CN113065563A - Method, system, terminal and medium for identifying screenshot and electronic document - Google Patents
Method, system, terminal and medium for identifying screenshot and electronic document Download PDFInfo
- Publication number
- CN113065563A CN113065563A CN202110315489.1A CN202110315489A CN113065563A CN 113065563 A CN113065563 A CN 113065563A CN 202110315489 A CN202110315489 A CN 202110315489A CN 113065563 A CN113065563 A CN 113065563A
- Authority
- CN
- China
- Prior art keywords
- screenshots
- picture
- computer
- image
- mobile phone
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a method, a system, a terminal and a medium for identifying a screenshot and an electronic document, and relates to the technical field of computer image identification. The information data processing terminal judges that the acquired image photo is a target picture as long as the pixel value of a certain row or a certain column at the border of one side among the four sides of the image is completely equal to the pixel value of the nearest certain row or column, wherein the target picture refers to a mobile phone screenshot, a computer screenshot and an electronic document. And after the acquired image picture is judged to be the target picture, if EXIF information still exists in the picture, detecting the EXIF information again, and if the exposure time does not exist, further determining the acquired image picture as the target picture and storing the target picture. The method disclosed by the invention has the advantages that the precision exceeds 95% in the actual test, the recall rate is 85.3%, the detection requirements are quickly and well realized, and various complex conditions in the prior art are solved by a simple method.
Description
Technical Field
The invention relates to the technical field of computer image identification, in particular to an image screenshot and electronic document identification method, system, terminal and medium.
Background
The currently available techniques include frequency domain analysis, spectral analysis, filtering and other conventional image processing techniques, and may also refer to EXIF information of a captured picture (which is not available if the picture is non-captured). EXIF of picture refers to: exchangeable image file format, english: changeable image file format. If the EXIF information is complete, for example, exposure time ('exposure time') exists, the EXIF information is considered to be directly shot by a camera and is a non-target picture, and the problem of copying the digital picture is not considered here, because the newly copied picture is completely consistent with the original picture as long as the digital picture is copied, but the technology is only used for identifying a mobile phone screenshot, a computer screenshot and an electronic document.
Through the above analysis, the problems and defects of the prior art are as follows:
in order to identify general pictures, mobile phone screenshots, computer screenshots, and electronic documents, the following four prior arts have been tried:
(1) the problem is converted into a frequency domain for analysis by using the traditional image processing technology, such as spectral analysis, filtering and the like, by using Fourier transform, and because the detection picture has complex diversity, the detection picture is difficult to find a stable characteristic in the frequency domain for detection.
(2) For an original picture, training is performed by using a currently popular deep learning model-Convolutional Neural Network (CNN) classification method, and the prediction effect is not feasible, because the detected picture has complex diversity.
(3) For the original picture, the RGB distribution rule is researched, statistical analysis is carried out, and the effect is poor.
(4) The EXIF information is easily damaged by conversion between data formats and transmission between different devices, and is difficult to have universality in practice.
The difficulty in solving the above problems and defects is: the pictures to be detected have complex diversity, so that the traditional technical means such as adopting a picture classification model (CNN) or researching the RGB distribution rule of the pictures in an original spatial domain, and using spectral analysis, filtering and the like in a frequency domain are not feasible.
The significance of solving the problems and the defects is as follows: the algorithm avoids the problems, invents a new algorithm based on pixel point detection, and can simply, accurately and quickly identify the screenshot of the mobile phone, the screenshot of the computer and the electronic document.
Disclosure of Invention
In order to overcome the problems in the related art, the disclosed embodiments of the present invention provide a method, system, terminal, and medium for identifying an image screenshot and an electronic document. In particular to a method for identifying a mobile phone screenshot, a computer screenshot and an electronic document based on pixel point detection, which comprises the following steps:
according to a first aspect of the disclosed embodiments of the present invention, there is provided a method for identifying a mobile phone screenshot, a computer screenshot, and an electronic document based on pixel point detection, which is applied to an information data processing terminal, and the method for identifying a mobile phone screenshot, a computer screenshot, and an electronic document based on pixel point detection includes:
and if the pixel value of a certain row or a certain column at the border of one side in the four sides of the image acquired by the information data processing terminal is completely equal to the pixel value of the nearest certain row or column, judging that the picture is not shot under the normal condition. The reason is that even in a very bright or dark environment, a line or column of a shot picture contains thousands of pixels, which are exactly equal to the pixel values of the nearest neighboring line or column, and this is almost impossible in the actual shot imaging.
In order to ensure accuracy, EXIF information of a next picture is detected after the determination condition (if not, the step is skipped to directly output the previous determination result and store the result), and if the attribute of exposure time ('exposure time') does not exist, the picture is further determined to be the target picture and stored.
