Pirate video identification method and system

A video recognition and video technology, applied in video data indexing, video data retrieval, character and pattern recognition, etc., can solve problems such as instability, unrecognizable bootleg video, serious exposure, etc., to improve precision and accuracy, solve Rights protection matters, the effect of improving image quality

Active Publication Date: 2021-10-19
厦门能见易判信息科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, using mobile phones, DV and other equipment with camera functions to shoot in dark light environments, and because the photographer is not a professional cameraman, the shooting is not standardized, unstable, and easy to shake, resulting in severe exposure, color distortion, and noise. , incorrect shooting angles, occlusion, deformation of the screen, and shooting of the surrounding environment other than the screen, such as curtains and walls, etc. Due to the problem, the accuracy and accuracy of the comparison results are not high, and the pirated video cannot be identified, which cannot meet the real scene

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Pirate video identification method and system
  • Pirate video identification method and system
  • Pirate video identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] This embodiment provides a bootleg video identification method, such as figure 1 As shown, mainly include the following steps (step S1 to step S5):

[0030] Step S1, correcting the image of the video to be recognized;

[0031] As an optional implementation of this embodiment, such as figure 2 As shown, step S1 specifically includes:

[0032] Step S11, using the Hough transform to generate a plurality of straight lines in the image of the video to be recognized, the angle between any one of the plurality of straight lines and the straight line in the vertical direction is less than 30 degrees;

[0033] Step S12, calculating the average value of the included angles formed by multiple straight lines and straight lines in the vertical direction;

[0034] Step S13, using the average value to rotate the video image;

[0035] Step S14, adjust the image details through the loss function method, wherein the image details refer to the pixels in the image, in the fixed image...

Embodiment 2

[0085] This embodiment provides a bootleg video identification system, such as Figure 8 As shown, it mainly includes: an image correction module 60, which is used to correct the image of the video to be recognized; a position extraction module 61, which is connected to the image correction module 60, and is used to determine the screen by extracting the position area of ​​interest in the corrected video the position; the cropping module 62 is connected with the position extraction module 61, and is used to crop the corrected video image according to the screen position; the noise reduction module 63 is connected with the cropping module 62, and is used for cropping the video image The video image is subjected to noise reduction processing; the video comparison module 64 is connected with the noise reduction module 63, and is used to compare the similarity between the video to be identified after the noise reduction processing and the genuine video, and determine the video to b...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a pirated video recognition method and system, wherein the method includes: Step S1, correcting the image of the video to be recognized; Step S2, judging the screen by extracting the interested position area of ​​the corrected video position; Step S3, according to the screen position, the video image after correction is cut; Step S4, the video image after cutting is subjected to noise reduction; Carry out similarity comparison, and judge whether the video to be identified is a pirated video according to the comparison result. Compared with the prior art, the invention can improve the precision and accuracy of the comparison result between the pirated video and the genuine video.

Description

technical field [0001] The invention relates to a bootleg video identification method and system, belonging to the technical field of video retrieval and comparison. Background technique [0002] The source of pirated films comes from genuine resources, and the main types can be roughly divided into screen videos shown in cinemas, CD-ROM videos, and programs broadcast on TV. Among them, using various hidden equipment to secretly record, screen videos can be turned into pirated videos. However, using mobile phones, DV and other equipment with camera functions to shoot in dark light environments, and because the photographer is not a professional cameraman, the shooting is not standardized, unstable, and easy to shake, resulting in severe exposure, color distortion, and noise. , incorrect shooting angles, occlusion, deformation of the screen, and shooting of the surrounding environment other than the screen, such as curtains and walls, etc. Due to the problem, the precision a...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/32G06K9/40G06K9/62G06T7/246G06F16/71G06F16/783
CPCG06T7/246G06F16/71G06F16/783G06T2207/10016G06T2207/20061G06T2207/30241G06V20/46G06V10/243G06V10/25G06V10/30G06F18/22
Inventor 林凡谢伟业赖华平杨宝英黄小红王丽媛
Owner 厦门能见易判信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap