Academic Journals Database
Disseminating quality controlled scientific knowledge

Image Representation Using EPANECHNIKOV Density Feature Points Estimator

ADD TO MY LIST
 
Author(s): Tranos Zuva | Seleman M. Ngwira | Sunday O. Ojo | Keneilwe Zuva

Journal: Signal & Image Processing
ISSN 2229-3922

Volume: 4;
Issue: 1;
Start page: 75;
Date: 2013;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Image representation | Segmentation | Visual content | Image retrieval

ABSTRACT
In image retrieval most of the existing visual content based representation methods are usually applicationdependent or non robust, making them not suitable for generic applications. These representation methodsuse visual contents such as colour, texture, shape,size etc. Human image recognition is largely basedonshape, thus making it very appealing for image representation algorithms in computer vision.In this paper we propose a generic image representation algorithm using Epanechnikov Density FeaturePoints Estimator (EDFPE). It is invariant to rotation, scale and translation. The image density featurepoints within defined rectangular rings around thegravitational centre of the image are obtained in theform of a vector. The EDFPE is applied to the vector representation of the image. The Cosine AngleDistance (CAD) algorithm is used to measure similarity of the images in the database. Quantitativeevaluation of the performance of the system and comparison with other algorithms was done
RPA Switzerland

Robotic Process Automation Switzerland

    

Tango Jona
Tangokurs Rapperswil-Jona