Unlock instant, AI-driven research and patent intelligence for your innovation.

Color relationship characteristic based image approximate copy detection method

A detection method and image technology, applied in the field of multimedia database management, can solve the problems of high time and space complexity, and achieve the effect of low space complexity

Inactive Publication Date: 2011-03-23
SUN YAT SEN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide an image approximate copy detection method based on color relationship features for the shortcomings of existing methods such as high time and space complexity

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
  • Color relationship characteristic based image approximate copy detection method
  • Color relationship characteristic based image approximate copy detection method
  • Color relationship characteristic based image approximate copy detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described below in conjunction with accompanying drawing.

[0043] Flow chart of the present invention is attached figure 1As shown, the steps include: (1) recording the color relationship features of the image block; (2) extracting robust features of the image; (3) selecting a threshold value and identifying an approximate copy of the image.

[0044] Each step is as follows:

[0045] Step (1), record the color relationship features of the image block

[0046] Suppose the image to be detected is I, and its size is M×N. First, as shown in Figure 2, I is decomposed into image blocks of the size of Bz×Bz (here Bz=16) without overlapping regions, denoted as Blk(j), j=1, 2, . . . , S , S = [ M Bz ] [ N Bz ] . For each small color image block Blk(j), first calculate the average gray value on the three colo...

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 a method for detecting approximate image copies based on colorful relationship characteristics, which comprises the following steps: (1) recording the color relationship characteristics of image blocks; (2) extracting the robust characteristic of an image; and (3) selecting a threshold and identifying the approximate image copies. The method can quickly extract the robust characteristic representation of the digital image and effectively judge whether two images I and I' are the approximate image copies through the characteristic. Compared with the prior art, the methodhas low time complexity and space complexity and can resist a large part of commonly used image processing operations.

Description

technical field [0001] The invention belongs to the fields of multimedia database management and multimedia digital copyright protection. Specifically, it relates to a method for quickly and effectively retrieving the approximate copy version of a given digital image from an image database. technical background [0002] A close copy of a digital image refers to a different version of an image after some conventional digital image processing operations. These modified versions are visually similar to the original image, but differ in quality. Judging whether a given image is an approximate copy of a certain image data in an existing image database (or network) is of great significance for reducing database redundancy and maintaining digital copyright. The detection of near-copies of images is similar to but different from traditional content-based image retrieval (CBIR) in that it only needs to identify different approximate versions from the same image, regardless of its c...

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): G06F17/30
Inventor 骆伟祺黄继武
Owner SUN YAT SEN UNIV