Method for extracting target closed contour based on shape prior

A closed contour and target technology, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of no occlusion, illumination robustness, elastic deformation invariance, background noise and internal texture interference, etc.

Inactive Publication Date: 2010-03-17
BEIJING JIAOTONG UNIV
View PDF2 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0018] The problem to be solved by the present invention is to provide a shape prior-based The me

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
  • Method for extracting target closed contour based on shape prior
  • Method for extracting target closed contour based on shape prior
  • Method for extracting target closed contour based on shape prior

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0090] The closed contour extraction of embodiment 1 horse

[0091] First, a salient edge map of the input image is obtained. Its working process is described as follows:

[0092] ①Simulate the complex cells in the human primary visual cortex to extract edge segments with specific frequency and orientation from the input image, and filter the image I with a set of odd-symmetric and even-symmetric Gabor filter banks. figure 2(a) The cell receptive field maps of the human primary visual cortex with odd symmetry and even symmetry are respectively given, and the image of the two-dimensional Gabor function in the spatial domain is similar to this.

[0093] ② Simulate the inhibitory effect in the human primary visual cortex, with a normalized difference of Gaussian filter Responses with complex cells p f，θ to represent the convolution. figure 2 (b) Schematic representation of inhibition of classical receptive fields in human primary visual cortex.

[0094] ③Inhibition is add...

Embodiment 2

[0107] Example 2 The Closed Contour Extraction of Pedestrians

[0108] The only difference between the operation of this embodiment and the first embodiment is that when calculating the similarity between the rough contour in the salient edge map and each template, different sizes are used for the template, ranging from 0.5 times the original size of the template to Take 6 sizes at equal intervals between 2 times, and calculate the similarity between the template and the salient edge map under different zoom sizes, so that the size with the highest similarity (that is, the smallest distance between shapes) is the matching size, and the subsequent steps are all in The matching dimensions are made. This is because the size of the pedestrian in the template may be different from that in the image to be processed, and such preprocessing is to make the present invention have scaling invariance.

[0109] Simulating the information processing mechanism of human vision, integrating s...

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 method for extracting target closed contour based on shape prior, belonging to the field of computer application technology. From the point of view of simitating the information of human vision, the extraction method inhibiting salient edges of noise and texture is adopted, the shape prior is blended on the basis, and a new target closed contour extraction algorithm can be provided by utilizing curve evolution technology based on differential geometry, so that the important technology is provided for automatic target detection. The experiments on a plurality of imagelibraries prove that when the image background is very disordered and has partial shading, and part of the target boundary is indistinct caused by weaker light, the method can obtain the whole targetclosed contour. Simultaneously, when only a few of templates of a certain category of objects are provided, the method can extract the contour of the category of objects with different postures, namely, the method has invariance property for elastic deformation to a certain extent, so as to be directly applied to intelligent image processing. The method can accurately extract the target closed contour and has wide applicability.

Description

technical field [0001] The invention belongs to the field of computer application technology, in particular to a method for extracting a closed contour of a target based on shape prior. Background technique [0002] When people are faced with a strange and complex image, people can quickly and accurately mark the outline of the target. However, when it comes to entrusting a computer with something that is fairly simple for humans, it is not so easy. Without information such as prior knowledge, the computer cannot judge where is the edge, where is the target contour, which is the salient area we want, and which content is redundant noise. Therefore, object contour extraction in complex and irregular images has become a common problem in computer vision. [0003] Extracting the closed contour of the target is one of the ways of target detection and tracking, although some unsupervised methods have achieved local success in images with better imaging conditions (for example: ...

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
Inventor 邹琪
Owner BEIJING JIAOTONG 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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap