A low-complexity deformation invariant descriptor

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In this paper, we propose a descriptor which is invariant to general deformations (only intensity locations change but not their value) by using Hilbert scanning. In our method, an image is converted to a 1-D sequence through Hilbert scanning at first. Then, we embed this sequence as a 1-D curve in the 2-D space. Because Hilbert scanning preserves the coherence in a 2-D image, it is easily to understand that the area under the curve is invariant to intensity location changes, naturally. Hence, we use some areas for an interest point as a deformation invariant descriptor. This descriptor can be computed in the 2-D space efficiently than other approaches where an image is embedded in the 3-D space or the dimensions of descriptors are very large. The experimental results show that our descriptor is low-complexity and superior to other approaches on interest point matching in deformation images.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages227-230
Number of pages4
Volume2
DOIs
Publication statusPublished - 2006
Event18th International Conference on Pattern Recognition, ICPR 2006 - Hong Kong
Duration: 2006 Aug 202006 Aug 24

Other

Other18th International Conference on Pattern Recognition, ICPR 2006
CityHong Kong
Period06/8/2006/8/24

Fingerprint

Scanning

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Cite this

Tian, L., & Kamata, S. (2006). A low-complexity deformation invariant descriptor. In Proceedings - International Conference on Pattern Recognition (Vol. 2, pp. 227-230). [1699188] https://doi.org/10.1109/ICPR.2006.91

A low-complexity deformation invariant descriptor. / Tian, Li; Kamata, Seiichiro.

Proceedings - International Conference on Pattern Recognition. Vol. 2 2006. p. 227-230 1699188.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tian, L & Kamata, S 2006, A low-complexity deformation invariant descriptor. in Proceedings - International Conference on Pattern Recognition. vol. 2, 1699188, pp. 227-230, 18th International Conference on Pattern Recognition, ICPR 2006, Hong Kong, 06/8/20. https://doi.org/10.1109/ICPR.2006.91
Tian L, Kamata S. A low-complexity deformation invariant descriptor. In Proceedings - International Conference on Pattern Recognition. Vol. 2. 2006. p. 227-230. 1699188 https://doi.org/10.1109/ICPR.2006.91
Tian, Li ; Kamata, Seiichiro. / A low-complexity deformation invariant descriptor. Proceedings - International Conference on Pattern Recognition. Vol. 2 2006. pp. 227-230
@inproceedings{e54c949d505048bf912f315757aec5db,
title = "A low-complexity deformation invariant descriptor",
abstract = "In this paper, we propose a descriptor which is invariant to general deformations (only intensity locations change but not their value) by using Hilbert scanning. In our method, an image is converted to a 1-D sequence through Hilbert scanning at first. Then, we embed this sequence as a 1-D curve in the 2-D space. Because Hilbert scanning preserves the coherence in a 2-D image, it is easily to understand that the area under the curve is invariant to intensity location changes, naturally. Hence, we use some areas for an interest point as a deformation invariant descriptor. This descriptor can be computed in the 2-D space efficiently than other approaches where an image is embedded in the 3-D space or the dimensions of descriptors are very large. The experimental results show that our descriptor is low-complexity and superior to other approaches on interest point matching in deformation images.",
author = "Li Tian and Seiichiro Kamata",
year = "2006",
doi = "10.1109/ICPR.2006.91",
language = "English",
isbn = "0769525210",
volume = "2",
pages = "227--230",
booktitle = "Proceedings - International Conference on Pattern Recognition",

}

TY - GEN

T1 - A low-complexity deformation invariant descriptor

AU - Tian, Li

AU - Kamata, Seiichiro

PY - 2006

Y1 - 2006

N2 - In this paper, we propose a descriptor which is invariant to general deformations (only intensity locations change but not their value) by using Hilbert scanning. In our method, an image is converted to a 1-D sequence through Hilbert scanning at first. Then, we embed this sequence as a 1-D curve in the 2-D space. Because Hilbert scanning preserves the coherence in a 2-D image, it is easily to understand that the area under the curve is invariant to intensity location changes, naturally. Hence, we use some areas for an interest point as a deformation invariant descriptor. This descriptor can be computed in the 2-D space efficiently than other approaches where an image is embedded in the 3-D space or the dimensions of descriptors are very large. The experimental results show that our descriptor is low-complexity and superior to other approaches on interest point matching in deformation images.

AB - In this paper, we propose a descriptor which is invariant to general deformations (only intensity locations change but not their value) by using Hilbert scanning. In our method, an image is converted to a 1-D sequence through Hilbert scanning at first. Then, we embed this sequence as a 1-D curve in the 2-D space. Because Hilbert scanning preserves the coherence in a 2-D image, it is easily to understand that the area under the curve is invariant to intensity location changes, naturally. Hence, we use some areas for an interest point as a deformation invariant descriptor. This descriptor can be computed in the 2-D space efficiently than other approaches where an image is embedded in the 3-D space or the dimensions of descriptors are very large. The experimental results show that our descriptor is low-complexity and superior to other approaches on interest point matching in deformation images.

UR - http://www.scopus.com/inward/record.url?scp=34047210077&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34047210077&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2006.91

DO - 10.1109/ICPR.2006.91

M3 - Conference contribution

AN - SCOPUS:34047210077

SN - 0769525210

SN - 9780769525211

VL - 2

SP - 227

EP - 230

BT - Proceedings - International Conference on Pattern Recognition

ER -