Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-feature-based saliency detection method

A detection method and multi-feature technology, applied in the field of image processing, can solve problems such as high computational complexity, unsatisfactory detection results, poor definition of target boundaries, etc., and achieve the effect of overcoming limitations

Inactive Publication Date: 2016-11-16
SYSU CMU SHUNDE INT JOINT RES INST +1
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The main disadvantages of the existing technology are: (1) The traditional image saliency detection method has the main disadvantages of low resolution, poorly defined object boundary, and high computational complexity; (2) The saliency detection method using individual features generates a saliency map It often contains a lot of background information, and cannot achieve satisfactory detection results on images with complex background textures

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
  • Multi-feature-based saliency detection method
  • Multi-feature-based saliency detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Such as figure 1 As shown, a multi-feature-based saliency detection method includes the following steps:

[0043] S1: collect the image I to be detected;

[0044] S2: Perform multi-scale comparison, histogram around the center, and color space distribution processing on image I to obtain feature saliency map I 1 , I 2 , I 3 ,Such as figure 2 shown;

[0045] S3: Use the Markov model to analyze the feature saliency map I respectively 1 , I 2 , I 3 Carry out the learning calculation of the weight, and then use the maximum likelihood estimation method to obtain the optimal solution of the parameter estimation of the Markov model;

[0046] S4: Use the Markov model of the optimal parameter estimation solution obtained in S3 to analyze the feature saliency map I respectively 1 , I 2 , I 3 The marker sequence with the highest probability is obtained through detection, and the final feature saliency map is obtained by expressing the marker sequence with the highest p...

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 multi-feature-based saliency detection method. The method comprises the steps of firstly, performing calculation by applying three different saliency clues of multi-scale comparison, a center-surround histogram and color space distribution to obtain separate feature saliency maps; secondly, calculating weights of the separate feature saliency maps through Markov model learning, and obtaining an optimal solution of model parameter estimation by adopting a maximum likelihood estimation method; and finally, detecting a test image by utilizing a Markov model.

Description

technical field [0001] The invention relates to the field of image processing, and more particularly, to a multi-feature-based saliency detection method. Background technique [0002] With the advent of the era of big data, massive amounts of information have brought a lot of convenience to people's lives, and a considerable part of these massive data belongs to image information. How to extract useful information from these image data as soon as possible is A matter of concern. For an image, usually, what we pay attention to is not the whole image, but a part of it that is important, useful and worthy of attention, that is, visually salient regions, which often contain the most important parts of the image. The saliency detection method represented by visual attention is an important technology to improve the real-time and analysis accuracy of screening information from big data, and saliency detection is an important content in the field of image processing and has a wide...

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
IPC IPC(8): G06K9/46
CPCG06V10/50G06V10/56G06V10/462
Inventor 胡海峰曹向前顾建权李昊曦
Owner SYSU CMU SHUNDE INT JOINT RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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