Fast image retrieval method based on HASH algorithm of SIFT

An image and fast technology, applied in computing, computer components, special data processing applications, etc., can solve problems such as cumbersome steps and non-real-time performance, and achieve the effects of reducing storage space, improving retrieval efficiency, and speeding up retrieval speed

Pending Publication Date: 2018-06-19
NANJING UNIV OF INFORMATION SCI & TECH
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method uses Hamming distance to simplify matching when quer

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 image retrieval method based on HASH algorithm of SIFT
  • Fast image retrieval method based on HASH algorithm of SIFT
  • Fast image retrieval method based on HASH algorithm of SIFT

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0023] Example

[0024] See attached figure 1 , A fast image retrieval method based on SIFT's HASH algorithm, including the following steps.

[0025] Step S1: preprocessing the template image and the query image to obtain an adjusted image;

[0026] The template image is a large number of images placed in a folder in advance. If the template image is a color image, the template image must first be converted into a grayscale image. Then adjust the resolution of the grayscale image obtained after the conversion to 240x320, which can avoid generating a large number of SIFT key point descriptors, which will greatly reduce the matching time.

[0027] Step S2: Extract the SIFT key point descriptors of the preprocessed template image and query image respectively; key points can also be called feature points or interest points, generally corner points, which means that the magnitude and direction of a gradient change quickly The pixels of, using sift program code, including:

[0028] Step S2...

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 fast image retrieval method based on the HASH algorithm of the SIFT. The HASH algorithm of a binaryzation SIFT key point descriptor is adopted. Firstly, an image file is pre-built for preprocessing a template image, a key point descriptor of the template image is obtained, binaryzation is conducted, and the binaryzation SIFT key point descriptor is stored as a HASH address code; secondly, similar operation is conducted on a query image to obtain the HASH address code of the query image, according to the address code, the same address code is searched in a template image base, then the Hamming distance between the SIFT key point descriptor of the query image and the SIFT key point descriptor of the template image is calculated, according to the Hamming distance, the similarity of matching of the SIFT key point descriptors of the query image and the template image is judged, and the image high in similarity is returned. The method can speed up the retrieval of similar features, reduce data storage space and improve the retrieval efficiency of a query, and can be applied in real time.

Description

technical field [0001] The invention relates to the technical field of image retrieval, in particular to a fast image retrieval method based on the SIFT HASH algorithm. Background technique [0002] Today's society has entered the information age. With the development of computer technology and communication technology, image information processing capabilities are also constantly improving, and people's attention to this is also increasing accordingly. Image matching is a key technology in image processing, which can be widely used in target object recognition, face recognition, change detection, parking lot license plate recognition and other fields. The SIFT (Scale Invariant Feature Transform) algorithm was proposed by Lowe, which is suitable for image matching. This algorithm realizes image matching by extracting the SIFT features of the image, and has good stability, uniqueness, multiplicity, and scalability. Performance. However, when the SIFT algorithm is applied to...

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): G06F17/30G06K9/46
CPCG06F16/583G06V10/462
Inventor 张闯杨咸兆徐齐全
Owner NANJING UNIV OF INFORMATION SCI & 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