Non-standard template image matching method based on tree decomposition

A template image and matching method technology, applied in the field of electronic information, can solve the problem that the template image cannot be processed, and achieve the effect of high practical value, obvious experimental effect and wide adaptability

Inactive Publication Date: 2014-12-31
BEIJING UNIV OF TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can obtain higher accuracy and faster matching speed, but it has a fatal flaw, that is, it can only handle standard template images with equal height and width and a size that is a power of 2. Template images that are powers of 2 will not be able to handle

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
  • Non-standard template image matching method based on tree decomposition
  • Non-standard template image matching method based on tree decomposition
  • Non-standard template image matching method based on tree decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] according to figure 2 Embodiments of the present invention are configured. When the present invention is implemented, it only needs to input the picture to be detected and the template image of content of any size expected to be searched. In a specific embodiment, a template image with a size of 59×29 and an image to be detected with a size of 120×160 (such as figure 1 shown), the steps are as follows:

[0033] Step (1): Read in the template image T, if T is a color image, convert it to a grayscale image, and the converted grayscale image is still represented by T; and calculate the integral map I of T T , the calculation method can use the method of column priority processing, namely

[0034] First perform superposition processing by column: superimpose the pixel values ​​of the first column to the second column, and then superimpose the newly obtained second column value to the third column, and so on until the last column;

[0035] Then superimpose by row: super...

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 non-standard template image matching method based on tree decomposition. The non-standard template image matching method sequentially comprises the following steps of: carrying out primary screening on all candidate windows in a strip type by a method for calculating region characteristic values; then carrying out halving division on the heights and the widths of the candidate windows, and calculating new region characteristic values of the candidate windows by virtue of a last division result; comparing the region characteristic values of the candidate windows with corresponding region characteristic values of template images so as to screen the candidate windows; carrying out the steps until the heights or the widths of the candidate windows cannot be divided any more; and finally, defining the best matched candidate window from the residual candidate windows by a full-search method. In the dividing process, as long as the heights or the widths of a template and the candidate widows can be divided, the dividing treatment is continually performed by the method, so that the method is adapted to the matching of the non-standard template images with different heights and widths. In the dividing process, with the adoption of a region characteristic calculation technology based on the tree decomposition, a large amount of repeated calculation is avoided, so that the matching speed is improved, and the non-standard template image matching method is wider in adaptability.

Description

technical field [0001] The invention relates to a non-standard template image matching method based on tree decomposition, which belongs to the technical field of electronic information. Background technique [0002] Template matching is a method of finding regions in an image to be detected that match a known template. It is widely used in signal processing, computer vision, image and video processing. The most original template matching method is to directly calculate the similarity between the template and all candidate regions of the same size in the image to be detected, and take the candidate region with the largest similarity as the best matching result. But doing so requires a large amount of computation and high time complexity, and the efficiency is very low in practical applications. For this reason, many effective improved methods have been proposed, including the fast template matching method based on orthogonal Haar transform, which uses orthogonal Haar trans...

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 Patents(China)
IPC IPC(8): G06T7/00
Inventor 李玉鑑李厚君谢欢曦
Owner BEIJING UNIV OF TECH
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