Automatic large-scale social image annotation algorithm based on inductive matrix completion

A social image and matrix completion technology, applied in the field of large-scale social image automatic labeling algorithms, can solve the problems of missing image labels and noise, and achieve the effect of solving automatic labeling problems.

Inactive Publication Date: 2018-01-16
NANJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to solve the problems of missing and noisy image tags, tagging of newly added images or images without tags, and large-scale application problems, thereby improving the accuracy and scale of automatic tagging of images

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
  • Automatic large-scale social image annotation algorithm based on inductive matrix completion
  • Automatic large-scale social image annotation algorithm based on inductive matrix completion
  • Automatic large-scale social image annotation algorithm based on inductive matrix completion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Embodiments of the present invention will be described below in conjunction with the accompanying drawings. Aiming at the problems of lack of image labels and noise in the prior art, labeling of newly added images or unlabeled images, and large-scale application problems, the present invention introduces the popular inductive matrix completion technology in the field of machine learning on the one hand, and The inherent sparsity of image labels is introduced into the inductive low-rank matrix completion technology, and an inductive low-rank matrix completion algorithm with sparse constraints is proposed to predict or correct missing or noisy image labels, and Newly added images or unlabeled images are effectively marked; on the other hand, parallel multi-block ADMMs are introduced to solve the problem model of the present invention, so as to well solve the problem of large-scale automatic labeling of images. Specific steps include:

[0029] (1) Select a large-scale soc...

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 an automatic large-scale social image annotation algorithm based on inductive matrix completion, and mainly aims at solving the label deficiency and noise containing problems of a large scale of social images to improve the accuracy of automatic image annotation. According to the method, on one hand, automatic annotation is conducted on newly-added images or label-free images by introducing an inductive matrix completion technology; on the other hand, prediction or error correction is conducted on deficient or noise-containing image labels by integrating the low rank performance of an image label matrix with the inherent sparsity of the image label matrix, and therefore the accuracy of image annotation is enhanced; and furthermore, a question model is solved by adopting a popular optimization solving method in machine learning, and therefore large-scale application is achieved. The accuracy and the scalability of image annotation are well improved.

Description

technical field [0001] The invention belongs to the technical field of automatic image labeling in the field of computer technology, and in particular relates to a large-scale social image automatic labeling algorithm based on inductive matrix completion. Background technique [0002] With the rapid development of digital technology and Internet technology, a large number of social multimedia sharing platforms have emerged, and massive image resources are shared by Internet users on these platforms. In such a large-scale image resource, how to effectively manage and query the required resources has become an urgent problem to be solved. In the past few decades, researchers in the computer field have done a lot of research on it from different perspectives. Some of the initial research was on text-based image retrieval, but its image labels required manual labeling, which was time-consuming, labor-intensive, subjectivity and inaccurate; some research was on content-based ima...

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): G06F17/30G06K9/46G06Q50/00
Inventor 陈蕾刘梦迪叶文采周宇轩杨庚戴华
Owner NANJING UNIV OF POSTS & TELECOMM
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