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

A Cloth Image Retrieval Method Based on Multi-Granularity

An image retrieval, multi-granularity technology, applied in the field of image processing, can solve problems such as the inability to effectively meet the needs of actual image retrieval.

Active Publication Date: 2017-10-27
广州盖特软件有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to propose a cloth image retrieval method based on multi-granularity, which can solve the problem that the actual image retrieval cannot be effectively met

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
  • A Cloth Image Retrieval Method Based on Multi-Granularity
  • A Cloth Image Retrieval Method Based on Multi-Granularity
  • A Cloth Image Retrieval Method Based on Multi-Granularity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] Below, the present invention is further described.

[0059] The specific implementation of this embodiment is carried out under the following conditions:

[0060] A. Test data set: SCC-125 data set (real cloth image data collection with simple color features), the total number of data records is 125×4=500; CCC-125 data set (real cloth image data with complex color features collection), the total number of records is 125×4=500.

[0061] B. Data preprocessing: The data is not normalized and the weight factor is not considered.

[0062] C. Evaluation criteria: Since the experiment is carried out without considering the threshold, the average ranking R is selected a , sorting closeness R q , sorting stability S o , the average query time T a , precision and recall as evaluation criteria.

[0063] The specific implementation steps of the cloth image retrieval method based on multi-granularity in this embodiment are divided into four parts:

[0064] (1) Generate the fe...

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 a multi-granularity-based cloth image retrieval method. According to the method, the granular computing theoretical research is adopted, and characteristic granularities of cloth images can be adjusted flexibly; by means of the method, multi-granularity retrieval can be conducted on the cloth images. Color characteristics and texture characteristics are used for describing the cloth images, meanwhile, three different color combination granularities (the single-main-color color combination granularity, the double-main-color color combination granularity and the three-main-color color combination granularity) are established for the color characteristics, the knowledge granularities in the field of the cloth images are used in cooperation, and therefore the cloth image retrieval method more conforming to human visual perception is realized.

Description

technical field [0001] The invention relates to image processing technology, in particular to a cloth image retrieval method based on multi-granularity. Background technique [0002] Luggage companies need to purchase raw materials frequently and in large quantities, and many fabric supply stores often need to find various fabrics that meet customer needs from a large number of fabric color cards. Using manual methods to compare the fabric color cards that need to be purchased has problems such as time-consuming, labor-intensive, and error-prone. It is easy to cause the raw materials actually needed by the enterprise to be inconsistent with the purchased raw materials, and normal production cannot be carried out, which seriously affects the enterprise. Production efficiency and economic benefits. Simultaneously, also bring a lot of inconveniences to cloth supply store. Therefore, enterprise purchasers and fabric supply stores urgently need a computer application system for...

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): G06F17/30G06T7/90
CPCG06T7/0004G06T7/90G06T2207/30112
Inventor 邱桃荣蔡征兵林美波周石林蔡志芳
Owner 广州盖特软件有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com