Supercharge Your Innovation With Domain-Expert AI Agents!

An Image Retrieval Method Based on Corner Descriptor

An image retrieval and descriptor technology, which is applied in still image data retrieval, image analysis, image enhancement, etc. Effect

Active Publication Date: 2020-05-29
XIDIAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

After decades of development, image retrieval technology has made great progress, and there are some practical results, but now there is a big gap between the query results of the image retrieval system and human cognitive judgment, and the accuracy rate of similar queries is still not human. satisfy

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 Retrieval Method Based on Corner Descriptor
  • An Image Retrieval Method Based on Corner Descriptor
  • An Image Retrieval Method Based on Corner Descriptor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The technical solutions and effects of the present invention will be described in further detail below with reference to the accompanying drawings.

[0033] The realization steps of the present invention are as follows:

[0034] Step 1, input query image I 0 and the target image database S.

[0035] Step 2, corner detection. After binarizing the query image and the image in the image database, extract the edge and filter it, and use the method based on the maximum value of the edge curvature to detect the corner point; for the query image I 0 Detect the corner points and get the corner point set P of the query image 0 ={P 0l},l=1,2,...,m, for any image I in the image database S j (j=1,2,…,k) detect the corners and get I j The set of corner points P j ={P jv}, v=1,2,...,n, where m, n are I 0 and I j The number of corner points; (orange is the added content)

[0036] (2.1) Edge extraction. Perform a binarization operation on the image and extract the edge curv...

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 retrieval method based on an angular point descriptor. Angular points are matched by extraction of local neighbourhood features and space position features of image angular points, and the accuracy is high in an image retrieval experiment. The method comprises the following steps: (1) carrying out binarization processing on retrieved images and images of a database; (2) respectively detecting angular points of inquired images and the images of the database; (3) fusing local distribution features LSD and global distribution features GSD which are extracted from the angular points; (4) carrying out angular point matching; and (5) returning a retrieval result according to an angular point matching degree. By the angular point description method, the robustness is high in similar image matching; and the image retrieval accuracy is high.

Description

technical field [0001] The invention belongs to the technical field of image retrieval, in particular to an image retrieval method based on corner descriptors. Background technique [0002] With the development of multimedia technology and the advent of the era of big data, image data has exploded, and images have become an important carrier for data acquisition and information exchange in today's society. How to quickly and effectively organize and retrieve image information from a huge network image database has become an increasingly issues of increasing concern. Image retrieval technology has a wide range of application scenarios, such as product search, icon deduplication, trademark registration, face retrieval, medical image retrieval, etc., and has important research significance. [0003] Image retrieval is generally realized by extracting visual features such as color, shape, and texture of the image, and searching and retrieving images with similar image features ...

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): G06F16/583G06F16/56G06T7/00
CPCG06F16/56G06F16/583G06T7/0002G06T2207/20164
Inventor 钟桦刘剑英
Owner XIDIAN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More