Title: Feature-based selection of image retrieval method for content-based geometrical images

Authors: Nisha S. Pathur; V.S. Thangarasu; Krishnamurthi Ilango

Addresses: Department of Computer Science and Engineering, Nehru Institute of Technology, 641105 Coimbatore, India ' Department of Mechanical Engineering, Nehru Institute of Engineering and Technology, 641105 Coimbatore, India ' Department of Computer Science and Engineering, Sri Krishna College of Engineering and Technology, 641008 Coimbatore, India

Abstract: Many areas of science, technology and business use large number of images for various applications of engineering. Searching and locating an image inside a large image database of digital images is considered to be tedious and time consuming and at times lacks accuracy. This paper proposes newly designed enhanced image retrieval algorithm to reduce the searching time and to increase the accuracy up to the maximum extent (up to 96%) using low level features like colour, shape, texture. The new algorithm lists the outcomes, based on relevance factor and narrow downs the search process of digital CAD images for engineering design applications like modifications of existing design and new conceptual designs based on CAD-based digital images for CAE applications.

Keywords: geometrical image retrieval; colour; shape; texture; automatic annotation; relevance factor; feature selection; content-based images; digital images; CAE; CAD images; engineering design.

DOI: 10.1504/IJISCM.2016.080826

International Journal of Information Systems and Change Management, 2016 Vol.8 No.3, pp.211 - 220

Received: 03 May 2016
Accepted: 15 Sep 2016

Published online: 08 Dec 2016 *

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