An Advanced Particle Swarm Optimization Based Feature Selection Method for Tri-script Handwritten Digit Recognition

Suryadipto Sarkar, Manosij Ghosh, Agneet Chatterjee, Samir Malakar, Ram Sarkar

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

Abstract

Handwritten digit recognition is a well-studied pattern recognition problem. Most of the techniques, reported in the literature, have been concentrated on designing several feature vectors which represent the digits in a better way. But, at times, such attempt not only increases the dimensionality of extracted feature vector but also suffers from having irrelevant and/or redundant features. To address this, in the present work, a recently introduced Particle Swarm Optimization (PSO) based feature selection method has been applied with suitable modifications. For the course of this experiment, we have confined ourselves to a newly employed feature vector for handwritten digit recognition, namely DAISY feature descriptor. The proposed feature selection method is tested on three handwritten digit databases written in Bangla, Devanagari and Roman scripts. The experimental results show that significant amount of feature dimension is reduced without compromising on recognition accuracy. Comparison of the present feature selection method with two of its ancestors also reveals that the present method outperforms the others.

Original languageEnglish
Title of host publicationComputational Intelligence, Communications, and Business Analytics - 2nd International Conference, CICBA 2018, Revised Selected Papers
EditorsSomnath Mukhopadhyay, Paramartha Dutta, Jyotsna Kumar Mandal, Kousik Dasgupta
PublisherSpringer Verlag
Pages82-94
Number of pages13
ISBN (Print)9789811385773
DOIs
Publication statusPublished - 01-01-2019
Externally publishedYes
Event2nd International Conference on Computational Intelligence, Communication, and Business Analytics, CICBA 2018 - Kalyani, India
Duration: 27-07-201828-07-2018

Publication series

NameCommunications in Computer and Information Science
Volume1030
ISSN (Print)1865-0929

Conference

Conference2nd International Conference on Computational Intelligence, Communication, and Business Analytics, CICBA 2018
CountryIndia
CityKalyani
Period27-07-1828-07-18

Fingerprint

Handwritten Digit Recognition
Feature Selection
Particle swarm optimization (PSO)
Particle Swarm Optimization
Feature extraction
Feature Vector
Digit
Pattern recognition
Descriptors
Pattern Recognition
Dimensionality
Experimental Results
Experiments
Experiment

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Mathematics(all)

Cite this

Sarkar, S., Ghosh, M., Chatterjee, A., Malakar, S., & Sarkar, R. (2019). An Advanced Particle Swarm Optimization Based Feature Selection Method for Tri-script Handwritten Digit Recognition. In S. Mukhopadhyay, P. Dutta, J. K. Mandal, & K. Dasgupta (Eds.), Computational Intelligence, Communications, and Business Analytics - 2nd International Conference, CICBA 2018, Revised Selected Papers (pp. 82-94). (Communications in Computer and Information Science; Vol. 1030). Springer Verlag. https://doi.org/10.1007/978-981-13-8578-0_7
Sarkar, Suryadipto ; Ghosh, Manosij ; Chatterjee, Agneet ; Malakar, Samir ; Sarkar, Ram. / An Advanced Particle Swarm Optimization Based Feature Selection Method for Tri-script Handwritten Digit Recognition. Computational Intelligence, Communications, and Business Analytics - 2nd International Conference, CICBA 2018, Revised Selected Papers. editor / Somnath Mukhopadhyay ; Paramartha Dutta ; Jyotsna Kumar Mandal ; Kousik Dasgupta. Springer Verlag, 2019. pp. 82-94 (Communications in Computer and Information Science).
@inproceedings{d75e952fe10346b5af11f22cc7400b0a,
title = "An Advanced Particle Swarm Optimization Based Feature Selection Method for Tri-script Handwritten Digit Recognition",
abstract = "Handwritten digit recognition is a well-studied pattern recognition problem. Most of the techniques, reported in the literature, have been concentrated on designing several feature vectors which represent the digits in a better way. But, at times, such attempt not only increases the dimensionality of extracted feature vector but also suffers from having irrelevant and/or redundant features. To address this, in the present work, a recently introduced Particle Swarm Optimization (PSO) based feature selection method has been applied with suitable modifications. For the course of this experiment, we have confined ourselves to a newly employed feature vector for handwritten digit recognition, namely DAISY feature descriptor. The proposed feature selection method is tested on three handwritten digit databases written in Bangla, Devanagari and Roman scripts. The experimental results show that significant amount of feature dimension is reduced without compromising on recognition accuracy. Comparison of the present feature selection method with two of its ancestors also reveals that the present method outperforms the others.",
author = "Suryadipto Sarkar and Manosij Ghosh and Agneet Chatterjee and Samir Malakar and Ram Sarkar",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-981-13-8578-0_7",
language = "English",
isbn = "9789811385773",
series = "Communications in Computer and Information Science",
publisher = "Springer Verlag",
pages = "82--94",
editor = "Somnath Mukhopadhyay and Paramartha Dutta and Mandal, {Jyotsna Kumar} and Kousik Dasgupta",
booktitle = "Computational Intelligence, Communications, and Business Analytics - 2nd International Conference, CICBA 2018, Revised Selected Papers",
address = "Germany",

