Exploiting features from triangle geometry for digit recognition

Mohd Sanusi Azmi, Mohammad Faidzul Nasrudin, Khairuddin Omar, Che Wan Shamsul Bahri Che Wan Ahmad, Khadijah Wan Mohd Ghazali

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

10 Citations (Scopus)

Abstract

Triangle is a basic geometry. There are six types of triangle, but scalene triangle was chosen to be used in this research which is based on coordinates of corners generated by our proposed algorithm. In this paper, nine features are proposed. Six of the features were derived from coordinates and sides of triangle whereas three others are angle of corners. After features are identified, the image is zoned into 25 zones. The zoning processes are based on Cartesian plan, Vertical and Horizontal zones. From the zoning process, nine features are expanded to become 225 features. The features proposed are used on HODA, MNIST, IFHCDB and BANGLA datasets. Experiments are conducted using supervised learning which are Support Vector Machine (SVM) and Multi-layer Perceptron (MLP). Results from the experiments are evaluated with different Cost (c) for the SVM and Learning Rate (LR) for the MLP. Then, the result is compared to the state of the art researches in this area.

Original languageEnglish
Title of host publication2013 International Conference on Control, Decision and Information Technologies, CoDIT 2013
Pages876-880
Number of pages5
DOIs
Publication statusPublished - 2013
Event2013 International Conference on Control, Decision and Information Technologies, CoDIT 2013 - Hammamet
Duration: 6 May 20138 May 2013

Other

Other2013 International Conference on Control, Decision and Information Technologies, CoDIT 2013
CityHammamet
Period6/5/138/5/13

Fingerprint

Zoning
Multilayer neural networks
Support vector machines
Geometry
Supervised learning
Experiments
Costs
Experiment
Support vector machine

Keywords

  • Dataset
  • Feature extraction
  • Triangle features
  • Zoning

ASJC Scopus subject areas

  • Information Systems and Management
  • Control and Systems Engineering

Cite this

Azmi, M. S., Nasrudin, M. F., Omar, K., Ahmad, C. W. S. B. C. W., & Ghazali, K. W. M. (2013). Exploiting features from triangle geometry for digit recognition. In 2013 International Conference on Control, Decision and Information Technologies, CoDIT 2013 (pp. 876-880). [6689658] https://doi.org/10.1109/CoDIT.2013.6689658

Exploiting features from triangle geometry for digit recognition. / Azmi, Mohd Sanusi; Nasrudin, Mohammad Faidzul; Omar, Khairuddin; Ahmad, Che Wan Shamsul Bahri Che Wan; Ghazali, Khadijah Wan Mohd.

