Fabric image retrieval method of locally invariant texture feature based on geometrical shape

A technology of texture features and local invariance, which is applied in the directions of image conversion, image enhancement, image analysis, etc., which can solve the problems of low retrieval efficiency and achieve good translation and robust retrieval effects

Active Publication Date: 2018-09-28
ZHENGZHOU UNIVERSITY OF LIGHT INDUSTRY
View PDF9 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the deficiencies in the prior art, and propose a fabric image retrieval method based on local invariant texture features of geometric shapes, which conforms to the visual perception mechanism of the human eye, and has good translation, rotation, and scaling invariance And contrast invariance, and good noise resistance, high accuracy, so as to solve the problems of fabric image management 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
  • Fabric image retrieval method of locally invariant texture feature based on geometrical shape
  • Fabric image retrieval method of locally invariant texture feature based on geometrical shape
  • Fabric image retrieval method of locally invariant texture feature based on geometrical shape

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to further illustrate the technical means adopted by the present invention and its effects, a detailed description is given below.

[0031] The scheme of the present invention mainly includes the following three parts: (1) topographic map representation of fabric images; (2) local invariant texture feature extraction based on geometric shapes; (3) similarity measurement of fabric image feature vectors. The implementation details of these parts are described in detail below:

[0032] 1. Topographic representation of fabric images

[0033] According to different application purposes, images can have different expressions. For image deblurring, image restoration, image denoising and other purposes, it is more appropriate to express images based on frequency model Fourier transform and wavelet theory. But from the perspective of image analysis, these expressions are not so easy to accept, because the wavelet is not translation invariant, and the Fourier transform...

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 fabric image retrieval method of a locally invariant texture feature based on a geometrical shape, comprising the following steps: 1, offline generating an index structure ofa fabric image database; 2, forming a user query: extracting a locally invariant texture feature based on the geometrical shape of a sample fabric image input via the user, and forming a query that the index database can be retrieved, wherein the step of extracting the locally invariant texture feature based on the geometrical shape is implemented according to the following steps: (1) conversionto a grayscale texture; (2) topographic map expression of the fabric image; (3) feature extraction: one is local expression of the image texture feature, the second one is an expression of structuralrelationship between nodes, and the third one is using a shape contrast feature to remove the influence of local contrast on features; (4) statistical expression of features; 3, calculating similarity, and outputting the result. The fabric image retrieval method provided by the invention proposes a locally invariant texture feature based on the geometrical shape, and the fabric image can be effectively retrieved by using the feature.

Description

technical field [0001] The invention relates to the field of computer multimedia information retrieval, in particular to a fabric image retrieval method based on local invariant texture features of geometric shapes. Background technique [0002] Textile and clothing are one of the most basic needs for human survival. my country is a major textile production and export country, and it is also the world's largest clothing consumer and producer. The textile industry is a traditional pillar industry of my country's national economy, an important livelihood industry and an industry with obvious international competitive advantages. With the rapid development of the textile industry, fabrics and other products as the main textile products are showing a continuous growth trend. The ensuing problem is how to use computers to organize, manage and effectively search the increasing fabrics. Especially important for fabric dealers, clothing industry, etc. For the clothing industry, fa...

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): G06F17/30G06T7/41G06T3/00G06T3/40G06K9/62G06T5/40G06T5/50
CPCG06T3/0006G06T3/40G06T5/40G06T5/50G06T7/41G06T2207/30124G06T2207/10024G06F18/22
Inventor 李玉华武丰龙陈明雷浩鹏黄艳马欢梁树军孙玉胜
Owner ZHENGZHOU UNIVERSITY OF LIGHT INDUSTRY
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