期刊名称：International Journal of Image Processing (IJIP)
电子版ISSN：1985-2304
出版年度：2011
卷号：5
期号：1
页码：1-12
出版社：Computer Science Journals
摘要：Content based image retrieval (CBIR) deals with retrieval of relevant images from the large image database. It works on the features of images extracted. In this paper we are using very innovative idea of sectorization of Full Haar Wavelet transformed images for extracting the features into 4, 8, 12 and 16 sectors. The paper proposes two planes to be sectored i.e. Forward plane (Even plane) and backward plane (Odd plane). Similarity measure is also very essential part of CBIR which lets one to find the closeness of the query image with the database images. We have used two similarity measures namely Euclidean distance (ED) and sum of absolute difference (AD). The overall performance of retrieval of the algorithm has been measured by average precision and recall cross over point and LIRS, LSRR. The paper compares the performance of the methods with respect to type of planes, number of sectors, types of similarity measures and values of LIRS and LSRR.
关键词：CBIR; Haar Wavelet; Euclidian Distance; Sum of Absolute Difference; LIRS and LSRR; Precision and Recall
