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

Method for searching massive clothes images in online manner on basis of stick figure interaction

A technology of sketches and images, applied in the field of online search of massive clothing images based on the interaction of sketches, can solve problems such as gaps, and achieve the effect of reducing difficulty, meeting the needs of commodity purchases, and improving user experience.

Inactive Publication Date: 2014-07-09
HANGZHOU TAOTAOSOU TECH
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to address the deficiencies of the prior art and provide an online search method for massive clothing images based on stick figure interaction, so that users can conveniently and quickly draw the outline of the clothing they need on the smart mobile terminal and obtain similar product information ;Using hand-drawn pattern retrieval can better solve the problem of "user gap", so that users do not need to think about how to express the products they need, but directly obtain the results in a WYSIWYG way

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
  • Method for searching massive clothes images in online manner on basis of stick figure interaction
  • Method for searching massive clothes images in online manner on basis of stick figure interaction
  • Method for searching massive clothes images in online manner on basis of stick figure interaction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be further described below with reference to the accompanying drawings.

[0024] Such as Figure 1-Figure 3 Shown, the present invention a kind of online search method based on the massive commodity image of stick figure interaction, comprises the following steps:

[0025] (1) Preprocessing a large number of product images, including contour extraction, feature point position and gradient direction calculation, and structure tensor calculation;

[0026] In order to better match the hand-painted stick figures, firstly, the edge contour extraction process should be performed on the product image, and then the feature points should be selected in the contour line, and the position and gradient description of the feature points should be obtained. In addition to the description of feature points, it is also necessary to calculate the structure tensor description of the image to improve the matching accuracy. In the present invention, the picture ...

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 method for searching massive clothes images in an online manner on the basis of stick figure interaction. The method has the advantages that feature description and piece quantity description are extracted for massive clothes image searching scenarios, feature indexes and commodity indexes are created, and a query service with a C / S (client / server) framework is created on the basis of the feature indexes and the commodity indexes; a query procedure includes steps of querying the feature indexes to acquire candidate sets and querying and reordering the commodity indexes to feed results, and the query efficiency and the query accuracy can be effectively integrated; drawing operation pages and asynchronous query interfaces are provided for clients, purchasing behavior can be directly generated according to the fed query results, and accordingly searching and purchasing requirements of users can be met.

Description

technical field [0001] The invention relates to the application field of mobile computing platforms, in particular to an online search method for mass clothing images based on stick figure interaction. Background technique [0002] With the development of mobile technology, more and more applications are migrated from traditional PC computers to smart mobile devices. Due to the portability and touch operation of mobile devices, hand-drawing operations can be easily realized. Therefore, combining device characteristics and e-commerce can realize innovative applications for searching and purchasing similar products based on hand-drawn stick figures. [0003] In the field of image retrieval based on sketching, Microsoft Research Asia proposed an image retrieval method based on hand-drawing and annotation in the paper "MindFinder: Image Search by Interactive Sketching and Tagging" published by Microsoft Research Asia in 2010, mainly using hand-drawn outlines , color and text an...

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): G06F17/30
CPCG06F16/951G06Q30/0253
Inventor 林朝辉孙凯张洪鑫
Owner HANGZHOU TAOTAOSOU TECH
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