Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Image evidence obtaining method and system based on multi-view features

A multi-view and image technology, applied to instruments, character and pattern recognition, computer components, etc., to achieve good flexibility, good expressiveness and accuracy, and good differentiation effects

Active Publication Date: 2021-07-30
TIANJIN POLYTECHNIC UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Data-dependent learning methods can obtain higher-quality image hashes, but most learning algorithms only emphasize feature learning using deep neural networks

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
  • Image evidence obtaining method and system based on multi-view features
  • Image evidence obtaining method and system based on multi-view features
  • Image evidence obtaining method and system based on multi-view features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0093] Below in conjunction with accompanying drawing, the present invention is described in further detail:

[0094] Feature extraction is a concept in computer vision and image processing. It refers to the description of image information extracted using a computer. The multi-features in the present invention refer to the features based on the three viewing angles of the image, which are image edge features, intensity features and texture features respectively, and the image forensics is completed through the features under the three viewing angles.

[0095] The present invention focuses on solving three key problems, as follows:

[0096] 1) How to better resist various security attacks of the authentication system in the hash algorithm design, and improve the security and robustness of feature selection.

[0097] 2) How to effectively utilize the complementarity of multiple perspectives in the process of perceptual hash coding generation, and develop a perceptual hash lea...

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 provides an image evidence obtaining method and system based on multi-view features, and belongs to the field of image detection. The method comprises the following steps: step 1, respectively obtaining image features of an original image and a to-be-tested image; 2, respectively calculating the hash value of the original image and the hash value of the to-be-tested image; 3, calculating to obtain a Hamming distance by using the hash value of the original image and the hash value of the to-be-tested image; and step 4, obtaining an evidence obtaining result by using the Hamming distance. According to the invention, the bottleneck of calculation and storage is solved, so that the Hash coding result has better expression ability and accuracy; according to the invention, a potential binary representation multi-view function is effectively utilized, and the method is more comprehensive compared with a single view; data with multiple view angles can be fused, so that the framework has better flexibility and wider application scenes; according to the invention, the operation robustness of the image content can be kept, and meanwhile, the method has good distinguishing performance on malicious tampering operation.

Description

technical field [0001] The invention belongs to the field of image detection, and in particular relates to an image forensics method and system based on multi-view features. Background technique [0002] With the proliferation of social sharing networks and the development of more advanced digital editing software, the web is flooded with unverified digital multimedia content. Therefore, how to solve the problem of image authentication requirements brought about by the explosive growth of image data has become a hot spot for researchers. Fortunately, due to the space-time efficiency of binary-aware hashing, it provides a good idea to solve this kind of problem. The image authentication scheme based on binary hashing completes forensics by comparing the Hamming distance of the binary hash between the original image and the image to be tested. [0003] Unlike other vision tasks such as image retrieval, perceptual hashing for image forensics requires a certain degree of robus...

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 Applications(China)
IPC IPC(8): G06K9/62
CPCG06V10/757
Inventor 杜玲王小超王祎婧陈振赫泽宏
Owner TIANJIN POLYTECHNIC UNIV
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
Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com