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

A Saliency Detection Method for Joint Manifold Sorting and Improved Convex Hull

A technology of manifold sorting and detection method, which is applied in the field of image processing and can solve the problems of poor algorithm adaptability and poor detection effect of multiple target images.

Active Publication Date: 2022-07-22
JIANGSU UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Because the traditional Bayesian model-based algorithm is not accurate enough for the fixed window selection, the algorithm has poor detection effect on multiple target images, and the algorithm has poor adaptability

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
  • A Saliency Detection Method for Joint Manifold Sorting and Improved Convex Hull
  • A Saliency Detection Method for Joint Manifold Sorting and Improved Convex Hull
  • A Saliency Detection Method for Joint Manifold Sorting and Improved Convex Hull

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The embodiments and effects of the invention will be described in further detail below with reference to the accompanying drawings.

[0061] refer to figure 1 , a saliency detection method for joint manifold sorting and improved convex hull of the present invention, the foreground saliency map of the image extracted by the MR algorithm is fused with the global comparison map calculated by superpixels to obtain a prior map, and then the Gaussian pyramid is used to reduce the saliency map. Sampling to form a multi-scale image, the Harris algorithm is used to detect corner points to form a convex hull of each scale, and the convex hull of different scales is fused to obtain a more reasonable convex hull. The convex hull is used to calculate the saliency inside and outside the convex hull. Theoretically fuse the prior map and the saliency map inside and outside the convex hull to obtain the final saliency map. The specific implementation steps are as follows:

[0062] Step...

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 saliency detection method for joint manifold sorting and improved convex hull. The saliency map of the approximate position of the salient region is obtained by calculating the color feature, and the foreground image extracted by the saliency map is fused to obtain the prior map; secondly, the image is downsampled by the Gaussian pyramid algorithm to obtain two images of different scales. Combined with the classic Harris The operator detects the corners of the original image and two images of different scales, and finds the intersection of the three to obtain a more reasonable convex hull; then uses the color histogram combined with the convex hull to calculate the observation likelihood probability; finally, according to the existing prior map and likelihood probability, combined with Bayesian model to get saliency map. Compared with the prior art, the method of the present invention can quickly and effectively detect the saliency area of ​​the image, obtain consistently bright salient objects, and obtain a saliency map that is more in line with visual perception.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a saliency detection method for joint manifold sorting and improved convex hull. Background technique [0002] The researchers found that the human visual attention mechanism can accurately and quickly locate the most attractive objects or areas in natural scenes, and the computer forms a saliency detection technology by imitating the principle of this visual attention mechanism. Saliency detection is a key stage in image processing and is widely used in the field of computer vision, including object recognition, video compression, content-based image retrieval, and segmentation of objects of interest in images. Saliency detection algorithms in the field of computer vision can generally be divided into two categories: bottom-up (data-driven) methods and top-down (task-driven) methods. The bottom-up method is based on low-level visual characteristics, such as the color, ...

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): G06T7/00G06T7/11G06T7/90G06V10/46
CPCG06T7/0002G06T7/11G06T7/90G06T2207/20016G06V10/462
Inventor 鲁文超段先华王长宝徐丹
Owner JIANGSU UNIV OF SCI & TECH
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