文章基本信息

标题：CBIR through CDH using Query by Group
本地全文：下载
作者：Anjali Sharma ; Ajay Kr. Singh
期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2015
卷号：28
期号：1
页码：21-27
DOI：10.14445/22312803/IJCTT-V28P106
出版社：Seventh Sense Research Group
摘要：In recent years we have seen a great pace in the research related to contentbased image retrieval. This paper presents a technique for image retrieval based on the color and edge orientation as the significant features for retrieval of similar images. The paper uses a form of Histogram known as Color Difference Histogram (CDH), which may be regarded as an improved version of a MultiTexton Histogram (MTH). The given histogram is different from the other existing histograms as it does not count the frequency of the number of pixels. The main essence of CDH is that it takes into account the perceptually uniform color difference between two points under different background in accordance with the color and the edge orientations. Here, both the color and texture based features are employed in a single algorithm to get better performance. In order to achieve the perceptual color difference, we exploit the L*a*b color space. The following color space removes the drawbacks of the most commonly used color space of retrieval purposes such as RGB color space as its components are highly correlated. Further in this paper we extend the concept of Query by example to QueryByGroup.
关键词：Image retrieval; CDH; L*a*b colorspace; Query by example and Query by Group