文章基本信息

标题：Image Retrieval Based on Combined features of DCT and ShapeDescriptor
本地全文：下载
作者：Arvind Sharma ; Nishchol Mishra
期刊名称：International Journal of Computer Technology and Applications
电子版ISSN：2229-6093
出版年度：2011
卷号：2
期号：4
页码：993-998
出版社：Technopark Publications
摘要：In the image retrieval technology, the aim is to retrieve an image based on combined features of DCT color coefficients and shape descriptor. There were many algorithms based on single feature and combined features, presented in past. Those algorithms have lack of speed and require more computational capability. In this algorithm by combining two features of image, most similar images are retrieved. The idea of DCT was to decouples the color component of image using YCbCr and transform these into DCT coefficients and measure the similarity moreover extract the region based shape descriptor to calculate central moment of an image with the help of edge information and morphological operations to find normalized feature vectors. Now, calculate similarity with combined features of quantized DCT color coefficients and normalized feature vectors to retrieve an image.
关键词：Discrete Cosine Transformation (DCT); Edge detection; Morphological operations; Shape analysis; Central moment.