北京奇艺世纪科技有限公司 一种识别侵权用户的方法及装置

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110807176A (zh) * 2019-10-15 2020-02-18 武汉牌洲湾广告科技有限公司 基于神经网络的图片版权鉴别方法、装置、设备及介质
CN112215812B (zh) * 2020-09-30 2023-12-19 大方众智创意广告(珠海)有限公司 图像检测方法、装置、电子设备及可读存储介质
CN112580620A (zh) * 2020-12-25 2021-03-30 北京百度网讯科技有限公司 标志图片处理方法、装置、设备和介质
CN112788363B (zh) * 2020-12-30 2023-04-28 北京奇艺世纪科技有限公司 识别侵权视频的方法、识别侵权视频的装置及电子设备
CN113536022A (zh) * 2021-08-06 2021-10-22 数贸科技(北京)有限公司 侵权图像的识别方法、装置、计算设备及计算机存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105138867A (zh) * 2014-06-09 2015-12-09 北大方正集团有限公司 图片版权保护的方法和设备
CN106530194A (zh) * 2015-09-09 2017-03-22 阿里巴巴集团控股有限公司 一种疑似侵权产品图片的检测方法及装置
CN106682124A (zh) * 2016-12-09 2017-05-17 百度在线网络技术(北京)有限公司 一种图片识别方法、装置和设备
CN107798649A (zh) * 2017-09-05 2018-03-13 北京五八信息技术有限公司 图片的识别方法和装置
CN107832384A (zh) * 2017-10-28 2018-03-23 北京安妮全版权科技发展有限公司 侵权检测方法、装置、存储介质和电子设备
CN108171264A (zh) * 2017-12-26 2018-06-15 北京非斗数据科技发展有限公司 一种利用深度学习结合哈希编码对图片侵权内容的提取识别技术

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101453333B (zh) * 2008-10-16 2010-12-29 北京光线传媒股份有限公司 一种针对媒体文件的版权识别方法、装置及系统
CN107958264A (zh) * 2017-11-20 2018-04-24 奕响(大连)科技有限公司 一种图片相似判定方法
CN107886134A (zh) * 2017-11-30 2018-04-06 奕响(大连)科技有限公司 一种局部创造性的图片相似判定方法
CN108108753B (zh) * 2017-12-15 2022-08-19 京北方信息技术股份有限公司 一种基于支持向量机的复选框选择状态的识别方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105138867A (zh) * 2014-06-09 2015-12-09 北大方正集团有限公司 图片版权保护的方法和设备
CN106530194A (zh) * 2015-09-09 2017-03-22 阿里巴巴集团控股有限公司 一种疑似侵权产品图片的检测方法及装置
CN106682124A (zh) * 2016-12-09 2017-05-17 百度在线网络技术(北京)有限公司 一种图片识别方法、装置和设备
CN107798649A (zh) * 2017-09-05 2018-03-13 北京五八信息技术有限公司 图片的识别方法和装置
CN107832384A (zh) * 2017-10-28 2018-03-23 北京安妮全版权科技发展有限公司 侵权检测方法、装置、存储介质和电子设备
CN108171264A (zh) * 2017-12-26 2018-06-15 北京非斗数据科技发展有限公司 一种利用深度学习结合哈希编码对图片侵权内容的提取识别技术

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111950360A (zh) * 2020-07-06 2020-11-17 北京奇艺世纪科技有限公司 一种识别侵权用户的方法及装置
CN111950360B (zh) * 2020-07-06 2023-08-18 北京奇艺世纪科技有限公司 一种识别侵权用户的方法及装置

Also Published As

Publication number Publication date
CN109299734B (zh) 2023-12-19
CN109299734A (zh) 2019-02-01

Similar Documents

Publication Publication Date Title
WO2020052083A1 (zh) 侵权图片的识别方法、装置和计算机可读存储介质
WO2020052084A1 (zh) 视频封面选择方法、装置和计算机可读存储介质
US8724908B2 (en) System and method for labeling a collection of images
WO2020037863A1 (zh) 三维人脸图像重建方法、装置和计算机可读存储介质
US11749020B2 (en) Method and apparatus for multi-face tracking of a face effect, and electronic device
US20210074054A1 (en) Image processing method and device, computer readable storage medium, and terminal
US8036432B2 (en) System and method of saving digital content classified by person-based clustering
WO2019242271A1 (zh) 图像变形方法、装置及电子设备
WO2020019664A1 (zh) 基于人脸的形变图像生成方法和装置
US10108643B2 (en) Graphical interface device, graphical interface method and medium
US20080240575A1 (en) Learning concept templates from web images to query personal image databases
WO2020019665A1 (zh) 基于人脸的三维特效生成方法、装置和电子设备
KR20160086090A (ko) 이미지를 디스플레이하는 사용자 단말기 및 이의 이미지 디스플레이 방법
CN110830846B (zh) 一种视频裁剪方法及服务器
TW201546636A (zh) 註解顯示器輔助裝置及輔助方法
CN111581208A (zh) 一种数据可视化展示方法及装置
WO2020052085A1 (zh) 视频文字检测方法、装置和计算机可读存储介质
TWI609280B (zh) 在電子閱讀器環境中基於內容及物件元資料的搜尋
WO2018166499A1 (zh) 文本分类方法、设备和存储介质
WO2020001015A1 (zh) 场景操控的方法、装置及电子设备
WO2017020719A1 (zh) 一种对页面中对象信息分类的方法和设备
CN109376764B (zh) 基于聚类的数据收集方法、装置和计算机可读存储介质
WO2020052082A1 (zh) 视频漂浮纸片检测方法、装置和计算机可读存储介质
CN108351888B (zh) 生成可推迟数据流
US20160267259A1 (en) Electronic device and content providing method in electronic device

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: 18933201

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

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 23/06/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18933201

Country of ref document: EP

Kind code of ref document: A1