Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

An Image Detection Method to Improve Feature Matching Accuracy

A technology of image detection and feature matching, which is applied in the field of medical computers, can solve the problems affecting the real-time performance and long time of SIFT algorithm, and achieve real-time performance, improve matching accuracy, and improve the matching speed

Active Publication Date: 2021-02-02
BEIJING INSTITUTE OF TECHNOLOGYGY +1
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It takes a long time for feature matching, which affects the real-time performance of the SIFT algorithm

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
  • An Image Detection Method to Improve Feature Matching Accuracy
  • An Image Detection Method to Improve Feature Matching Accuracy
  • An Image Detection Method to Improve Feature Matching Accuracy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The specific implementation process of the present invention will be described below in conjunction with the accompanying drawings.

[0044] An image detection method that improves the accuracy of feature matching, the flow chart of the steps is as follows figure 1 shown. Specifically include the following steps.

[0045]Step 1. Use the Roberts operator to filter the image to be detected I(x,y) to generate a Gaussian smooth image; or: select a different scale factor σ, and combine the two-dimensional Gaussian function G(x,y,σ) with the image to be detected The pixels of I(x,y) are convolved to generate a Gaussian smooth image;

[0046] Step 2. Calculate the Gaussian smooth image output in the previous step by using the Gaussian difference scale space function to generate a DOG image;

[0047] Step 3, extracting the feature points of the DOG image, determining its position and scale;

[0048] Step 4. Use Radon transformation to obtain a series of projection images on...

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 an image detection method for improving feature matching precision, and belongs to the technical field of medical computers. The invention improves the SIFT algorithm, and uses the value obtained by Radon transformation of the image to form a feature vector. Using this method, the invention reduces it from 128 dimensions to 24 dimensions, thereby improving the real-time performance of the algorithm. At the same time, in order to improve the matching of feature vectors, the present invention selects two methods for removing false matches, first using structural similarity to roughly remove matching point pairs, and then using the distribution of spatial geometry and its Constraint conditions realize the fine elimination of matching points. On the basis of not affecting the image matching effect, the present invention can not only increase the matching speed, but also improve the matching accuracy and realize real-time performance.

Description

technical field [0001] The invention relates to an image detection method for improving feature matching accuracy, and belongs to the technical field of medical computers. Background technique [0002] After the 20th century, medical image technology has changed rapidly. Medical images can be divided into two types according to the information they provide. One is anatomical structure images, such as CT, MRI, B-ultrasound, etc., which have high pixel resolution and can display detailed anatomical information at a glance. The second is functional images, such as SPECT, PET, etc., which can completely display relevant information of organs, but the pixel resolution is relatively low, and some details of anatomy are powerless. Although these studies on medical images have been of great help, due to the limitations of providing image information, doctors need to combine their experience, spatial conception and speculation to judge the required information when making a diagnosi...

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): G06K9/62G06K9/44
CPCG06V10/34G06V10/751G06F18/22
Inventor 郭树理韩丽娜郝晓亭司全金林辉陈启明刘宏斌刘宏伟刘丝雨
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com