Edge direction matrixes-based local binary patterns descriptor for invariant pattern recognition

Mohammed Ahmed Talab, Siti Norul Huda Sheikh Abdullah, Mohammad Hakim Assiddiq Razalan

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

1 Citation (Scopus)

Abstract

Invariant descriptor for shape and texture image recognition usage is an essential branch of pattern recognition. It is made up of techniques that aim at extracting information from shape images via human knowledge and works. The descriptors need to have strong Local Binary Pattern (LBP) in order to encode the information distinguishing them. Local Binary Pattern (LBP) ensures encoding global and local information and scaling invariance by introducing a look-up table to reflect the uniformity structure of an object. It is needed as the edge direction matrices (EDMS) only apply global invariant descriptor which employs first and secondary order relationships. The main objective of this paper is the need of improved recognition capabilities which achieved by the combining LBP and EDMS. Working together, these two descriptors will add advantages to the program and enable the researcher to investigate the weaknesses of each one. Two classifiers are used: multi-layer neural network and random forest. The techniques used in this paper are compared with Gray-Level Co-occurrence matrices (GLCM-EDMS) and Scale Invariant Feature Transform (SIFT) by using two benchmark dataset: MPEG-7 CE-Shape-1 for shape and Arabic calligraphy for texture. The experiments have shown the superiority of the introduced descriptor over the GLCM-EDMS and the SIFT.

Original languageEnglish
Title of host publication2013 International Conference on Soft Computing and Pattern Recognition, SoCPaR 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages13-18
Number of pages6
ISBN (Print)9781479934003
DOIs
Publication statusPublished - 3 Mar 2003
Event2013 International Conference on Soft Computing and Pattern Recognition, SoCPaR 2013 - Hanoi, Viet Nam
Duration: 15 Dec 201318 Dec 2013

Other

Other2013 International Conference on Soft Computing and Pattern Recognition, SoCPaR 2013
CountryViet Nam
CityHanoi
Period15/12/1318/12/13

Fingerprint

Pattern recognition
Textures
Mathematical transformations
Image recognition
Multilayer neural networks
Invariance
Classifiers
Experiments

Keywords

  • Classification
  • Edge direction matrixes(EDMS)
  • Feature extraction
  • Local binary patterns(LBP)

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Talab, M. A., Sheikh Abdullah, S. N. H., & Razalan, M. H. A. (2003). Edge direction matrixes-based local binary patterns descriptor for invariant pattern recognition. In 2013 International Conference on Soft Computing and Pattern Recognition, SoCPaR 2013 (pp. 13-18). [7054123] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SOCPAR.2013.7054123

Edge direction matrixes-based local binary patterns descriptor for invariant pattern recognition. / Talab, Mohammed Ahmed; Sheikh Abdullah, Siti Norul Huda; Razalan, Mohammad Hakim Assiddiq.

2013 International Conference on Soft Computing and Pattern Recognition, SoCPaR 2013. Institute of Electrical and Electronics Engineers Inc., 2003. p. 13-18 7054123.

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

Talab, MA, Sheikh Abdullah, SNH & Razalan, MHA 2003, Edge direction matrixes-based local binary patterns descriptor for invariant pattern recognition. in 2013 International Conference on Soft Computing and Pattern Recognition, SoCPaR 2013., 7054123, Institute of Electrical and Electronics Engineers Inc., pp. 13-18, 2013 International Conference on Soft Computing and Pattern Recognition, SoCPaR 2013, Hanoi, Viet Nam, 15/12/13. https://doi.org/10.1109/SOCPAR.2013.7054123
Talab MA, Sheikh Abdullah SNH, Razalan MHA. Edge direction matrixes-based local binary patterns descriptor for invariant pattern recognition. In 2013 International Conference on Soft Computing and Pattern Recognition, SoCPaR 2013. Institute of Electrical and Electronics Engineers Inc. 2003. p. 13-18. 7054123 https://doi.org/10.1109/SOCPAR.2013.7054123
Talab, Mohammed Ahmed ; Sheikh Abdullah, Siti Norul Huda ; Razalan, Mohammad Hakim Assiddiq. / Edge direction matrixes-based local binary patterns descriptor for invariant pattern recognition. 2013 International Conference on Soft Computing and Pattern Recognition, SoCPaR 2013. Institute of Electrical and Electronics Engineers Inc., 2003. pp. 13-18
@inproceedings{869e504fd64b4ea69f436362f64be864,
title = "Edge direction matrixes-based local binary patterns descriptor for invariant pattern recognition",
abstract = "Invariant descriptor for shape and texture image recognition usage is an essential branch of pattern recognition. It is made up of techniques that aim at extracting information from shape images via human knowledge and works. The descriptors need to have strong Local Binary Pattern (LBP) in order to encode the information distinguishing them. Local Binary Pattern (LBP) ensures encoding global and local information and scaling invariance by introducing a look-up table to reflect the uniformity structure of an object. It is needed as the edge direction matrices (EDMS) only apply global invariant descriptor which employs first and secondary order relationships. The main objective of this paper is the need of improved recognition capabilities which achieved by the combining LBP and EDMS. Working together, these two descriptors will add advantages to the program and enable the researcher to investigate the weaknesses of each one. Two classifiers are used: multi-layer neural network and random forest. The techniques used in this paper are compared with Gray-Level Co-occurrence matrices (GLCM-EDMS) and Scale Invariant Feature Transform (SIFT) by using two benchmark dataset: MPEG-7 CE-Shape-1 for shape and Arabic calligraphy for texture. The experiments have shown the superiority of the introduced descriptor over the GLCM-EDMS and the SIFT.",
keywords = "Classification, Edge direction matrixes(EDMS), Feature extraction, Local binary patterns(LBP)",
author = "Talab, {Mohammed Ahmed} and {Sheikh Abdullah}, {Siti Norul Huda} and Razalan, {Mohammad Hakim Assiddiq}",
year = "2003",
month = "3",
day = "3",
doi = "10.1109/SOCPAR.2013.7054123",
language = "English",
isbn = "9781479934003",
pages = "13--18",
booktitle = "2013 International Conference on Soft Computing and Pattern Recognition, SoCPaR 2013",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Edge direction matrixes-based local binary patterns descriptor for invariant pattern recognition

