Image annotationlabeling method based on regional context relation deep learning

A technology of image annotation and deep learning, which is applied in the field of automatic learning of image features and pattern recognition, can solve the problem that deep features cannot effectively express object structure information, and achieve the effect of improving quality

Inactive Publication Date: 2020-02-04
ZHENGZHOU UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the purpose of the present invention is to provide an automatic image labeling method that fuses the contextual relationship of the image area to solve the problem that the depth feature cannot effectively express the structural information of the object. Deep features to improve image annotation performance

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
  • Image annotationlabeling method based on regional context relation deep learning
  • Image annotationlabeling method based on regional context relation deep learning
  • Image annotationlabeling method based on regional context relation deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0048] The present invention provides an automatic image labeling method based on deep learning of image region context relations, such as figure 1 As shown, in the process of automatic image tagging machine learning, only relying on the morphological features of the object, ignoring the structural information of the object in the image, and the semantic interpretation and tagging effect of complex objects are not ideal, a contextual relationship between image regions is proposed The deep learning framework and its parameter optimization method automatically update the relationship between the image grids through the end-to-end structure, learn the internal structure with different semantics, and integrate the structural relationship into the extraction of deep features to enhance the discrimination ability of features , to improve the performance of se...

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 an image annotation method for regional context deep learning, and aims to solve the problem that most of current universal image annotation methods are based on visual features, especially depth features of images, but when semantic keywords needing to be annotated are more and scattered, complex image annotation cannot be effectively solved only by means of the visual features. The invention provides an image annotation method based on thea regional context relation deep learning network. The method comprises the steps of automatically learning a context relationshipbetween regions in an image, fusing the context relationship into feature expression of the regions, accumulating features of the regions to serve as features of the image, and finally learning a multi-class support vector machine to perform semantic recognition on each image and sort contribution values of semantics to obtain annotation keywords. The method is flexible and convenient, can automatically learn the regional context relation of the image while achieving the image labeling, and is higher in practicality.

Description

technical field [0001] The invention relates to the fields of automatic learning of image features and pattern recognition, in particular to a method for learning deep features of image context perception and semantically annotating images. Background technique [0002] With the popularization of consumer electronics such as computers and the rapid development of Internet technology, the number of images in social media networks has increased geometrically, and a large number of images pose severe challenges to tasks such as data retrieval and classification. Quickly understanding images is an important prerequisite for content monitoring and management of network images, and image annotation, as a key technology for image understanding, has attracted more and more attention and research. [0003] Image annotation is a method for describing image content, and its purpose is to describe an image with one or more semantic keywords. Due to the high cost of manually labeling im...

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): G06K9/62G06K9/46G06N3/04G06N3/08
CPCG06N3/084G06V10/40G06N3/045G06F18/2411
Inventor 酒明远齐林陈恩庆马龙靳少辉
Owner ZHENGZHOU 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