Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Image matching method based on local filtering Eigen vector

A feature vector and local filtering technology, applied to computer parts, instruments, character and pattern recognition, etc., can solve the problems of complex extraction of visual saliency models, absolute image grid division, affecting performance and effect, etc., to reduce memory The effect of consumption, removal of information redundancy, and step size

Active Publication Date: 2018-01-09
西安应用光学研究所
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, subsequent further research found that the division of the image grid by this method is too absolute, which may artificially separate some potential feature regions, which is not conducive to the distinction of features; at the same time, the extraction of visual saliency models is complex and requires a large amount of calculation. , affecting the actual performance and effect of the method

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 matching method based on local filtering Eigen vector
  • Image matching method based on local filtering Eigen vector
  • Image matching method based on local filtering Eigen vector

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention is described in further detail below in conjunction with accompanying drawing:

[0047] see figure 1 , the hardware environment used for implementation is: Pentium(R)Dual E2200 2.20GHz 2.19GHz, 1.98GB memory computer, the running software environment is: Windows 2002 and MATLAB R2007b. We have realized the method that the present invention proposes with matlab programming language. The image data set used in the experiment is the Oxford standard data set proposed by Mikolajczyk et al., which contains 8 groups (6 images in each group) with a total of 48 images, including 6 different transformations (view angle change, scale transformation, image rotation, image blur, brightness changes and JPEG compression). Experimental parameter values: sliding window size w L = h L = 32,w M = h M =16,w S =h S = 8; initial step size Smoothness Judgment Threshold δ L =48,δM =24,δ S =12; filter vector dimension Z=64; distance measure weighting coeffici...

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 an image matching method based on a local filtering Eigen vector. According to the method, image local information is extracted in a condition of different scales, an Eigen vector is obtained through Gauss filtering, and binary system binary system features with better comprehensive performance are extracted to conduct image matching. The method includes the steps of conducting multi-scale self-adaptive sliding window Gauss filtering on images, conducting ordering on the basis of the Gauss filtering, cutting off too bright and too dark region segments, generating filtering vectors of the images in a condition of different scales, carrying out amplitude comparison between Harris feature points and the filtering vectors, generating a binary system Eigen vector, and carrying out matching of the image feature points through the Eigen vector.

Description

technical field [0001] The invention relates to the fields of computer vision, image comprehension, pattern recognition and the like, in particular to an image matching method based on local filtering feature vectors. Background technique [0002] Image matching is a basic problem in the field of computer vision and image processing, widely used in robot vision, satellite remote sensing, target recognition and tracking and other fields. The feature point descriptor is an indispensable tool for image registration. However, on embedded devices with limited computing power and storage space, quickly extracting and reasonably representing hundreds or thousands of feature points has always been a major research task. Difficult problems to be solved urgently. [0003] Traditional image matching local feature descriptors such as SIFT and SURF, which are widely used at present, face severe challenges in the application of large-scale multimedia data. Since its feature vector is a ...

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): G06K9/62
Inventor 邹彬李良福钱钧刘培桢陆阳范鹏程刘健鹏周锋飞聂伟乐杨一洲黄西莹宋磊
Owner 西安应用光学研究所
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
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