期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2012
卷号：3
期号：2
页码：265-269
语种：English
出版社：Ayushmaan Technologies
摘要：This paper proposed a new simple method of combined DCT feature extraction and shape descriptor that utilize to accelerate the speed and decrease storage needed in image retrieving process by the aim of direct content access and extraction from JPEG compressed domain. Our method first, we normalized and resize the query image by the original database image after the extracts the average of some DCT block coefficients of the image block. The idea of DCT was to decouples the color component of image using YCbCr and transform these into DCT coefficients and measure the similarity of an image with the help of shape descriptor, edge information and morphological operations, to find normalized feature vectors. Now, calculate similarity with combined features of quantized DCT color coefficients and normalized feature vectorts to retrieve an image.
