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

Image significance detection method based on color and texture concentration degrees

A detection method and aggregation technology, applied in the field of image processing, can solve the problem of difficult and accurate positioning of images

Active Publication Date: 2015-12-09
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods can get satisfactory results for images with relatively simple color to background and obvious contrast of salient objects, but for images with complex backgrounds and insufficient color information of salient objects, it is difficult to accurately locate salient regions.

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 significance detection method based on color and texture concentration degrees
  • Image significance detection method based on color and texture concentration degrees
  • Image significance detection method based on color and texture concentration degrees

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0092] like figure 1 As shown, a kind of image saliency detection method based on color and texture aggregation of the present invention comprises the following steps:

[0093] 1. Calculation of color salience: through FCM clustering of color channels, calculate the corresponding color features and their salience extracted in each color channel according to the aggregation degree and inter-class difference degree of each class, and obtain color salience picture. It specifically includes the following steps: (1) Carry out color space conversion on the original image to obtain five color channels of L, a, b, H, and S in the Lab and HSV color spaces, and the i-th channel is marked as CF i (2) cluster the five color channels obtained in step (1) with the fuzzy C-means clustering algorithm (FCM), specify the classification number N=4, obtain 20 candidate classes altogether, be divided into five groups , each group has four candidate classes, and the jth class of the i-th group is...

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 significance detection method based on color and texture concentration degrees, and the method comprises the following steps: 1, color significance calculation; 2, texture significance calculation; 3, confidence characteristic selection; 4, weight confidence characteristic fusion. The method carries out testing on an ASD data set, can guarantee that a saliency map result meets the requirements, and can obtain a higher-accuracy saliency map result for each type of natural images.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to an image saliency detection method based on color and texture aggregation, and the invention is a natural color image saliency detection method. Background technique [0002] Most of human perception of the external environment comes from vision. The perception information of the human visual system to the surrounding environment accepted by the human brain mainly includes the perception of light, color, space-time frequency and moving objects. The acquisition, analysis and utilization of information requires a series of brain processes. Studies have shown that the processing of information by the human visual system tends to focus on the part with strong perception and consider it as salient information in the external environment. Salient regions of an image represent image regions that the human visual system pays attention to. Visual salience is closely related to how the h...

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): G06K9/46
CPCG06V10/462
Inventor 沃焱陈晰刘红成
Owner SOUTH CHINA UNIV OF TECH