Local reflection symmetry axis extraction method in image based on multi-instance subspace learning

A reflection symmetry and extraction method technology, applied in the field of computer vision, can solve the problems of large sample differences and difficulty in training classifiers

Active Publication Date: 2017-08-29
SHANGHAI UNIV
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] But on the other hand, for more complex problems like extracting symmetry axes, the samples a

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
  • Local reflection symmetry axis extraction method in image based on multi-instance subspace learning
  • Local reflection symmetry axis extraction method in image based on multi-instance subspace learning
  • Local reflection symmetry axis extraction method in image based on multi-instance subspace learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] Such as figure 1 As shown in FIG. 4 , the symmetry axis extraction technology provided by the present invention proposes a new multi-instance learning method, that is, a multi-instance subspace learning method. This method uses partial random projection trees to divide multi-instance features into appropriate subspaces, and then trains classifiers for each subspace to achieve easier and more accurate symmetry axis extraction. It is a new symmetry axis extraction method. . First, for each sample point on the natural image in the training data set, the contour intensity features and self-similarity features are extracted at multiple scales and angles, and merged into a multi-instance feature bag of these sample points, and constructed using the feature bag of positive samples. Partially randomly project the tree, and then assign the negative samples to the appropriate leaf nodes (subspaces) according to the constructed projection rules, train their own classifiers for ea...

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 local reflection symmetry axis extraction method in an image based on multi-instance subspace learning. The method comprises the following steps of 1, acquiring a local image multi-instance characteristic package of a natural image; 2, constructing a stepwise random projection tree; and 3, performing judgment analysis, namely analyzing the multi-instance characteristic package of the natural image of the to-be-extracted symmetry axis and a multi-instance characteristic package in a training data set by means of a subspace classifier, thereby obtaining an analysis result. The local reflection symmetry axis extraction method has advantages of simple and applicable characteristic extraction process, relatively high execution result recall rate and relatively high accuracy.

Description

technical field [0001] The invention belongs to computer vision technology, and relates to a method for extracting local reflection symmetry axes in images based on multi-instance subspace learning. Background technique [0002] Symmetry axis, also known as central axis or skeleton, is an important underlying feature of local images, which can be used to describe the shape of objects in the image. In recent years, it has been widely used in many popular fields such as shape-based object recognition, biomedical image analysis, human body gesture recognition, and motion capture. The symmetry axis is divided into reflection symmetry axis, rotation symmetry axis, translation symmetry axis and so on. The most commonly used one is the reflection symmetry axis, which is the focus of research and application. Hereinafter, the reflection symmetry axis will be referred to as the symmetry axis for short. [0003] At present, most of the symmetry axis extraction methods rely on the eff...

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): G06K9/46G06K9/62
CPCG06V10/44G06F18/24
Inventor 沈为江远白翔张之江
Owner SHANGHAI 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