Academic Journals Database
Disseminating quality controlled scientific knowledge

An Approach for Classification of Preprocessed Textures Based On Boundary Moments

Author(s): Dr. M. Rama Bai

Journal: International Journal of Engineering and Advanced Technology
ISSN 2249-8958

Volume: 2;
Issue: 5;
Start page: 286;
Date: 2013;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Image classification | shape representation | morphological operation | Hu moment invariants | boundary extraction | preprocessing techniques | structuring element.

Texture classification is one of the problems which have been paid much attention on by image processing scientists. Consequently, many different methods have been proposed to solve this problem. In most of these methods the researchers attempted to describe and discriminate textures based on linear and non-linear patterns. The present paper describes a novel and effective method of shape classification by combining innovative preprocessing techniques, morphological boundary method and Hu moments. To offer better classification rate, first innovative preprocessing methods are applied on various texture images. Preprocessing mechanisms describe various methods of converting a grey level image into binary image with minimal consideration of the noise model. Then shape features are evaluated using HM by suitable numerical characterization derived from moment invariant measures on the proposed Morphological Boundary(MB) method for a precise classification. This proposed MB derives a new shape descriptor to address the image classification problem by combining boundary extraction and Hu moment(HM) invariants information. A good comparison is made between these methods by combining preprocessing techniques, boundary extraction and Hu moments. This texture classification study using MB and HM has given a good performance. The experimental results clearly show the efficacy of the present method.
Affiliate Program      Why do you need a reservation system?