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

Image grey scale and gradient combining improved sift characteristic extracting method

A technology of image grayscale and feature extraction, used in instruments, character and pattern recognition, computer parts, etc.

Inactive Publication Date: 2012-12-26
HANGZHOU TAOTAOSOU TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This deficiency is particularly prominent in the field of image search

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
  • Image grey scale and gradient combining improved sift characteristic extracting method
  • Image grey scale and gradient combining improved sift characteristic extracting method
  • Image grey scale and gradient combining improved sift characteristic extracting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] In the following, an image is used as an input, and the steps of feature extraction are further described in detail in conjunction with the accompanying drawings. For the framework and process of the whole system, see figure 1 shown. For the input image, the sift features of its grayscale and gradient will be calculated separately, and then the features of the two parts will be fused as a new feature vector output.

[0018] Specifically, the present invention combines the improved sift feature extraction method of image grayscale and gradient, comprising the following steps:

[0019] 1. Input image.

[0020] 2. Extract the original sift features of the grayscale image.

[0021] The Sift feature of the image itself has some good characteristics, and we hope to keep this feature in the features we extract, so the sift feature of the original grayscale image will be our basis.

[0022] The extraction of grayscale sift features is as follows figure 2 As shown in , for...

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 grey scale and gradient combining improved sift characteristic extracting method, which is to calculate the sift characteristics of an input image grey level and an input image gradient respectively, fuse the characteristics of the two parts, and output the fused characteristics as a new characteristic vector. The method is an improved image sift characteristic extracting method, is expanded in invariance in the characteristic matching of images similar with inverted color images, and when used for calculating the similarity between two images, can acquire more complete and accurate result; and when used for searching for similar images, the method can find out more results which are more reliable.

Description

technical field [0001] The invention relates to the technical field of image feature extraction, in particular to an improved SIFT feature extraction method which can be accurately and conveniently used for subsequent image matching and combines image grayscale and gradient. Background technique [0002] With the continuous development of image search technology, how to extract local invariant features in two similar images is becoming increasingly important. This feature needs to maintain a certain stability in various changes of the image (including geometric deformation, position, illumination change, etc.). At present, there are many local feature extraction methods, including SIFT, SURF, MSER, etc. Studies have shown that sift is one of the best performance. [0003] The classic sift feature extraction method was proposed by D.G..Lowe in 1999 and perfected in 2004. It is the most widely used and most effective method in the field of feature extraction. It has the fo...

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): G06K9/48
Inventor 王海洋黄琦曾凡涛郑聃
Owner HANGZHOU TAOTAOSOU TECH
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