Comparative Analysis of Keypoint Detection Performance in SIFT Implementations on Small-Scale Image Datasets

arif, rahman and Suprihatin, Karta Comparative Analysis of Keypoint Detection Performance in SIFT Implementations on Small-Scale Image Datasets. Jinita, 6 (2). ISSN 2715-9248

Text 2399-Article Text-11302-1-10-20241227.pdf Download (802kB)

Abstract

Scale-invariant feature transform (SIFT) is widely used as an image local feature extraction method because of its invariance to rotation, scale, and illumination change. SIFT has been implemented in different program libraries. However, studies that analyze the performance of SIFT implementations have not been conducted. This study examines the keypoint extraction of three well-known SIFT libraries, i.e., David Lowe's implementation, OpenSIFT, and vlSIFT in vlfeat. Performance analysis was conducted on multiclass small-scale image datasets to capture the sensitivity of keypoint detection. Although libraries are based on the same algorithm, their performance differs slightly. Regarding execution time and the average number of keypoints detected in each image, vlSIFT outperforms David Lowe’s library and OpenSIFT.

Item Type:	Artikel Umum
Subjects:	Q Science > QA Mathematics > QA76 Computer software
Depositing User:	S.Si., M.Kom Suprihatin Karto
Date Deposited:	08 Feb 2025 04:55
Last Modified:	08 Feb 2025 04:55
URI:	http://eprints.uad.ac.id/id/eprint/80090

Actions (login required)

View Item