Multi-characteristic integrated image matching method

A multi-feature fusion and matching method technology, which is applied in image analysis, image data processing, instruments, etc., can solve the problems of serious time-consuming matching process and excessive calculation amount, achieve speed satisfaction, and solve sensitive problems of spatial position offset Effect

Inactive Publication Date: 2017-10-10
安徽慧视金瞳科技有限公司
View PDF8 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These two types of methods are either sensitive to the position offset of coordinate points, or the amount of calculation is too large, and the matching process takes a lot of time

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-characteristic integrated image matching method
  • Multi-characteristic integrated image matching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Such as figure 1 The image matching method of shown multi-feature fusion is characterized in that, comprises the following steps:

[0051] 1), target image feature preparation: Considering that the target image and the template image are matched, some features will be used. In the present invention, four features of interest points, edges, regions and HOG features are used, so the target image is first interested Point detection, edge extraction, region extraction processing, and the calculation of the gradient direction integral map of the target image complete the target image feature preparation, and obtain interest points, edges, stable regions, and the HOG integral map of the target image as features to be matched, as follows:

[0052] (1) Interest point detection processing: the SUSAN operator is used to detect the interest point of the target image, and the interest point with high precision can be obtained by using the SUSAN operator, and then the interest point i...

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 belongs to the image processing technology field, and more particularly, to a multi-characteristic integrated image matching method, comprising the following steps: 1) processing a targeted image to obtain the characteristics of the interest points, the edges, the regions and the HOG; 2) based on the initial comparison of the HOG characteristics of the targeted image and a template image, selecting a plurality of position regions on the targeted image that match the template image as candidate regions for precise search; 3) performing the matching in each candidate region of the targeted image and recording the matching similarities; 4) integrating the matching similarities at different positions in each candidate region on the targeted image to obtain the general similarity for the different positions of the targeted image; and 5) based on the general similarity, determining the position where the targeted image and the template image match best. According to the invention, the advantage of maximizing the precise description of the local characteristics can be realized, which solves the defect of the sensitivity to spatial position deviation. The algorithm speed can completely meet the real-time requirement.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image matching method of multi-feature fusion. Background technique [0002] Image matching is a common technique in the image processing and computer vision industries, and it is often used in image stitching, target tracking, and image recognition. [0003] Conventional image matching methods are mainly divided into two categories - local matching based on interest points, and similarity calculation based on image blocks. These two types of methods are either sensitive to the positional offset of the coordinate points, or the amount of calculation is too large, and the matching process is time-consuming. Contents of the invention [0004] Aiming at the defects and deficiencies of the prior art, the present invention proposes a multi-feature fusion image matching method. [0005] The technical scheme that the present invention adopts is as follows: ...

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): G06K9/46G06T7/11G06T7/12G06T7/33
CPCG06T7/11G06T7/12G06T7/337G06V10/443G06V10/462
Inventor 汪俊锋邓宏平刘罡戴平
Owner 安徽慧视金瞳科技有限公司
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