SITD and across-bin matching for deformed images acquired by scanners

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

5 Citations (Scopus)

Abstract

In this paper, a Shearing Invariant Texture Descriptor (SITD) is presented and the across-bin matching techniques Quadratic Distance (QD) and the Earth Movers Distance (EMD) are used. The shearing and 180° rotation are the main deformations generated during the image acquisition process from the physical paper using scanners. It is very common that a sheet of paper is placed imperfectly on the scanner, whereas the slight rotation is usually not based on the paper geometrical center. The acquired image therefore deformed with irregular rotation which produces a shearing transform. Besides, the image can easily be scanned upside down when the query image is acquired. This problem produces an images deformed with 180° rotation. The SITD is only invariant to the shearing transform and the 180° rotation turning positions of the extracted features. Thus, using the ordinary bin-by-bin matching techniques result in incorrect matches to the corresponding features. Hence, we proposed to use the across-bin matching techniques to perfectly match the features. The experimental results showed the superiority of the SITD along with QD when compared to the benchmark methods Local Binary Pattern (LBP) and Shearing Moment Invariant (SMI) descriptors. Besides, in most cases the QD outperformed the EMD and showed a reasonable performance.

Original languageEnglish
Title of host publicationProceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014
PublisherIEEE Computer Society
Pages14-19
Number of pages6
ISBN (Print)9781479915323
DOIs
Publication statusPublished - 2014
Event2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014 - Kuala Lumpur
Duration: 7 Mar 20149 Mar 2014

Other

Other2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014
CityKuala Lumpur
Period7/3/149/3/14

Fingerprint

Bins
Shearing
Textures
Earth (planet)
Image acquisition

Keywords

  • 180° rotation
  • across-bin matching
  • paper fingerprinting
  • paper scanning
  • shearing deformation
  • SITD

ASJC Scopus subject areas

  • Signal Processing

Cite this

Wahdan, O. M., Nasrudin, M. F., & Omar, K. (2014). SITD and across-bin matching for deformed images acquired by scanners. In Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014 (pp. 14-19). [6805712] IEEE Computer Society. https://doi.org/10.1109/CSPA.2014.6805712

SITD and across-bin matching for deformed images acquired by scanners. / Wahdan, Omar M.; Nasrudin, Mohammad Faidzul; Omar, Khairuddin.

Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014. IEEE Computer Society, 2014. p. 14-19 6805712.

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

Wahdan, OM, Nasrudin, MF & Omar, K 2014, SITD and across-bin matching for deformed images acquired by scanners. in Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014., 6805712, IEEE Computer Society, pp. 14-19, 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014, Kuala Lumpur, 7/3/14. https://doi.org/10.1109/CSPA.2014.6805712
Wahdan OM, Nasrudin MF, Omar K. SITD and across-bin matching for deformed images acquired by scanners. In Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014. IEEE Computer Society. 2014. p. 14-19. 6805712 https://doi.org/10.1109/CSPA.2014.6805712
Wahdan, Omar M. ; Nasrudin, Mohammad Faidzul ; Omar, Khairuddin. / SITD and across-bin matching for deformed images acquired by scanners. Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014. IEEE Computer Society, 2014. pp. 14-19
@inproceedings{c4117c36b85749acacdc6f46beaa92e8,
title = "SITD and across-bin matching for deformed images acquired by scanners",
abstract = "In this paper, a Shearing Invariant Texture Descriptor (SITD) is presented and the across-bin matching techniques Quadratic Distance (QD) and the Earth Movers Distance (EMD) are used. The shearing and 180° rotation are the main deformations generated during the image acquisition process from the physical paper using scanners. It is very common that a sheet of paper is placed imperfectly on the scanner, whereas the slight rotation is usually not based on the paper geometrical center. The acquired image therefore deformed with irregular rotation which produces a shearing transform. Besides, the image can easily be scanned upside down when the query image is acquired. This problem produces an images deformed with 180° rotation. The SITD is only invariant to the shearing transform and the 180° rotation turning positions of the extracted features. Thus, using the ordinary bin-by-bin matching techniques result in incorrect matches to the corresponding features. Hence, we proposed to use the across-bin matching techniques to perfectly match the features. The experimental results showed the superiority of the SITD along with QD when compared to the benchmark methods Local Binary Pattern (LBP) and Shearing Moment Invariant (SMI) descriptors. Besides, in most cases the QD outperformed the EMD and showed a reasonable performance.",
keywords = "180° rotation, across-bin matching, paper fingerprinting, paper scanning, shearing deformation, SITD",
author = "Wahdan, {Omar M.} and Nasrudin, {Mohammad Faidzul} and Khairuddin Omar",
year = "2014",
doi = "10.1109/CSPA.2014.6805712",
language = "English",
isbn = "9781479915323",
pages = "14--19",
booktitle = "Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - SITD and across-bin matching for deformed images acquired by scanners

