TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

A comparison of feature detectors and descriptors for object class matching

Tutkimustuotosvertaisarvioitu

Standard

A comparison of feature detectors and descriptors for object class matching. / Hietanen, Antti; Lankinen, Jukka; Kämäräinen, Joni-Kristian; Buch, Anders Glent; Krüger, Norbert.

julkaisussa: Neurocomputing, Vuosikerta 184, 02.12.2015, s. 3-12.

Tutkimustuotosvertaisarvioitu

Harvard

Hietanen, A, Lankinen, J, Kämäräinen, J-K, Buch, AG & Krüger, N 2015, 'A comparison of feature detectors and descriptors for object class matching', Neurocomputing, Vuosikerta. 184, Sivut 3-12. https://doi.org/10.1016/j.neucom.2015.08.106

APA

Vancouver

Author

Hietanen, Antti ; Lankinen, Jukka ; Kämäräinen, Joni-Kristian ; Buch, Anders Glent ; Krüger, Norbert. / A comparison of feature detectors and descriptors for object class matching. Julkaisussa: Neurocomputing. 2015 ; Vuosikerta 184. Sivut 3-12.

Bibtex - Lataa

@article{adff5fcca6414794afdcd0a47e8fa655,
title = "A comparison of feature detectors and descriptors for object class matching",
abstract = "Solid protocols to benchmark local feature detectors and descriptors were introduced by Mikolajczyk et al. [1,2]. The detectors and the descriptors are popular tools in object class matching, but the wide baseline setting in the benchmarks does not correspond to class-level matching where appearance variation can be large. We extend the benchmarks to the class matching setting and evaluate state-of-the-art detectors and descriptors with Caltech and ImageNet classes. Our experiments provide important findings with regard to object class matching: (1) the original SIFT is still the best descriptor; (2) dense sampling outperforms interest point detectors with a clear margin; (3) detectors perform moderately well, but descriptors? performance collapses; (4) using multiple, even a few, best matches instead of the single best has significant effect on the performance; (5) object pose variation degrades dense sampling performance while the best detector (Hessian-affine) is unaffected. The performance of the best detector-descriptor pair is verified in the application of unsupervised visual class alignment where state-of-the-art results are achieved. The findings help to improve the existing detectors and descriptors for which the framework provides an automatic validation tool.",
keywords = "Local descriptor, Local detector, Interest point, SIFT, SURF, BRIEF",
author = "Antti Hietanen and Jukka Lankinen and Joni-Kristian K{\"a}m{\"a}r{\"a}inen and Buch, {Anders Glent} and Norbert Kr{\"u}ger",
year = "2015",
month = "12",
day = "2",
doi = "10.1016/j.neucom.2015.08.106",
language = "English",
volume = "184",
pages = "3--12",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier Science B.V.",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - A comparison of feature detectors and descriptors for object class matching

AU - Hietanen, Antti

AU - Lankinen, Jukka

AU - Kämäräinen, Joni-Kristian

AU - Buch, Anders Glent

AU - Krüger, Norbert

PY - 2015/12/2

Y1 - 2015/12/2

N2 - Solid protocols to benchmark local feature detectors and descriptors were introduced by Mikolajczyk et al. [1,2]. The detectors and the descriptors are popular tools in object class matching, but the wide baseline setting in the benchmarks does not correspond to class-level matching where appearance variation can be large. We extend the benchmarks to the class matching setting and evaluate state-of-the-art detectors and descriptors with Caltech and ImageNet classes. Our experiments provide important findings with regard to object class matching: (1) the original SIFT is still the best descriptor; (2) dense sampling outperforms interest point detectors with a clear margin; (3) detectors perform moderately well, but descriptors? performance collapses; (4) using multiple, even a few, best matches instead of the single best has significant effect on the performance; (5) object pose variation degrades dense sampling performance while the best detector (Hessian-affine) is unaffected. The performance of the best detector-descriptor pair is verified in the application of unsupervised visual class alignment where state-of-the-art results are achieved. The findings help to improve the existing detectors and descriptors for which the framework provides an automatic validation tool.

AB - Solid protocols to benchmark local feature detectors and descriptors were introduced by Mikolajczyk et al. [1,2]. The detectors and the descriptors are popular tools in object class matching, but the wide baseline setting in the benchmarks does not correspond to class-level matching where appearance variation can be large. We extend the benchmarks to the class matching setting and evaluate state-of-the-art detectors and descriptors with Caltech and ImageNet classes. Our experiments provide important findings with regard to object class matching: (1) the original SIFT is still the best descriptor; (2) dense sampling outperforms interest point detectors with a clear margin; (3) detectors perform moderately well, but descriptors? performance collapses; (4) using multiple, even a few, best matches instead of the single best has significant effect on the performance; (5) object pose variation degrades dense sampling performance while the best detector (Hessian-affine) is unaffected. The performance of the best detector-descriptor pair is verified in the application of unsupervised visual class alignment where state-of-the-art results are achieved. The findings help to improve the existing detectors and descriptors for which the framework provides an automatic validation tool.

KW - Local descriptor

KW - Local detector

KW - Interest point

KW - SIFT

KW - SURF

KW - BRIEF

U2 - 10.1016/j.neucom.2015.08.106

DO - 10.1016/j.neucom.2015.08.106

M3 - Article

VL - 184

SP - 3

EP - 12

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -