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

A Sketch Recognition Method and Its Application in Commodity Retrieval

A technology of sketch recognition and sketch, which is applied in the field of sketch recognition that integrates deep learning and semantic tree, can solve time-consuming and difficult problems, achieve the effects of alleviating the semantic gap, improving satisfaction, and meeting retrieval needs

Active Publication Date: 2021-07-30
ANHUI UNIVERSITY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this case, it becomes a time-consuming and difficult task to purchase products that satisfy users

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 Sketch Recognition Method and Its Application in Commodity Retrieval
  • A Sketch Recognition Method and Its Application in Commodity Retrieval
  • A Sketch Recognition Method and Its Application in Commodity Retrieval

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] Example 1: Such as figure 1 , figure 2 and image 3 As shown, the present embodiment will be described in a aircraft sketch, a sketch identification method, including the following steps:

[0030] Get Sketch:

[0031] Specifically, in this embodiment, the user is hand-painted with the grass, and the system is input.

[0032] S2. The system is splitted with semantic information for the acquired sketch:

[0033] Specifically, in the present embodiment, after obtaining the user's hand-drawn sketch image, use the data-driven sketch to divide the algorithm, split the sketch to the stroke layer, and then combine the sequence of strokes as a stroke group, including the sequence of strokes. One-by-one combination; use existing 3D shape libraries, such as 3D Shape Galleries, Shape Repository, etc., the pen painting group is iterative compared with the partial diagram of the 3D shape library, and then utilizes a 3D component label information to 2D stroke group Semantic labeling, get ...

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 sketch recognition method, which comprises the following steps: S1. Obtaining a picture to be processed; S2. Carrying out component segmentation with semantic information on the collected picture to obtain a component diagram of the sketch; S3. Using a deep learning network The model obtains the label of the component by identifying the component graph; S4. Associates the semantic information of the component with the semantic information of the object to which the component belongs; S5. Outputs the label of the object to which the component belongs through the semantic tree. And the application of the sketch recognition method in commodity retrieval, which is characterized in that it includes the following steps: 1) obtaining picture information, 2) the retrieval system uses the sketch recognition method to obtain the label of the item that the user wants to find according to the picture, 3) According to the identified tags, the corresponding products are recommended for users. The invention improves the correct rate of recognition of complete sketches, saves time for users to select commodities, and enhances user experience.

Description

Technical field [0001] The present invention relates to the field of image processing, and more particularly to a sketch recognition method for fusion depth learning and semantic trees. Background technique [0002] With the popularity of the Internet, online shopping has become the preferred consumption method of today's society. Users only need to enter the name of the item on the shopping website, you can pick items, then place an order, that is, the user, reduce shopping costs, It is also convenient for merchants to reduce the central turnover of middlemen. However, the user's way of purchasing goods is limited to the input product name or the input product, and then get a list of recommendations. In real life, in some cases, the user does not know the exact name of the product, and there is no product product photo. There is only one substantially item shape in the mind. In this case, the purchase of the goods to be satisfactory to make a time-consuming and difficult thing. ...

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): G06K9/62G06T7/11G06F16/53G06Q30/06
CPCG06Q30/0603G06T7/11G06T2207/20172G06F18/22
Inventor 赵鹏冯晨成韩莉
Owner ANHUI UNIVERSITY
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