Template image edge point optimization method

A template image and optimization method technology, applied in the field of image processing, can solve problems such as reducing matching speed, matching information redundancy, and inability to improve accuracy.

Active Publication Date: 2021-02-02
易思维(杭州)科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Template matching has its own limitations, and it requires high matching of feature points. In the existing methods, only the edge extraction method is used to obtain the edge points in the template image, and no further processing is performed on the edge points, which will make the template image There are many edge points in the template image, which affect the matching accuracy; at the same time, when the number of edge points in the template image is too large, it will cause redundancy of matching information. In this case, instead of improving the accuracy, the matching speed will be reduced.

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
  • Template image edge point optimization method
  • Template image edge point optimization method
  • Template image edge point optimization method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0024] A method for optimizing edge points of a template image, comprising: selecting a plurality of images to be matched, and extracting edge points in the template image and each image to be matched;

[0025] In this embodiment, a plurality of images to be matched under different situations (different scales, inclination angles) are collected in advance;

[0026] Using the edge point A in the template image i information to match the edge points in each image to be matched, such as figure 1 As shown, find the matching point D in each image to be matched ij And the matching score value S corresponding to each matching point ij ;i represents the i-th edge point, 1≤i≤m, m represents the total number of edge points in the template image; j represents the jth image to be matched, 1≤j≤n, n represents the total number...

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 template image edge point optimization method, and the method comprises the following steps: selecting a plurality of images to be matched, and respectively extracting edge points in a template image and each image to be matched; matching the edge points in each to-be-matched image by utilizing the edge point Ai information in the template image, and finding a matching point Dij and a matching score Sij corresponding to each matching point in each to-be-matched image; calculating the weight Votei of the i-th edge point by using the score value Sij; traversing each edge point, removing the points with the weight values smaller than a preset value, and marking the remaining edge points as optimized template image edge points. According to the method, the edge pointsin the template image are optimized by utilizing the to-be-matched image under various different conditions, and on the basis, the clustering method and the nearest neighbor method are combined, so the edge points which have no influence on the matching precision are removed, and the matching speed is increased.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for optimizing edge points of a template image. Background technique [0002] Template matching is the most primitive and basic pattern recognition method, and it is the most basic and commonly used matching method in image processing. Template matching has its own limitations, and it requires high matching of feature points. In the existing methods, only the edge extraction method is used to obtain the edge points in the template image, and no further processing is performed on the edge points, which will make the template image There are many noise points in the edge points, which affects the matching accuracy; at the same time, when the number of edge points in the template image is too large, it will cause redundancy of matching information, which will not only fail to improve the accuracy but reduce the matching speed. Contents of the invention [0003] For the pr...

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
CPCG06F18/22G06F18/23213
Inventor 尹仕斌郭寅赵进邝丽娜
Owner 易思维(杭州)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