AU - Talab, Mohammed Ahmed

AU - Sheikh Abdullah, Siti Norul Huda

AU - Razalan, Mohammad Hakim Assiddiq

PY - 2003/3/3

Y1 - 2003/3/3

N2 - Invariant descriptor for shape and texture image recognition usage is an essential branch of pattern recognition. It is made up of techniques that aim at extracting information from shape images via human knowledge and works. The descriptors need to have strong Local Binary Pattern (LBP) in order to encode the information distinguishing them. Local Binary Pattern (LBP) ensures encoding global and local information and scaling invariance by introducing a look-up table to reflect the uniformity structure of an object. It is needed as the edge direction matrices (EDMS) only apply global invariant descriptor which employs first and secondary order relationships. The main objective of this paper is the need of improved recognition capabilities which achieved by the combining LBP and EDMS. Working together, these two descriptors will add advantages to the program and enable the researcher to investigate the weaknesses of each one. Two classifiers are used: multi-layer neural network and random forest. The techniques used in this paper are compared with Gray-Level Co-occurrence matrices (GLCM-EDMS) and Scale Invariant Feature Transform (SIFT) by using two benchmark dataset: MPEG-7 CE-Shape-1 for shape and Arabic calligraphy for texture. The experiments have shown the superiority of the introduced descriptor over the GLCM-EDMS and the SIFT.

AB - Invariant descriptor for shape and texture image recognition usage is an essential branch of pattern recognition. It is made up of techniques that aim at extracting information from shape images via human knowledge and works. The descriptors need to have strong Local Binary Pattern (LBP) in order to encode the information distinguishing them. Local Binary Pattern (LBP) ensures encoding global and local information and scaling invariance by introducing a look-up table to reflect the uniformity structure of an object. It is needed as the edge direction matrices (EDMS) only apply global invariant descriptor which employs first and secondary order relationships. The main objective of this paper is the need of improved recognition capabilities which achieved by the combining LBP and EDMS. Working together, these two descriptors will add advantages to the program and enable the researcher to investigate the weaknesses of each one. Two classifiers are used: multi-layer neural network and random forest. The techniques used in this paper are compared with Gray-Level Co-occurrence matrices (GLCM-EDMS) and Scale Invariant Feature Transform (SIFT) by using two benchmark dataset: MPEG-7 CE-Shape-1 for shape and Arabic calligraphy for texture. The experiments have shown the superiority of the introduced descriptor over the GLCM-EDMS and the SIFT.

KW - Classification

KW - Edge direction matrixes(EDMS)

KW - Feature extraction

KW - Local binary patterns(LBP)

UR - http://www.scopus.com/inward/record.url?scp=84949925270&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949925270&partnerID=8YFLogxK

U2 - 10.1109/SOCPAR.2013.7054123

DO - 10.1109/SOCPAR.2013.7054123

M3 - Conference contribution

AN - SCOPUS:84949925270

SN - 9781479934003

SP - 13

EP - 18

BT - 2013 International Conference on Soft Computing and Pattern Recognition, SoCPaR 2013

PB - Institute of Electrical and Electronics Engineers Inc.

ER -