The improbability of Harris interest points

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

The improbability of Harris interest points. / Loog, Marco; Lauze, Francois Bernard.

I: IEEE Transaction on Pattern Analysis and Machine Intelligence, Bind 32, Nr. 6, 2010, s. 1141-1147.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Loog, M & Lauze, FB 2010, 'The improbability of Harris interest points', IEEE Transaction on Pattern Analysis and Machine Intelligence, bind 32, nr. 6, s. 1141-1147. https://doi.org/10.1109/TPAMI.2010.53

APA

Loog, M., & Lauze, F. B. (2010). The improbability of Harris interest points. IEEE Transaction on Pattern Analysis and Machine Intelligence, 32(6), 1141-1147. https://doi.org/10.1109/TPAMI.2010.53

Vancouver

Loog M, Lauze FB. The improbability of Harris interest points. IEEE Transaction on Pattern Analysis and Machine Intelligence. 2010;32(6):1141-1147. https://doi.org/10.1109/TPAMI.2010.53

Author

Loog, Marco ; Lauze, Francois Bernard. / The improbability of Harris interest points. I: IEEE Transaction on Pattern Analysis and Machine Intelligence. 2010 ; Bind 32, Nr. 6. s. 1141-1147.

Bibtex

@article{88b389205c0a11df928f000ea68e967b,
title = "The improbability of Harris interest points",
abstract = "An elementary characterization of the map underlying Harris corners, also known as Harris interest points or key points, is provided. Two principal and basic assumptions made are: 1) Local image structure is captured in an uncommitted way, simply using weighted raw image values around every image location to describe the local image information, and 2) the lower the probability of observing the image structure present in a particular point, the more salient, or interesting, this position is, i.e., saliency is related to how uncommon it is to see a certain image structure, how surprising it is. Through the latter assumption, the axiomatization proposed makes a sound link between image saliency in computer vision on the one hand and, on the other, computational models of preattentive human visual perception, where exactly the same definition of saliency has been proposed. Because of this link, the characterization provides a compelling case in favor of Harris interest points over other approaches.",
keywords = "Faculty of Science",
author = "Marco Loog and Lauze, {Francois Bernard}",
year = "2010",
doi = "10.1109/TPAMI.2010.53",
language = "English",
volume = "32",
pages = "1141--1147",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "Institute of Electrical and Electronics Engineers",
number = "6",

}

RIS

TY - JOUR

T1 - The improbability of Harris interest points

AU - Loog, Marco

AU - Lauze, Francois Bernard

PY - 2010

Y1 - 2010

N2 - An elementary characterization of the map underlying Harris corners, also known as Harris interest points or key points, is provided. Two principal and basic assumptions made are: 1) Local image structure is captured in an uncommitted way, simply using weighted raw image values around every image location to describe the local image information, and 2) the lower the probability of observing the image structure present in a particular point, the more salient, or interesting, this position is, i.e., saliency is related to how uncommon it is to see a certain image structure, how surprising it is. Through the latter assumption, the axiomatization proposed makes a sound link between image saliency in computer vision on the one hand and, on the other, computational models of preattentive human visual perception, where exactly the same definition of saliency has been proposed. Because of this link, the characterization provides a compelling case in favor of Harris interest points over other approaches.

AB - An elementary characterization of the map underlying Harris corners, also known as Harris interest points or key points, is provided. Two principal and basic assumptions made are: 1) Local image structure is captured in an uncommitted way, simply using weighted raw image values around every image location to describe the local image information, and 2) the lower the probability of observing the image structure present in a particular point, the more salient, or interesting, this position is, i.e., saliency is related to how uncommon it is to see a certain image structure, how surprising it is. Through the latter assumption, the axiomatization proposed makes a sound link between image saliency in computer vision on the one hand and, on the other, computational models of preattentive human visual perception, where exactly the same definition of saliency has been proposed. Because of this link, the characterization provides a compelling case in favor of Harris interest points over other approaches.

KW - Faculty of Science

U2 - 10.1109/TPAMI.2010.53

DO - 10.1109/TPAMI.2010.53

M3 - Journal article

C2 - 20431138

VL - 32

SP - 1141

EP - 1147

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 6

ER -

ID: 19662576