|
ABSTRACT
Title |
: |
EVALUATION OF CBIR APPROACHES FOR DIFFERENTLY SIZED IMAGES |
Authors |
: |
Vaibhav Gupta, Dr Anil Ramawat |
Keywords |
: |
Image Retrieval, Image Size, Color Histogram, Correlation |
Issue Date |
: |
January 2012. |
Abstract |
: |
CBIR is the application of computer vision techniques to the image retrieval problem, that is, the problem of searching for digital images in large databases. An experimental comparison of a number of different color descriptors for evaluation of CBIR approaches for differently sized images is presented in this paper. Color descriptors are considered for retrieval. The primary goal is to determine which approach is most efficient in representing the similarity of color images which are not same in size, though their aspect ratio is same. In this paper, we present the comparison of different color descriptors. For the purpose we have used Global Color Histogram (GCH), Local Color Histogram (LCH) and Color average. Publicly available image database is used and the retrieval performance of the features is analyzed in detail. The work is concluded by stating which method performs well. |
Page(s) |
: |
40-44 |
ISSN |
: |
0975–3397 |
Source |
: |
Vol. 4, Issue.01 |
|