The information data processing terminal includes: a mobile phone, a computer, a camera or an intelligent shooting device capable of acquiring image information.
The identification method for the mobile phone screenshot, the computer screenshot and the electronic document based on the pixel point detection further comprises the following steps:
the information data processing terminal takes picture size of 960 × 1708 as an example, and detects pixel values of points at two frames, and if the pixel values of points contained in the 1 st column and the 2 nd column are equal on the side of size 960; or on the side of size 1708, if the pixel values of the points contained in the 1 st and 2 nd rows are equal, the picture is considered as the target picture. The target pictures refer to mobile phone screenshots, computer screenshots and electronic documents.
According to a second aspect of the disclosed embodiments of the present invention, there is provided a system for identifying a screenshot of a mobile phone, a screenshot of a computer, and an electronic document based on pixel point detection, which is applied to an information data processing terminal, and the system for identifying a screenshot of a mobile phone, a screenshot of a computer, and an electronic document based on pixel point detection includes:
the image pixel value acquisition module is used for acquiring pixel values of a certain row or a certain column at the position of an image frame and the nearest vicinity of the image frame;
and the target picture judging module is used for judging the pixel values acquired by the image pixel value acquiring module, detecting whether the pixel values of a certain row or a certain column at the frame are completely equal to the pixel values of the nearest certain row or a certain column, and if the pixel values are completely equal, determining that the target picture is the target picture.
Preferably, the system for recognizing a mobile phone screenshot, a computer screenshot, and an electronic document based on pixel point detection further includes:
the target picture further verification module is used for detecting EXIF information if EXIF information still exists in the picture (if the EXIF information does not exist in the picture, the step is skipped to directly output the further judgment result and the result is stored), and if the EXIF information does not exist in the picture, the obtained picture is further determined as the target picture;
and the storage module is used for storing the result verified by the target picture further verification module.
According to a third aspect of the disclosed embodiments of the present invention, an information data processing terminal is provided, which implements a method for recognizing a mobile phone screenshot, a computer screenshot, and an electronic document based on pixel point detection.
According to a fourth aspect of the disclosed embodiments of the present invention, there is provided a computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of:
judging that the acquired image photo is a target picture if the pixel value of a certain row or a certain column at the position of a frame of one side among four sides of an image acquired by an information data processing terminal is completely equal to the pixel value of the most adjacent certain row or certain column at the position of the frame;
after the obtained image photo is judged to be the target picture, if the picture does not have EXIF information, skipping the step and directly outputting the judgment result of the previous step and storing the judgment result;
if the picture still has EXIF information, then detecting the EXIF information, if the exposure time does not exist, further determining the acquired image picture as the target picture, and storing the target picture.
According to a fifth aspect of the disclosed embodiments of the present invention, there is provided a program storage medium for receiving user input, the stored computer program enabling an electronic device to execute the method for recognizing a screenshot of a mobile phone, a screenshot of a computer, and an electronic document based on pixel point detection.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
with the development of artificial intelligence and big data, the requirements for various image auditing services become more and more, and in the application scene of the patent, how to quickly identify a target image becomes important when the auditing of tens of thousands of images on the line is faced every day. The target picture refers to a mobile phone screenshot, a computer screenshot and an electronic document of the picture, and is an illegal picture; legal pictures refer to various data directly taken by the camera, such as various proofs.
Because all pixel points of a picture do not need to be traversed, only information at a frame needs to be detected, the detection speed of the method is high, the precision exceeds 95% in actual test, and the recall rate is 85.3% (10831 pictures are randomly tested on line, 297 unqualified pictures are detected by the algorithm, including mobile phone screenshots, computer screenshots and electronic documents, 285 unqualified pictures are manually judged in 297, 334 unqualified pictures are manually judged in 10831), and the detection requirement is quickly and well realized, which is the advantage of the algorithm.
However, there are some cases that the algorithm cannot detect at present, and the reason for this is that the distribution of pixel values at the frame of the picture is no longer single, and the pixel value of the 1 st row (column) is no longer equal to the pixel value of the 2 nd row (column).
The invention can quickly and accurately detect the screenshot of the mobile phone, the screenshot of the computer and the electronic document. The core idea of the invention is to detect whether the pixel values of two rows or two columns at the picture frame are completely the same, and solve various complex conditions existing in the prior art by a simple method.
The effects and advantages obtained by combining experimental or experimental data with the prior art are: as shown in fig. 3:
inputting: several pictures, put under 111 folders.
And (3) outputting: and returning the picture name of the mobile phone screenshot, the computer screenshot or the electronic document, and printing the time detected by the algorithm.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a flowchart of a method for identifying a mobile phone screenshot, a computer screenshot, and an electronic document based on pixel point detection according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a system for recognizing a mobile phone screenshot, a computer screenshot, and an electronic document based on pixel point detection according to an embodiment of the present invention.
