Low-dimensional shape index using color feature for Content-based image retrieval

Rohini H. Kale, Dr.S.A. Ladhake


A low-dimensional shape based indexing technique is used for achieving efficient and effective retrieval performance. This paper present a simple index based on shape features of regions that are segmented out of images based on color. A new shape similarity measure conforming to human perception is applied and shown to be effective. Low-level visual features like color, shape, texture, etc are being used for representing and retrieving images in many Content-Based Image Retrieval systems. Generally such methods suffer from the problems of high dimensionality leading to more computational time and inefficient indexing and retrieval performance. Images are segmented to obtain homogeneous color regions that are dominant and similar images form an image cluster stored in a hash structure. Each region within an image is then indexed by a region-based shape index. The shape index is invariant to translation, rotation and scaling. The retrieval performance is studied and compared with that of a region-based shape-indexing scheme.

Keywords: Content-Based Image Retrieval, low-dimensional, Color based image.

Full Text:


DOI: https://doi.org/10.26483/ijarcs.v3i3.1231


  • There are currently no refbacks.

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