Shape Based Features Extracted Using Wavelet Decomposition and Morphological Operators

Padmashree D. Desai, Jagadeesh Pujari, Nagaratna Yaligar

Abstract


Content-Based Image Retrieval (CBIR) allows automatic extraction of target images from a database of images according to objective visual contents of the image itself. Shape, colour and texture represent the visual features of an image. Among all these features shape gains its importance because of its complexity in representation. We propose a novel image retrieval method based on shape features extracted using wavelet decomposition and morphological operators. As edge detection is the fundamental step in identifying the shape of an image, the proposed method uses wavelet decomposition to find the edge map and mathematical morphological operators to obtain better shape features of an image. The proposed technique is tested on Wang’s bench mark image database with 1000 images spread across 10 categories. The average precision and recall of all queries are computed and considered for performance analysis. In all, 50 queries (5 from each category) are fired on the image database. The results show that the methods discussed in this paper overcome the problems existed in traditional methods of edge detection in an image, such as noise- sensitive, no clear boundary etc, and can obtain good effect on edge detection.


Keywords: CBIR; Wavelets; Morphological operators; Edge detection; shape


Full Text:

PDF


DOI: https://doi.org/10.26483/ijarcs.v3i3.1206

Refbacks

  • There are currently no refbacks.




Copyright (c) 2016 International Journal of Advanced Research in Computer Science