A completed modeling of shearing and half rotation invariant texture descriptor for deformed images acquired by scanners

Omar M. Wahdan, Dimitri Androutsos, Mohammad Faidzul Nasrudin

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

Abstract

In this paper, a completed modeling of Shearing Invariant Texture Descriptor (SITD) is proposed and half-rotation (180° rotation) invariant features are achieved for scanners texture images applications. The main deformations generated during the image acquisition process from physical paper using flatbed scanners are shearing and half-rotation. It's very common that a sheet of paper is slightly rotated on the scanner. The acquired image is therefore deformed with irregular rotation, which produces a shearing transform. Furthermore, the image can easily be scanned upside down when the query image is acquired. This problem produces an image deformed with 180° rotation. Recently, by decomposing image local patterns into sign and magnitude components, the authors proposed the SITD only based on the first component. In this paper, we proposed a generalization approach called the Completed SITD (CSITD) employs to extract additional discrimination features based on the second component and concatenate them with their complementary from the SITD. The CSITD is however invariant only to the shearing deformation. To achieve the half-rotation invariance, a new method developed to maintain the sequence of the features of CSITD. The experimental results based on real paper texture images showed that the half-rotation invariant features of SITD (RSITD) achieved 98.1%, which is superior over the tested state-of-the-art descriptors. Implementing the half-rotation invariant method with CSITD features (CRSITD) exhibited an improvement over the RSITD with 1.9%.

Original languageEnglish
Title of host publicationISCAIE 2017 - 2017 IEEE Symposium on Computer Applications and Industrial Electronics
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages17-21
Number of pages5
ISBN (Electronic)9781509047529
DOIs
Publication statusPublished - 18 Oct 2017
Event2017 IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2017 - Langkawi Island, Malaysia
Duration: 24 Apr 201725 Apr 2017

Other

Other2017 IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2017
CountryMalaysia
CityLangkawi Island
Period24/4/1725/4/17

Fingerprint

shearing
Shearing
scanners
textures
Textures
Image acquisition
Invariance
discrimination
invariance
acquisition

Keywords

  • Completed modeling
  • Image acquisition
  • LBP
  • Shear rotation invariant descriptor
  • SITD

ASJC Scopus subject areas

  • Instrumentation
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering

Cite this

Wahdan, O. M., Androutsos, D., & Nasrudin, M. F. (2017). A completed modeling of shearing and half rotation invariant texture descriptor for deformed images acquired by scanners. In ISCAIE 2017 - 2017 IEEE Symposium on Computer Applications and Industrial Electronics (pp. 17-21). [8074942] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAIE.2017.8074942

A completed modeling of shearing and half rotation invariant texture descriptor for deformed images acquired by scanners. / Wahdan, Omar M.; Androutsos, Dimitri; Nasrudin, Mohammad Faidzul.

ISCAIE 2017 - 2017 IEEE Symposium on Computer Applications and Industrial Electronics. Institute of Electrical and Electronics Engineers Inc., 2017. p. 17-21 8074942.

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

Wahdan, OM, Androutsos, D & Nasrudin, MF 2017, A completed modeling of shearing and half rotation invariant texture descriptor for deformed images acquired by scanners. in ISCAIE 2017 - 2017 IEEE Symposium on Computer Applications and Industrial Electronics., 8074942, Institute of Electrical and Electronics Engineers Inc., pp. 17-21, 2017 IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2017, Langkawi Island, Malaysia, 24/4/17. https://doi.org/10.1109/ISCAIE.2017.8074942
Wahdan OM, Androutsos D, Nasrudin MF. A completed modeling of shearing and half rotation invariant texture descriptor for deformed images acquired by scanners. In ISCAIE 2017 - 2017 IEEE Symposium on Computer Applications and Industrial Electronics. Institute of Electrical and Electronics Engineers Inc. 2017. p. 17-21. 8074942 https://doi.org/10.1109/ISCAIE.2017.8074942
Wahdan, Omar M. ; Androutsos, Dimitri ; Nasrudin, Mohammad Faidzul. / A completed modeling of shearing and half rotation invariant texture descriptor for deformed images acquired by scanners. ISCAIE 2017 - 2017 IEEE Symposium on Computer Applications and Industrial Electronics. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 17-21
@inproceedings{50cfb3d779424178b307d7c06850e08d,
title = "A completed modeling of shearing and half rotation invariant texture descriptor for deformed images acquired by scanners",
abstract = "In this paper, a completed modeling of Shearing Invariant Texture Descriptor (SITD) is proposed and half-rotation (180° rotation) invariant features are achieved for scanners texture images applications. The main deformations generated during the image acquisition process from physical paper using flatbed scanners are shearing and half-rotation. It's very common that a sheet of paper is slightly rotated on the scanner. The acquired image is therefore deformed with irregular rotation, which produces a shearing transform. Furthermore, the image can easily be scanned upside down when the query image is acquired. This problem produces an image deformed with 180° rotation. Recently, by decomposing image local patterns into sign and magnitude components, the authors proposed the SITD only based on the first component. In this paper, we proposed a generalization approach called the Completed SITD (CSITD) employs to extract additional discrimination features based on the second component and concatenate them with their complementary from the SITD. The CSITD is however invariant only to the shearing deformation. To achieve the half-rotation invariance, a new method developed to maintain the sequence of the features of CSITD. The experimental results based on real paper texture images showed that the half-rotation invariant features of SITD (RSITD) achieved 98.1{\%}, which is superior over the tested state-of-the-art descriptors. Implementing the half-rotation invariant method with CSITD features (CRSITD) exhibited an improvement over the RSITD with 1.9{\%}.",
keywords = "Completed modeling, Image acquisition, LBP, Shear rotation invariant descriptor, SITD",
author = "Wahdan, {Omar M.} and Dimitri Androutsos and Nasrudin, {Mohammad Faidzul}",
year = "2017",
month = "10",
day = "18",
doi = "10.1109/ISCAIE.2017.8074942",
language = "English",
pages = "17--21",
booktitle = "ISCAIE 2017 - 2017 IEEE Symposium on Computer Applications and Industrial Electronics",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A completed modeling of shearing and half rotation invariant texture descriptor for deformed images acquired by scanners

