Publication detail
Corner Detectors: Evaluation of Information Content
ZUKAL, M. ČÍKA, P.
Original Title
Corner Detectors: Evaluation of Information Content
English Title
Corner Detectors: Evaluation of Information Content
Type
conference paper
Language
en
Original Abstract
This paper aims at the comparison of different corner detectors in terms of information content. Specifically, the FAST, Harris, Harris-Laplace and KLT detector are tested. We prove a hypothesis that the neighborhood of points detected by interest point detectors conveys more information than randomly selected points. The information content was computed from the 8x8 neighborhood of the detected points using entropy. From the qualitative point of view, we have observed that the Harris detector performed best in this measurement and was closely followed by the KLT detector.
English abstract
This paper aims at the comparison of different corner detectors in terms of information content. Specifically, the FAST, Harris, Harris-Laplace and KLT detector are tested. We prove a hypothesis that the neighborhood of points detected by interest point detectors conveys more information than randomly selected points. The information content was computed from the 8x8 neighborhood of the detected points using entropy. From the qualitative point of view, we have observed that the Harris detector performed best in this measurement and was closely followed by the KLT detector.
Keywords
FAST, Harris detector, information content, interest point detector, KLT
RIV year
2012
Released
04.07.2012
ISBN
978-1-4673-1118-2
Book
35th International Conference on Telecommunications and Signal Processing
Edition number
1
Pages from
763
Pages to
767
Pages count
5
Documents
BibTex
@inproceedings{BUT93536,
author="Martin {Zukal} and Petr {Číka}",
title="Corner Detectors: Evaluation of Information Content",
annote="This paper aims at the comparison of different corner detectors in terms of information content. Specifically, the FAST, Harris, Harris-Laplace and KLT detector are tested. We prove a hypothesis that the neighborhood of points detected by interest point detectors conveys more information than randomly selected points. The information content was computed from the 8x8 neighborhood of the detected points using entropy. From the qualitative point of view, we have observed that the Harris detector performed best in this measurement and was closely
followed by the KLT detector.",
booktitle="35th International Conference on Telecommunications and Signal Processing",
chapter="93536",
howpublished="electronic, physical medium",
year="2012",
month="july",
pages="763--767",
type="conference paper"
}