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

Fast template matching algorithm based on gradient integrals

A template matching and gradient technology, applied in computing, computer components, character and pattern recognition, etc., can solve problems such as poor stability and slow speed, and achieve the effects of improving reliability, avoiding repeated operations, and reducing redundancy

Inactive Publication Date: 2018-11-13
GUANGDONG AOPUTE TECH CO LTD
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the existing template matching algorithms use all the information of the template image and calculate the similarity for each position of the image to be detected, which has the problems of slow speed and poor stability under changes in scale, rotation, etc.

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
  • Fast template matching algorithm based on gradient integrals
  • Fast template matching algorithm based on gradient integrals
  • Fast template matching algorithm based on gradient integrals

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] This embodiment provides a fast template matching algorithm based on gradient integration, including the following steps:

[0032] Step 1: Decompose the template image and the target image into an image pyramid, and obtain a series of templates and original images whose resolutions gradually decrease from the bottom to the top of the pyramid. Among them, the image with the largest resolution is referred to as the bottom image, and the image with the smallest resolution is referred to as It is the top image; the minimum resolution template in the template collection contains at least 30 contour points;

[0033] Step 2, calculating the contours of templates at different angles and scales at different resolutions and their corresponding gradients;

[0034] Step 3, calculate the gradient of all pixels in the top image of the original image, and normalize;

[0035] Step 4: Calculate the gradient integral of the top image of the original image according to the size of the to...

Embodiment 2

[0044] This embodiment provides a fast template matching algorithm based on gradient integration, including the following steps:

[0045] Step 1: Decompose the template image and the target image into an image pyramid, and obtain a series of templates and original images whose resolutions gradually decrease from the bottom to the top of the pyramid. Among them, the image with the largest resolution is referred to as the bottom image, and the image with the smallest resolution is referred to as It is the top image; the minimum resolution template in the template collection contains at least 30 contour points;

[0046] Step 2, calculating the contours of templates at different angles and scales at different resolutions and their corresponding gradients;

[0047] Step 3, calculate the gradient of all pixels in the top image of the original image, and normalize;

[0048] Step 4: Calculate the gradient integral of the top image of the original image according to the size of the to...

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, which belongs to the technical field of machine vision image matching, in particular to a fast template matching algorithm based on gradient integrals. The method comprises: carrying out image pyramid calculation on a template image and a target image to obtain templates and original images with different resolutions; extracting contours points and carrying out gradient integrals; carrying out rough matching on templates and sub images; calculating image similarity values and selecting a target position, a target scale and a target direction; and carrying out repeated similaritycalculation and refined matching, and carrying out fitting to obtain a high precision result. Compared with the prior art, the fast template matching algorithm has the following beneficial effects: because of combination of the image pyramid, the extracted contour points and the gradient integral, the redundancy of the data us reduced substantially, lots of repeated operations are avoided, and the computing efficiency is improved; the interference caused by some noise points is eliminated and the computing reliability is improved; and on the basis of the matching strategy from rough matchingto refined matching, the reliability of the result is verified repeatedly and then fitting is carried out to obtain a high-precision result.

Description

technical field [0001] The invention belongs to the technical field of machine vision image matching, in particular to a gradient integral-based fast template matching algorithm. Background technique [0002] Machine vision is the use of machines instead of human eyes for measurement and judgment. The machine vision system refers to converting the ingested target into an image signal through machine vision products, sending it to a dedicated image processing system, and converting it into a digital signal according to pixel distribution, brightness, color and other information; the image system performs various operations on these signals To extract the characteristics of the target, and then control the on-site equipment action according to the result of the discrimination. [0003] In recent years, with the rapid development of the microelectronics industry, machine vision systems with high resolution and high processing speed have been born, which put forward new require...

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): G06K9/62
CPCG06F18/22
Inventor 曹玲卢盛林
Owner GUANGDONG AOPUTE TECH CO LTD