Title: SIASRO: Semantic Image Annotation System for building Relationship among Objects

Authors: G. Sureshkumar, R. Baskaran, M. Sathya

Addresses: Department of Computer Science, Pondicherry University, Pondicherry 605 014, India. ' DCSE, Anna University, Chennai 600 025, India. ' Department of Computer Science, Pondicherry University, Pondicherry 605 014, India

Abstract: In this paper, we extended our previous work for annotating multi-object images and to build real semantic descriptions. Our proposed system ||Semantic Image Annotation System for building Relationship among Objects (SIASRO)|| is capable to annotate multi-object images and to identify the natural semantic relation based on the position and arrangements of the objects. In this paper, we proposed a novel image segmentation algorithm ||Enhanced Region Growing and Labelling|| for extracting the individual objects present in the image and its colour. Experimental results show that, the proposed framework is suitable for annotating multi-object images with semantic description.

Keywords: semantic image annotation; SVM; support vector machines; object relations; enhanced region growing; multi-object images; image segmentation; semantics.

DOI: 10.1504/IJSISE.2009.033723

International Journal of Signal and Imaging Systems Engineering, 2009 Vol.2 No.3, pp.109 - 116

Received: 24 Jul 2008
Accepted: 12 May 2009
Published online: 29 Jun 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article