In fig. 2: 1. an image pixel value acquisition module; 2. a target picture judging module; 3. the target picture further verification module; 4. and a storage module.
Fig. 3 is a diagram of an algorithm detection time interface provided by the embodiment of the invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
As shown in fig. 1, the present invention provides a method for identifying a mobile phone screenshot, a computer screenshot, and an electronic document based on pixel point detection, which is applied to an information data processing terminal, and includes:
s101, if the pixel value of a certain row or a certain column at the border of one side in the four sides of the image acquired by the information data processing terminal is completely equal to the pixel value of the nearest certain row or certain column, the acquired image photo is determined to be the target picture.
And S102, after the acquired image photo is determined to be the target picture, if EXIF information still exists in the picture (if the EXIF information does not exist, the step is skipped to directly output the further determination result and the result is stored), the EXIF information is detected again, and if the exposure time does not exist, the acquired image photo is further determined to be the target picture and is stored.
In the present invention, the information data processing terminal includes: a mobile phone, a computer, a camera or an intelligent shooting device capable of acquiring image information.
As a preferred embodiment, the method for identifying a screenshot of a mobile phone, a screenshot of a computer, and an electronic document based on pixel point detection further includes:
the information data processing terminal takes picture size of 960 × 1708 as an example, and detects pixel values of points at two frames, and if the pixel values of points contained in the 1 st column and the 2 nd column are equal on the side of size 960; or on the side of size 1708, if the pixel values of the points contained in the 1 st and 2 nd rows are equal, the picture is considered as the target picture.
As shown in fig. 2, in the present specification, a system for identifying a screenshot of a mobile phone, a screenshot of a computer, and an electronic document based on pixel point detection is provided, which is applied to an information data processing terminal, and includes:
the image pixel value acquisition module 1 is used for acquiring pixel values of a certain row or a certain column at the position of an image frame and the nearest vicinity of the image frame;
and the target picture judging module 2 is used for judging the pixel values acquired by the image pixel value acquiring module, detecting whether the pixel values of a certain row or a certain column at the border are completely equal to the pixel values of a certain row or a certain column which is the nearest to the border, and if the pixel values are completely equal, determining that the picture is the target picture. The target picture further verification module 3 is configured to, after determining that the obtained image picture is the target picture, detect EXIF information of the picture if the picture still has EXIF information (if the EXIF information is not present, the step is skipped to directly output a further determination result, and the EXIF information is stored), and if the EXIF information is not present, further determine that the obtained image picture is the target picture;
and the storage module 4 is used for further verifying the storage of the target picture after the verification of the module.
The technical solution of the present invention is further described below with reference to specific examples.
Examples
The core idea of the method for identifying the mobile phone screenshot, the computer screenshot and the electronic document based on the pixel point detection provided by the embodiment of the invention is that the screenshot or the electronic document is considered to have a regular connected region with the same pixel values, and whether the pixel values of the 1 st row or the 1 st column at the image frame and the adjacent row or column are equal or not is always detected in consideration of the actual situation and the speed of the algorithm, because the pixel values of the adjacent row or column are unlikely to be identical even if the difference is slight and cannot be distinguished by human eyes during normal shooting.
Specifically, the method for identifying a mobile phone screenshot, a computer screenshot and an electronic document based on pixel point detection provided by the embodiment of the invention comprises the following steps:
if only one of the four sides of the image has a pixel value of a certain row or a certain column at the border completely equal to the pixel value of a certain row or a certain column which is most adjacent to the pixel value, the picture is not normally taken. The reason is that even in a very bright or dark environment, a line or column of a shot picture contains thousands of pixels, which are exactly equal to the pixel values of the nearest neighboring line or column, and this is almost impossible in the actual shot imaging.
In order to ensure accuracy, EXIF information of a next picture is detected after the determination condition (if not, the step is skipped to directly output the previous determination result and store the result), and if the attribute of exposure time ('exposure time') does not exist, the picture is further determined as the target picture and stored.
The accuracy rate of the test on 10,831 pictures is over 95 percent, and the speed is also fast. The reason is that for speed, only the pixel values at the image borders are detected, which is enough to cover most cases from the practical test case, with a recall of 85.3%.
In the example of the screenshot test of the present invention, which has a size of 960 × 1708, the pixel values of two frame points are tested: on the side of dimension 960, if the pixel values of the dots contained in column 1 and column 2 are equal (thus, 1708 pairs of pixel dots are detected together); or on the side of size 1708, if the pixel values of the points contained in the 1 st row and the 2 nd row are equal (thus 960 pairs of pixel points are detected in total), the target picture is considered, and the algorithm detects the time: 0.03 sec (Intel Core i5,1.4GHz), as in FIG. 3. Wherein FIG. 3 illustrates:
inputting: several pictures, put under 111 folders.