AU - Wahdan, Omar M.

AU - Nasrudin, Mohammad Faidzul

AU - Omar, Khairuddin

PY - 2014

Y1 - 2014

N2 - In this paper, a Shearing Invariant Texture Descriptor (SITD) is presented and the across-bin matching techniques Quadratic Distance (QD) and the Earth Movers Distance (EMD) are used. The shearing and 180° rotation are the main deformations generated during the image acquisition process from the physical paper using scanners. It is very common that a sheet of paper is placed imperfectly on the scanner, whereas the slight rotation is usually not based on the paper geometrical center. The acquired image therefore deformed with irregular rotation which produces a shearing transform. Besides, the image can easily be scanned upside down when the query image is acquired. This problem produces an images deformed with 180° rotation. The SITD is only invariant to the shearing transform and the 180° rotation turning positions of the extracted features. Thus, using the ordinary bin-by-bin matching techniques result in incorrect matches to the corresponding features. Hence, we proposed to use the across-bin matching techniques to perfectly match the features. The experimental results showed the superiority of the SITD along with QD when compared to the benchmark methods Local Binary Pattern (LBP) and Shearing Moment Invariant (SMI) descriptors. Besides, in most cases the QD outperformed the EMD and showed a reasonable performance.

AB - In this paper, a Shearing Invariant Texture Descriptor (SITD) is presented and the across-bin matching techniques Quadratic Distance (QD) and the Earth Movers Distance (EMD) are used. The shearing and 180° rotation are the main deformations generated during the image acquisition process from the physical paper using scanners. It is very common that a sheet of paper is placed imperfectly on the scanner, whereas the slight rotation is usually not based on the paper geometrical center. The acquired image therefore deformed with irregular rotation which produces a shearing transform. Besides, the image can easily be scanned upside down when the query image is acquired. This problem produces an images deformed with 180° rotation. The SITD is only invariant to the shearing transform and the 180° rotation turning positions of the extracted features. Thus, using the ordinary bin-by-bin matching techniques result in incorrect matches to the corresponding features. Hence, we proposed to use the across-bin matching techniques to perfectly match the features. The experimental results showed the superiority of the SITD along with QD when compared to the benchmark methods Local Binary Pattern (LBP) and Shearing Moment Invariant (SMI) descriptors. Besides, in most cases the QD outperformed the EMD and showed a reasonable performance.

KW - 180° rotation

KW - across-bin matching

KW - paper fingerprinting

KW - paper scanning

KW - shearing deformation

KW - SITD

UR - http://www.scopus.com/inward/record.url?scp=84901650411&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901650411&partnerID=8YFLogxK

U2 - 10.1109/CSPA.2014.6805712

DO - 10.1109/CSPA.2014.6805712

M3 - Conference contribution

AN - SCOPUS:84901650411

SN - 9781479915323

SP - 14

EP - 19

BT - Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014

PB - IEEE Computer Society

ER -