Japanese / English

Detail of Publication

Text Language Japanese
Authors Masakazu Iwamura, Tomohiro Nakai, and Koichi Kise
Title Analysis on Image Retrieval Method Based on Arrangements of Feature Points —Comparison of Geometric Hashing and LLAH—
Journal Trans. IEICE
Vol. J93-D
No. 4
Pages pp.494-501
Reviewed or not Reviewed
Month & Year April 2010
Abstract For an image described with feature points, how do we search the identical arrangement of feature points? The image may be affected by perspective distortion and the arrangement may be not completely identical due to replacement, insert and deletion of feature points. As methods to solve the problem, Geometric Hashing (GH) and Locally Likely Arrangement Hashing (LLAH) are known. Both of them can search efficiently, however, LLAH outperforms GH in computational cost and memory amount. In this paper, we reveal the reason by comparing two methods.
URL http://search.ieice.org/bin/summary.php?id=j93-d_4_494
Back to list