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

Color picture retrieval and classification method

A color image, classification method technology, applied in special data processing applications, instruments, electrical digital data processing, etc., to achieve the effects of good retrieval and classification performance, improved computing efficiency, and strong anti-noise interference ability

Inactive Publication Date: 2017-04-19
YIBIN UNIV
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The method of the present invention aims at the deficiencies of existing image classification and retrieval methods, and proposes a method that considers the correlation of color channels and utilizes Log-Gabor filters to realize image retrieval and classification methods

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
  • Color picture retrieval and classification method
  • Color picture retrieval and classification method
  • Color picture retrieval and classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The method of the present invention will be further described below in conjunction with the drawings. The specific implementation steps are as follows (such as figure 1 Shown):

[0024] Step 1. Use a two-dimensional Log-Gabor filter to decompose the RGB color image on 3 channels in 4 scales and 6 directions respectively, so that a total of 72 Log-Gabor output images (4×6×3) are obtained, called Log -Gabor subband.

[0025] Step 2: Perform a straightening operation on each Log-Gabor subband separately, that is, concatenate the two-dimensional Log-Gabor subbands from top to bottom and from left to right to form a one-dimensional vector (called a subband vector). For Log-Gabor subbands of M rows and N columns, a subband vector of length P (P=M×N) will be generated.

[0026] Step 3. Use Weibull distribution to fit 72 subband vectors respectively. Fitting is to calculate the parameters α and β according to the Weibull distribution on each Log-Gabor subband vector, so that the c...

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 relates to an image retrieval and classification method through a Log-Gabor filter. The method mainly comprises the following steps of 1) utilizing a copula model to capture correlation of Log-Gabor wavelet sub-bands and correlation of a color channel to improve retrieval and classification accuracy, and 2) selecting the Log-Gabor wavelet sub-bands (eliminating redundant sub-bands to improve algorithm precision and reduce calculation time) on the color channel, building one copula model for each color picture to improve calculation efficiency. Compared with the prior art, the color picture retrieval and classification method achieves strong noise interference resistance, great retrieval and classification performance and low calculation complexity.

Description

Technical field [0001] The present invention relates to the field of image retrieval technology and classification, in particular to an image retrieval method using color channel correlation. Background technique [0002] At present, most of the images acquired by image acquisition equipment are color images (RGB images are the most common one), but most of the current image retrieval methods are designed based on grayscale images, that is, color images (such as RGB images) Convert to grayscale image. The disadvantage of classification and retrieval based on the texture information of the gray image is that the color feature of the image is not used, which reduces the recognition accuracy of the algorithm. Commonly used image retrieval and classification methods include discrete wavelet transform (DWT), dual tree wavelet transform (DT-CWT), Gabor wavelet decomposition method, local binary pattern method (LBP) and its extension methods. In order to use color features, the above ...

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): G06F17/30
CPCG06F16/5838
Inventor 李朝荣
Owner YIBIN UNIV
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