}

Sarkar, S, Ghosh, M, Chatterjee, A, Malakar, S & Sarkar, R 2019, An Advanced Particle Swarm Optimization Based Feature Selection Method for Tri-script Handwritten Digit Recognition. in S Mukhopadhyay, P Dutta, JK Mandal & K Dasgupta (eds), Computational Intelligence, Communications, and Business Analytics - 2nd International Conference, CICBA 2018, Revised Selected Papers. Communications in Computer and Information Science, vol. 1030, Springer Verlag, pp. 82-94, 2nd International Conference on Computational Intelligence, Communication, and Business Analytics, CICBA 2018, Kalyani, India, 27-07-18. https://doi.org/10.1007/978-981-13-8578-0_7

An Advanced Particle Swarm Optimization Based Feature Selection Method for Tri-script Handwritten Digit Recognition. / Sarkar, Suryadipto; Ghosh, Manosij; Chatterjee, Agneet; Malakar, Samir; Sarkar, Ram.

Computational Intelligence, Communications, and Business Analytics - 2nd International Conference, CICBA 2018, Revised Selected Papers. ed. / Somnath Mukhopadhyay; Paramartha Dutta; Jyotsna Kumar Mandal; Kousik Dasgupta. Springer Verlag, 2019. p. 82-94 (Communications in Computer and Information Science; Vol. 1030).

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

TY - GEN

T1 - An Advanced Particle Swarm Optimization Based Feature Selection Method for Tri-script Handwritten Digit Recognition

AU - Sarkar, Suryadipto

AU - Ghosh, Manosij

AU - Chatterjee, Agneet

AU - Malakar, Samir

AU - Sarkar, Ram

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Handwritten digit recognition is a well-studied pattern recognition problem. Most of the techniques, reported in the literature, have been concentrated on designing several feature vectors which represent the digits in a better way. But, at times, such attempt not only increases the dimensionality of extracted feature vector but also suffers from having irrelevant and/or redundant features. To address this, in the present work, a recently introduced Particle Swarm Optimization (PSO) based feature selection method has been applied with suitable modifications. For the course of this experiment, we have confined ourselves to a newly employed feature vector for handwritten digit recognition, namely DAISY feature descriptor. The proposed feature selection method is tested on three handwritten digit databases written in Bangla, Devanagari and Roman scripts. The experimental results show that significant amount of feature dimension is reduced without compromising on recognition accuracy. Comparison of the present feature selection method with two of its ancestors also reveals that the present method outperforms the others.

AB - Handwritten digit recognition is a well-studied pattern recognition problem. Most of the techniques, reported in the literature, have been concentrated on designing several feature vectors which represent the digits in a better way. But, at times, such attempt not only increases the dimensionality of extracted feature vector but also suffers from having irrelevant and/or redundant features. To address this, in the present work, a recently introduced Particle Swarm Optimization (PSO) based feature selection method has been applied with suitable modifications. For the course of this experiment, we have confined ourselves to a newly employed feature vector for handwritten digit recognition, namely DAISY feature descriptor. The proposed feature selection method is tested on three handwritten digit databases written in Bangla, Devanagari and Roman scripts. The experimental results show that significant amount of feature dimension is reduced without compromising on recognition accuracy. Comparison of the present feature selection method with two of its ancestors also reveals that the present method outperforms the others.

UR - http://www.scopus.com/inward/record.url?scp=85068661343&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068661343&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-8578-0_7

DO - 10.1007/978-981-13-8578-0_7

M3 - Conference contribution

AN - SCOPUS:85068661343

SN - 9789811385773

T3 - Communications in Computer and Information Science

SP - 82

EP - 94

BT - Computational Intelligence, Communications, and Business Analytics - 2nd International Conference, CICBA 2018, Revised Selected Papers

A2 - Mukhopadhyay, Somnath

A2 - Dutta, Paramartha

A2 - Mandal, Jyotsna Kumar

A2 - Dasgupta, Kousik

PB - Springer Verlag

ER -

Sarkar S, Ghosh M, Chatterjee A, Malakar S, Sarkar R. An Advanced Particle Swarm Optimization Based Feature Selection Method for Tri-script Handwritten Digit Recognition. In Mukhopadhyay S, Dutta P, Mandal JK, Dasgupta K, editors, Computational Intelligence, Communications, and Business Analytics - 2nd International Conference, CICBA 2018, Revised Selected Papers. Springer Verlag. 2019. p. 82-94. (Communications in Computer and Information Science). https://doi.org/10.1007/978-981-13-8578-0_7