文章基本信息

标题：Image Representation Using EPANECHNIKOV Density Feature Points Estimator
本地全文：下载
作者：Tranos Zuva ; Keneilwe Zuva ; Sunday O. Ojo 等
期刊名称：Signal & Image Processing : An International Journal (SIPIJ)
印刷版ISSN：2229-3922
电子版ISSN：0976-710X
出版年度：2013
卷号：4
期号：1
页码：75
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：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 based onshape, 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 the gravitational 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.
关键词：Image representation; Segmentation; Visual content; Image retrieval