Commodity image semantic annotation method based on domain ontology

A product image and domain ontology technology, applied in the field of natural language processing, can solve problems such as difficulty in directly extracting semantic information from product images and image description texts, lack of annotations on product images, etc., and achieve optimal labeling effects

Inactive Publication Date: 2018-09-14
EAST CHINA NORMAL UNIV
View PDF3 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Aiming at the problems in the prior art, the purpose of the present invention is to provide a method for semantic labeling of commodity images based on domain ontology, which can correctly and quickly semantically label commodity images, and solve the problem of lack of labeling of commodity images and the difficulty of direct extraction of commodity images and image description texts Technical Problems of Semantic Information

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
  • Commodity image semantic annotation method based on domain ontology
  • Commodity image semantic annotation method based on domain ontology
  • Commodity image semantic annotation method based on domain ontology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals denote the same or similar structures in the drawings, and thus their repeated descriptions will be omitted.

[0061] Such as figure 1 As shown, in order to solve the problem that the semantic information contained in the product image and its image description text is weak, the embodiment of the present invention provides a method for semantic labeling of product images based on domain ontology. The image is semantically tagged, and the method specifically includes the following steps:

[0062] S100: Using the domain ontology concep...

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 provides a commodity image semantic annotation method based on the domain ontology. The method comprises steps that multiple domain ontology concepts are employed as keywords to capturecommodity data; corresponding image description texts are classified based on each domain ontology concept, and category annotation of the corresponding commodity images is carried out according to the categories of the image description texts; attribute annotation of the corresponding commodity images is carried out. The method is advantaged in that correct and rapid semantic annotation of the commodity images can be realized, a problem that the commodity images do not match the description texts is solved, the partial semantic information of the commodity images in the predetermined domain can be acquired according to the concept and concept attributes of the domain ontology, semantic level annotation of the commodity images is realized, and the correct semantic annotation data set is acquired; the crowdsourcing technology is utilized to acquire the correct image annotation data, the iterative processing mode is employed to most reasonably utilize a crowdsourcing platform at the least cost, and the relatively good annotation result is achieved.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a method for semantically labeling commodity images based on domain ontology for correct and fast semantic labeling of commodity images. Background technique [0002] In recent years, with the rapid development of multimedia technology and the Internet, the number of electronic images has grown rapidly. The Internet has also become an important means for people to shop, so the classified management of commodity images in the e-commerce field is particularly important. If there is no good classification management, it will cause great trouble for users when searching for related products. Therefore, how to realize the rapid and effective management of commodity images in the field of e-commerce has become a hot research topic today. [0003] In the past few decades, there has been a lot of research on content-based image management, but it is limited by seman...

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): G06K9/62G06F17/30
CPCG06F18/23213G06F18/24147
Inventor 杨静朱寒婷
Owner EAST CHINA NORMAL UNIV
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