Unlock instant, AI-driven research and patent intelligence for your innovation.

Matching method based on gradient information

A matching method and gradient information technology, applied to instruments, character and pattern recognition, computer components, etc., can solve problems such as time-consuming, cumbersome process, rotation, scaling, and occlusion

Active Publication Date: 2020-04-28
易思维(杭州)科技有限公司
View PDF10 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Template matching is the process of finding sub-regions similar to the template image in another image according to the template image; The matching images cannot be completely matched. In order to deal with the above template matching problem, the common processing method at this stage is to generate a series of template image sets from angle to angle, and then use each image in the template image set to match the image to be matched during template matching. , this method needs to use multiple templates for matching, and compare them one by one. The process is cumbersome and time-consuming, which greatly limits the application of template matching technology.

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
  • Matching method based on gradient information
  • Matching method based on gradient information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] A matching method based on gradient information, comprising the following steps:

[0043] 1) extract the edge gradient information of the template image, and obtain the amplitude value and gradient direction of each template edge point in the template image; record all template edge points or selected part of the template edge points as a key point set;

[0044] Extract the edge gradient information of the image to be matched, obtain the magnitude value and gradient direction of each edge point in the image to be matched, and record the set of edge points in all images to be matched as the point set to be matched;

[0045] like figure 1As shown, take a single point in the point set to be matched as the center point, determine the neighborhood, and copy the gradient direction corresponding to the center point to other points in the neighborhood; traverse all points in the point set to be matched; set the point to be matched The set composed of the original gradient dire...

Embodiment 2

[0053] In order to prevent the rotation and scaling of the image to be matched from affecting the matching result; in this embodiment, the template image is rotated and scaled, and multiple template images are used for matching. The detection result can not only output the best match in the image to be matched The coordinate position of the pixel point can also output the rotation and scaling information of the image to be matched;

[0054] The technical solution is as follows:

[0055] A matching method based on gradient information, comprising the following steps:

[0056] 1) Extract the edge gradient information of the image to be matched, obtain the magnitude value and gradient direction of each edge point in the image to be matched, and record the set of edge points in all images to be matched as the set of points to be matched;

[0057] like figure 1 As shown, take a single point in the point set to be matched as the center point, determine the neighborhood, and copy t...

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 matching method based on gradient information. The method comprises the steps: extracting the edge gradient information of a template image, and screening a key point set; extracting edge gradient information of the image to be matched; obtaining the gradient direction of the target edge point; obtaining a to-be-matched point set; taking a single point in the to-be-matched point set as a central point, determining a neighborhood, and respectively copying the gradient direction of the central point to other points in the neighborhood; marking a set formed by the gradient directions corresponding to the single points as a set A; traversing all points in the to-be-matched point set to obtain a feature number of each point, recording a maximum value as a matching value, judging whether the matching value is greater than a preset value or not, If not, determining that matching fails; if yes, the specific point in the to-be-matched point set corresponding to the matching value is a matching result, and matching of the to-be-matched image is completed; when the to-be-measured target has the problems of rotation, zooming, shielding and the like, the method has thecharacteristics of high accuracy and good real-time performance.

Description

technical field [0001] The invention relates to the technical field of image positioning and recognition, in particular to a matching method based on gradient information. Background technique [0002] Template matching is the process of finding sub-regions similar to the template image in another image according to the template image; The matching images cannot be completely matched. In order to deal with the above template matching problem, the common processing method at this stage is to generate a series of template image sets from angle to angle, and then use each image in the template image set to match the image to be matched during template matching. , this method needs to use multiple templates for matching, and compare them one by one, the process is cumbersome and time-consuming, which greatly limits the application of template matching technology. Contents of the invention [0003] Using image gradients as geometric features for similarity matching has the abi...

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): G06K9/62G06K9/36G06K9/46
CPCG06V10/248G06V10/20G06V10/44G06F18/22
Inventor 赵进崔鹏飞尹仕斌郭寅
Owner 易思维(杭州)科技有限公司