AU - Wahdan, Omar M.

AU - Androutsos, Dimitri

AU - Nasrudin, Mohammad Faidzul

PY - 2017/10/18

Y1 - 2017/10/18

N2 - In this paper, a completed modeling of Shearing Invariant Texture Descriptor (SITD) is proposed and half-rotation (180° rotation) invariant features are achieved for scanners texture images applications. The main deformations generated during the image acquisition process from physical paper using flatbed scanners are shearing and half-rotation. It's very common that a sheet of paper is slightly rotated on the scanner. The acquired image is therefore deformed with irregular rotation, which produces a shearing transform. Furthermore, the image can easily be scanned upside down when the query image is acquired. This problem produces an image deformed with 180° rotation. Recently, by decomposing image local patterns into sign and magnitude components, the authors proposed the SITD only based on the first component. In this paper, we proposed a generalization approach called the Completed SITD (CSITD) employs to extract additional discrimination features based on the second component and concatenate them with their complementary from the SITD. The CSITD is however invariant only to the shearing deformation. To achieve the half-rotation invariance, a new method developed to maintain the sequence of the features of CSITD. The experimental results based on real paper texture images showed that the half-rotation invariant features of SITD (RSITD) achieved 98.1%, which is superior over the tested state-of-the-art descriptors. Implementing the half-rotation invariant method with CSITD features (CRSITD) exhibited an improvement over the RSITD with 1.9%.

AB - In this paper, a completed modeling of Shearing Invariant Texture Descriptor (SITD) is proposed and half-rotation (180° rotation) invariant features are achieved for scanners texture images applications. The main deformations generated during the image acquisition process from physical paper using flatbed scanners are shearing and half-rotation. It's very common that a sheet of paper is slightly rotated on the scanner. The acquired image is therefore deformed with irregular rotation, which produces a shearing transform. Furthermore, the image can easily be scanned upside down when the query image is acquired. This problem produces an image deformed with 180° rotation. Recently, by decomposing image local patterns into sign and magnitude components, the authors proposed the SITD only based on the first component. In this paper, we proposed a generalization approach called the Completed SITD (CSITD) employs to extract additional discrimination features based on the second component and concatenate them with their complementary from the SITD. The CSITD is however invariant only to the shearing deformation. To achieve the half-rotation invariance, a new method developed to maintain the sequence of the features of CSITD. The experimental results based on real paper texture images showed that the half-rotation invariant features of SITD (RSITD) achieved 98.1%, which is superior over the tested state-of-the-art descriptors. Implementing the half-rotation invariant method with CSITD features (CRSITD) exhibited an improvement over the RSITD with 1.9%.

KW - Completed modeling

KW - Image acquisition

KW - LBP

KW - Shear rotation invariant descriptor

KW - SITD

UR - http://www.scopus.com/inward/record.url?scp=85040021211&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040021211&partnerID=8YFLogxK

U2 - 10.1109/ISCAIE.2017.8074942

DO - 10.1109/ISCAIE.2017.8074942

M3 - Conference contribution

SP - 17

EP - 21

BT - ISCAIE 2017 - 2017 IEEE Symposium on Computer Applications and Industrial Electronics

PB - Institute of Electrical and Electronics Engineers Inc.

ER -