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

Clothing electronic tag generation method based on machine vision

A technology of electronic label and machine vision, applied in the field of image processing, to achieve the effect of improving efficiency, easy to use, and reducing time cost

Active Publication Date: 2019-09-03
DONGHUA UNIV
View PDF11 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the gradual enrichment of people's material life, we have more and more diverse clothing, but we lack a technology that can convert clothing into tags and store them in the database

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
  • Clothing electronic tag generation method based on machine vision
  • Clothing electronic tag generation method based on machine vision
  • Clothing electronic tag generation method based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] In order to make the present invention more comprehensible, preferred embodiments are described in detail as follows.

[0014] A method for generating clothing electronic tags based on machine vision provided by the present invention takes the recognition results of clothing characteristics based on computer vision as the main information source, and then uses the main information source as an input to generate similarity for a certain item by constructing a visual matrix similarity. There are multiple possible categories of each characteristic of clothing, and then by means of human-computer interaction, the selection of each possible category in each of these characteristics is used as a deviation correction item, and finally forms a A multi-dimensional clothing electronic tag that can accurately describe any piece of clothing in terms of texture (Attribute-Texture), fabric (Attribute-Fabric), color, style (Attribute-Style), and category (Category) 5 characteristics. ...

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 clothing electronic tag generation method based on machine vision, and the method is characterized by comprising the following steps of building a Fast Net clothing characteristic multi-dimensional prediction network, wherein the Fast Net clothing characteristic multi-dimensional prediction network comprises a forward propagation part and a backward propagation part; training and testing the FastFastNet clothing characteristic multi-dimensional prediction network by using the DeepFastNet data set, wherein the number of the possible categories corresponding to each characteristic is closely related to the matching degree of the prediction result and the characteristic category of the clothes, and selecting two categories with the highest possible correct probability and the original prediction result for a user to select to form the electronic tag of the clothes. According to the technical scheme provided by the invention, the label output of the clothes can be provided for the clothes recommendation system, and meanwhile, the visual similarity matrix under the predicted error input problem is constructed, so that a good label modification way is providedfor the user.

Description

technical field [0001] The present invention outputs the tag feature of clothing through clothing characteristic classification network and FashionNet clothing characteristic multi-dimensional prediction network, belongs to image processing technical field. Background technique [0002] With the gradual enrichment of people's material life, we have more and more diverse clothing, but we lack a technology that can convert clothing into tags and store them in the database after identification. The application of this technology will greatly improve the level of people's management of household and commercial clothing, and further lay the foundation for the intelligent matching recommendation of clothing in the future. Contents of the invention [0003] The purpose of the present invention is: provide a kind of method that after clothing identification is changed into label, make label can be preserved in the database. [0004] In order to achieve the above object, the techn...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/24Y02P90/30
Inventor 高世宇齐洁苏耀斌冯世阳孙浩周雪姚劼王辰吴雨晨杜杰邱玥朱行凯李星仪
Owner DONGHUA 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