2013 International Conference on Control, Decision and Information Technologies, CoDIT 2013. 2013. p. 876-880 6689658.

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

Azmi, MS, Nasrudin, MF, Omar, K, Ahmad, CWSBCW & Ghazali, KWM 2013, Exploiting features from triangle geometry for digit recognition. in 2013 International Conference on Control, Decision and Information Technologies, CoDIT 2013., 6689658, pp. 876-880, 2013 International Conference on Control, Decision and Information Technologies, CoDIT 2013, Hammamet, 6/5/13. https://doi.org/10.1109/CoDIT.2013.6689658
Azmi MS, Nasrudin MF, Omar K, Ahmad CWSBCW, Ghazali KWM. Exploiting features from triangle geometry for digit recognition. In 2013 International Conference on Control, Decision and Information Technologies, CoDIT 2013. 2013. p. 876-880. 6689658 https://doi.org/10.1109/CoDIT.2013.6689658
Azmi, Mohd Sanusi ; Nasrudin, Mohammad Faidzul ; Omar, Khairuddin ; Ahmad, Che Wan Shamsul Bahri Che Wan ; Ghazali, Khadijah Wan Mohd. / Exploiting features from triangle geometry for digit recognition. 2013 International Conference on Control, Decision and Information Technologies, CoDIT 2013. 2013. pp. 876-880
@inproceedings{00441d65f12b4949a7d50910e3dd57f8,
title = "Exploiting features from triangle geometry for digit recognition",
abstract = "Triangle is a basic geometry. There are six types of triangle, but scalene triangle was chosen to be used in this research which is based on coordinates of corners generated by our proposed algorithm. In this paper, nine features are proposed. Six of the features were derived from coordinates and sides of triangle whereas three others are angle of corners. After features are identified, the image is zoned into 25 zones. The zoning processes are based on Cartesian plan, Vertical and Horizontal zones. From the zoning process, nine features are expanded to become 225 features. The features proposed are used on HODA, MNIST, IFHCDB and BANGLA datasets. Experiments are conducted using supervised learning which are Support Vector Machine (SVM) and Multi-layer Perceptron (MLP). Results from the experiments are evaluated with different Cost (c) for the SVM and Learning Rate (LR) for the MLP. Then, the result is compared to the state of the art researches in this area.",
keywords = "Dataset, Feature extraction, Triangle features, Zoning",
author = "Azmi, {Mohd Sanusi} and Nasrudin, {Mohammad Faidzul} and Khairuddin Omar and Ahmad, {Che Wan Shamsul Bahri Che Wan} and Ghazali, {Khadijah Wan Mohd}",
year = "2013",
doi = "10.1109/CoDIT.2013.6689658",
language = "English",
isbn = "9781424497966",
pages = "876--880",
booktitle = "2013 International Conference on Control, Decision and Information Technologies, CoDIT 2013",

}

TY - GEN

T1 - Exploiting features from triangle geometry for digit recognition

AU - Azmi, Mohd Sanusi

AU - Nasrudin, Mohammad Faidzul

AU - Omar, Khairuddin

AU - Ahmad, Che Wan Shamsul Bahri Che Wan

AU - Ghazali, Khadijah Wan Mohd

PY - 2013

Y1 - 2013

N2 - Triangle is a basic geometry. There are six types of triangle, but scalene triangle was chosen to be used in this research which is based on coordinates of corners generated by our proposed algorithm. In this paper, nine features are proposed. Six of the features were derived from coordinates and sides of triangle whereas three others are angle of corners. After features are identified, the image is zoned into 25 zones. The zoning processes are based on Cartesian plan, Vertical and Horizontal zones. From the zoning process, nine features are expanded to become 225 features. The features proposed are used on HODA, MNIST, IFHCDB and BANGLA datasets. Experiments are conducted using supervised learning which are Support Vector Machine (SVM) and Multi-layer Perceptron (MLP). Results from the experiments are evaluated with different Cost (c) for the SVM and Learning Rate (LR) for the MLP. Then, the result is compared to the state of the art researches in this area.

AB - Triangle is a basic geometry. There are six types of triangle, but scalene triangle was chosen to be used in this research which is based on coordinates of corners generated by our proposed algorithm. In this paper, nine features are proposed. Six of the features were derived from coordinates and sides of triangle whereas three others are angle of corners. After features are identified, the image is zoned into 25 zones. The zoning processes are based on Cartesian plan, Vertical and Horizontal zones. From the zoning process, nine features are expanded to become 225 features. The features proposed are used on HODA, MNIST, IFHCDB and BANGLA datasets. Experiments are conducted using supervised learning which are Support Vector Machine (SVM) and Multi-layer Perceptron (MLP). Results from the experiments are evaluated with different Cost (c) for the SVM and Learning Rate (LR) for the MLP. Then, the result is compared to the state of the art researches in this area.

KW - Dataset

KW - Feature extraction

KW - Triangle features

KW - Zoning

UR - http://www.scopus.com/inward/record.url?scp=84893329570&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893329570&partnerID=8YFLogxK

U2 - 10.1109/CoDIT.2013.6689658

DO - 10.1109/CoDIT.2013.6689658

M3 - Conference contribution

AN - SCOPUS:84893329570

SN - 9781424497966

SP - 876

EP - 880

BT - 2013 International Conference on Control, Decision and Information Technologies, CoDIT 2013

ER -