And (3) outputting: and returning the picture name of the mobile phone screenshot, the computer screenshot or the electronic document, and printing the time detected by the algorithm.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure should be limited only by the attached claims.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110315489.1A CN113065563A (en) | 2021-03-24 | 2021-03-24 | Method, system, terminal and medium for identifying screenshot and electronic document |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110315489.1A CN113065563A (en) | 2021-03-24 | 2021-03-24 | Method, system, terminal and medium for identifying screenshot and electronic document |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113065563A true CN113065563A (en) | 2021-07-02 |
Family
ID=76561963
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110315489.1A Pending CN113065563A (en) | 2021-03-24 | 2021-03-24 | Method, system, terminal and medium for identifying screenshot and electronic document |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113065563A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117095192A (en) * | 2023-08-21 | 2023-11-21 | 万达信息股份有限公司 | Method and system for realizing mobile phone screenshot judgment based on picture metadata |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101547316A (en) * | 2008-03-25 | 2009-09-30 | 索尼株式会社 | Image capture apparatus and method |
| US8923551B1 (en) * | 2014-07-16 | 2014-12-30 | Interactive Memories, Inc. | Systems and methods for automatically creating a photo-based project based on photo analysis and image metadata |
| CN109947967A (en) * | 2017-10-10 | 2019-06-28 | 腾讯科技（深圳）有限公司 | Image-recognizing method, device, storage medium and computer equipment |
-
2021
- 2021-03-24 CN CN202110315489.1A patent/CN113065563A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101547316A (en) * | 2008-03-25 | 2009-09-30 | 索尼株式会社 | Image capture apparatus and method |
| US8923551B1 (en) * | 2014-07-16 | 2014-12-30 | Interactive Memories, Inc. | Systems and methods for automatically creating a photo-based project based on photo analysis and image metadata |
| CN109947967A (en) * | 2017-10-10 | 2019-06-28 | 腾讯科技（深圳）有限公司 | Image-recognizing method, device, storage medium and computer equipment |
Non-Patent Citations (2)
| Title |
|---|
| 太平洋科技: "P图P到神仙都不认得?教你识破图片有没有被P过", 《HTTPS://BAIJIAHAO.BAIDU.COM/S?ID=1688672477972814763&WFR=SPIDER&FOR=PC》, pages 1 - 4 * |
| 百度经验: "百度经验经验发烧友如何查看图片是不是原图", 《HTTPS://JINGYAN.BAIDU.COM/ARTICLE/A65957F4DC80E224E67F9BF5.HTML》, pages 1 - 4 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117095192A (en) * | 2023-08-21 | 2023-11-21 | 万达信息股份有限公司 | Method and system for realizing mobile phone screenshot judgment based on picture metadata |
| CN117095192B (en) * | 2023-08-21 | 2025-08-26 | 万达信息股份有限公司 | A method and system for realizing mobile phone screenshot determination based on image metadata |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kwon et al. | Learning jpeg compression artifacts for image manipulation detection and localization | |
| Liu et al. | Image retargeting quality assessment | |
| CN102693528B (en) | Noise suppressed in low light images | |
| CN109871845B (en) | Certificate image extraction method and terminal equipment | |
| Bahrami et al. | Blurred image splicing localization by exposing blur type inconsistency | |
| CN101971611B (en) | Method of selecting best image and image selection apparatus | |
| JP2007503030A5 (en) | ||
| TWI358674B (en) | ||
| CN111175318A (en) | Screen scratch fragmentation detection method and equipment | |
| CN105450932B (en) | Backlight photographic method and device | |
| Gourrame et al. | A zero-bit Fourier image watermarking for print-cam process | |
| CN109377494B (en) | A method and device for semantic segmentation of images | |
| CN112307853A (en) | Detection method of aerial image, storage medium and electronic device | |
| CN113628134B (en) | Image noise reduction method and device, electronic equipment and storage medium | |
| CN111767828A (en) | Certificate image copying and identifying method and device, electronic equipment and storage medium | |
| US20150332120A1 (en) | Detecting and processing small text in digital media | |
| Mandelli et al. | Source camera model identification | |
| CN110430424B (en) | FOV testing method and device, storage medium and electronic equipment | |
| CN112287905A (en) | Vehicle damage identification method, device, equipment and storage medium | |
| CN113065563A (en) | Method, system, terminal and medium for identifying screenshot and electronic document | |
| Sandoval Orozco et al. | Image source acquisition identification of mobile devices based on the use of features | |
| WO2021147383A1 (en) | Camera blur detection method and apparatus | |
| CN115115848B (en) | Image processing method, device, electronic device and storage medium | |
| CN116129420A (en) | License plate classification method and device and nonvolatile storage medium | |
| Chen et al. | Forensic technology for source camera identification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210702 |