Graph Learning System for Automatic Image Annotation

K. Aishwaryameenakshi; S. Halima Banu; A. Krishna Priya; S. Chitrakala

Third International conference on advances in communication, network and computing

Research Article

Graph Learning System for Automatic Image Annotation

Download

228 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-642-35615-5_65,
    author={K. Aishwaryameenakshi and S. Halima Banu and A. Krishna Priya and S. Chitrakala},
    title={Graph Learning System for Automatic Image Annotation},
    proceedings={Third International conference on advances in communication, network and computing},
    proceedings_a={CNC},
    year={2012},
    month={12},
    keywords={automatic image annotation graph learning graph link weighting fast solution},
    doi={10.1007/978-3-642-35615-5_65}
}

K. Aishwaryameenakshi
S. Halima Banu
A. Krishna Priya
S. Chitrakala
Year: 2012
Graph Learning System for Automatic Image Annotation
CNC
Springer
DOI: 10.1007/978-3-642-35615-5_65

K. Aishwaryameenakshi¹^,*, S. Halima Banu¹^,*, A. Krishna Priya¹^,*, S. Chitrakala¹^,*

1: Easwari Engineering College

*Contact email: k.aishwaryameenakshi@gmail.com, halimabanu91@gmail.com, priya.gita6@gmail.com, ckgops@gmail.com

Abstract

Automating the process of annotation of images is a crucial step towards efficient and effective management of increasingly high volume of content. A graph-based approach for automatic image annotation is proposed which models both feature similarities and semantic relations in a single graph. The proposed approach models the relationship between the images and words by an undirected graph. Semantic information is extracted from paired nodes. The quality of annotation is enhanced by introducing graph link weighting techniques. The proposed method achieves fast solution by using incremental fast random walk with restart (IFRWR) algorithm, without apparently affecting the accuracy of image annotation.

Keywords: automatic image annotation graph learning graph link weighting fast solution

Published: 2012-12-04

: http://dx.doi.org/10.1007/978-3-642-35615-5_65