Clothing classification and recommendation method based on image contents

A technology of image content and recommendation method, applied in the field of computer vision, to achieve the effect of increasing accuracy, shortening computing time, and improving efficiency

Active Publication Date: 2016-12-07
KUNMING UNIV OF SCI & TECH
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Currently, many recommender systems only consider recommending outfits that fit specific dress codes

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 classification and recommendation method based on image contents
  • Clothing classification and recommendation method based on image contents
  • Clothing classification and recommendation method based on image contents

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Embodiment 1: as Figure 1-6 As shown, a clothing classification and recommendation method based on image content, including training the classification model on the established face image collection and constructing the basis for clothing recommendation; clothing recommendation is performed on the face images that need clothing recommendation.

[0026] The basis for the described face image set training classification model and construction clothing recommendation includes:

[0027] For the set of face images A={A i The images in ,i=1,...,n} are divided into four categories according to the color theory of the four seasons, and the three positions of skin, hair and pupil of each face image in each category of images are extracted respectively to obtain the hair color , the color data of skin color and pupil color, and the format of the color data is converted into HSV format, and then the color data of hair color, skin color and pupil color converted into HSV format i...

Embodiment 2

[0035] Embodiment 2: as Figure 1-6 As shown, a clothing classification and recommendation method based on image content, including training the classification model on the established face image collection and constructing the basis for clothing recommendation; clothing recommendation is performed on the face images that need clothing recommendation.

[0036] The basis for the described face image set training classification model and construction clothing recommendation includes:

[0037] For the set of face images A={A i The images in ,i=1,...,n} are divided into four categories according to the color theory of the four seasons, and the three positions of skin, hair and pupil of each face image in each category of images are extracted respectively to obtain the hair color , the color data of skin color and pupil color, and the format of the color data is converted into HSV format, and then the color data of hair color, skin color and pupil color converted into HSV format i...

Embodiment 3

[0039] Embodiment 3: as Figure 1-6 As shown, a clothing classification and recommendation method based on image content, including training the classification model on the established face image collection and constructing the basis for clothing recommendation; clothing recommendation is performed on the face images that need clothing recommendation.

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 classification and recommendation method based on image contents and belongs to the field of computer visual technology. According to the invention, the method includes the following steps: conducting training classification modeling on an established face image set and constructing basis for clothing recommendation; recommending clothing to face images that require clothing recommendation. According to the invention, the method is highly accurate, highly efficient and highly personalized. The method, through the introduction of four season color principle, can meet the demands of highly personalization of users. The classification and processing of data sets can increase the efficiency of clothing recommendation. The introduction of an evaluation module can further optimize clothing recommendation computing method in accordance with individual user, and meet custom made demands of the user. The method increases the accuracy of clothing recommendation along with the increasing uses of the method.

Description

technical field [0001] The invention relates to a clothing classification and recommendation method based on image content, belonging to the technical field of computer vision. Background technique [0002] Current technology can recommend clothing to users based on various needs, but it still lacks accuracy. Reasons for the lack of accuracy include the growing variety of clothing and the immaturity of the technology in the field. Currently, many recommender systems only consider recommending clothing collocations that fit a particular dress code. Liu (<ACM international conference>, 2012) proposed a "Magic Wardrobe" system based on a unified latent SVM framework to learn a clothing recommendation model. This latent model consists of four aspects: 1) visual feature-to-attribute, 2) visual feature-to-scene, 3) attribute-to-scene, and 4) attribute-to-attribute. The first three items belong to the connection between clothing and scenes, and the last item belongs to the...

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): G06K9/00G06K9/62G06F17/30G06Q30/02
CPCG06F16/583G06F16/5838G06Q30/0271G06V40/16G06V40/168G06V40/172G06F18/23G06F18/214
Inventor 王安琪刘骊付晓东黄青松刘利军
Owner KUNMING UNIV OF SCI & TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap