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

Multi-feature fusion based color image retrieval method for HSV space image retrieval

A multi-feature fusion, color image technology, applied in the field of image processing, can solve the problems of difficult to accurately describe keywords, low retrieval efficiency, time-consuming and labor-consuming, etc., to avoid manual labeling process, improve retrieval efficiency, and enhance practicability. Effect

Inactive Publication Date: 2016-06-01
LIAONING NORMAL UNIVERSITY
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are the following defects: it takes a lot of time and manpower to manually label each image in the database; it is difficult to accurately describe the connotation of images with different contents using keywords; manual selection of keywords will contain strong subjectivity, which may cause problems in image understanding. The deviation directly affects the retrieval effect of the image
There are problems of high computational complexity and low retrieval efficiency

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
  • Multi-feature fusion based color image retrieval method for HSV space image retrieval
  • Multi-feature fusion based color image retrieval method for HSV space image retrieval

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] A kind of color image retrieval method based on the HSV space image retrieval of multi-feature fusion, it is characterized in that carrying out according to following steps:

[0036] Step 1: Convert the color image from RGB space to HSV space to obtain three components of H, S, and V;

[0037] The details are as follows: Assume and represent the image respectively three components, and represent images respectively Three components, the conversion formula from RGB space to HSV space is:

[0038] .

[0039] Using the three grayscale images obtained in HSV space to approximately reconstruct the color image; carry out the stability and correctness test of the three dimensions of the image in HSV space.

[0040] Step 2: Use the non-subsampled Shearlet shear wave to decompose the three components of H, S, and V to obtain subbands of different scales and directions; the details are as follows:

[0041] Step 21: Determine the decomposition coefficient of the no...

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 multi-feature fusion based color image retrieval method for HSV space image retrieval. According to the method, a color image is transferred from an RGB space to an HSV space in the color image retrieval process, a gray-scale image is decomposed by utilizing non-subsample Shearlet shear waves, color histogram feature extraction and texture index spacing amplitude feature extraction are respectively performed by utilizing different scales of sub-bands obtained through decomposition, finally the similarity of different images is calculated by utilizing an Euclidean distance as an image similarity calculating method, and results are sorted and output according to the similarity from big to small. Compared with single color or texture retrieval, the retrieval accuracy is improved to the greatest degree, and accordingly the problem that the ideal image retrieval efficiency cannot be achieved according to individual color features or individual texture features is solved.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a color image retrieval method based on HSV space image retrieval based on multi-feature fusion, which can reduce computational complexity and improve retrieval efficiency. Background technique [0002] The previous image retrieval technology (TBIR) follows the traditional text retrieval technology, which does not consider the inherent color, texture, shape and other content characteristics of the image itself, but uses keywords to describe and retrieve images. There are the following defects: it takes a lot of time and manpower to manually label each image in the database; it is difficult to accurately describe the connotation of images with different contents using keywords; manual selection of keywords will contain strong subjectivity, which may cause problems in image understanding. The deviation directly affects the image retrieval effect. In order to overcome the above defe...

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 Applications(China)
IPC IPC(8): G06F17/30G06K9/46
CPCG06F16/5838G06V10/507
Inventor 杨红颖许娜王向阳牛盼盼
Owner LIAONING NORMAL UNIVERSITY
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