Handwritten digits recognition with artificial neural network

Kh Tohidul Islam; Ghulam Mujtaba; Ram Gopal Raj; Henry Friday Nweke

doi:10.1109/ICE2T.2017.8215993

Handwritten digits recognition with artificial neural network

Kh Tohidul Islam
, Ghulam Mujtaba
, Ram Gopal Raj
, Henry Friday Nweke

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

39 Citations (Scopus)

Abstract

In a computer vision system, handwritten digits recognition is a complex task that is central to a variety of emerging applications. It has been widely used by machine learning and computer vision researchers for implementing practical applications like computerized bank check numbers reading. In this study, we implemented a multi-layer fully connected neural network with one hidden layer for handwritten digits recognition. The testing has been conducted from publicly available MNIST handwritten database. From the MNIST database, we extracted 28,000 digits images for training and 14,000 digits images for performing the test. Our multi-layer artificial neural network has an accuracy of 99.60% with test performance.

Original language	English
Title of host publication	2017 International Conference on Engineering Technology and Technopreneurship (ICE2T 2017)
Editors	Mohamad Ismail Sulaiman, Aizat Faiz Ramli, Ahmad Sabry Mohamad, Mohd Hazli Mohd Rusli, Suhaiza Ngah, Harlisya Harun
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	248-251
Number of pages	4
ISBN (Electronic)	9781538618073
ISBN (Print)	9781538618080
DOIs	https://doi.org/10.1109/ICE2T.2017.8215993
Publication status	Published - 2017
Externally published	Yes
Event	International Conference on Engineering Technology and Technopreneurship (ICET) 2017 - Kuala Lumpur, Malaysia Duration: 18 Sept 2017 → 20 Sept 2017 https://ieeexplore.ieee.org/xpl/conhome/8171402/proceeding (Proceedings)

Conference

Conference	International Conference on Engineering Technology and Technopreneurship (ICET) 2017
Abbreviated title	ICE2T 2017
Country/Territory	Malaysia
City	Kuala Lumpur
Period	18/09/17 → 20/09/17
Internet address	https://ieeexplore.ieee.org/xpl/conhome/8171402/proceeding (Proceedings)

Keywords

Artificial neural network
Computer vision
Handwritten digits
Recognition

Access to Document

10.1109/ICE2T.2017.8215993

Cite this

Islam, K. T., Mujtaba, G., Raj, R. G., & Nweke, H. F. (2017). Handwritten digits recognition with artificial neural network. In M. I. Sulaiman, A. F. Ramli, A. S. Mohamad, M. H. M. Rusli, S. Ngah, & H. Harun (Eds.), 2017 International Conference on Engineering Technology and Technopreneurship (ICE2T 2017) (pp. 248-251). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICE2T.2017.8215993

Islam, Kh Tohidul ; Mujtaba, Ghulam ; Raj, Ram Gopal et al. / Handwritten digits recognition with artificial neural network. 2017 International Conference on Engineering Technology and Technopreneurship (ICE2T 2017). editor / Mohamad Ismail Sulaiman ; Aizat Faiz Ramli ; Ahmad Sabry Mohamad ; Mohd Hazli Mohd Rusli ; Suhaiza Ngah ; Harlisya Harun. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. pp. 248-251

@inproceedings{3a673d0879c442a4aaca02b5010eefd8,

title = "Handwritten digits recognition with artificial neural network",

abstract = "In a computer vision system, handwritten digits recognition is a complex task that is central to a variety of emerging applications. It has been widely used by machine learning and computer vision researchers for implementing practical applications like computerized bank check numbers reading. In this study, we implemented a multi-layer fully connected neural network with one hidden layer for handwritten digits recognition. The testing has been conducted from publicly available MNIST handwritten database. From the MNIST database, we extracted 28,000 digits images for training and 14,000 digits images for performing the test. Our multi-layer artificial neural network has an accuracy of 99.60\% with test performance.",

keywords = "Artificial neural network, Computer vision, Handwritten digits, Recognition",

author = "Islam, \{Kh Tohidul\} and Ghulam Mujtaba and Raj, \{Ram Gopal\} and Nweke, \{Henry Friday\}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; International Conference on Engineering Technology and Technopreneurship (ICET) 2017, ICE2T 2017 ; Conference date: 18-09-2017 Through 20-09-2017",

year = "2017",

doi = "10.1109/ICE2T.2017.8215993",

language = "English",

isbn = "9781538618080",

pages = "248--251",

editor = "Sulaiman, \{Mohamad Ismail\} and Ramli, \{Aizat Faiz\} and Mohamad, \{Ahmad Sabry\} and Rusli, \{Mohd Hazli Mohd\} and Suhaiza Ngah and Harlisya Harun",

booktitle = "2017 International Conference on Engineering Technology and Technopreneurship (ICE2T 2017)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

url = "https://ieeexplore.ieee.org/xpl/conhome/8171402/proceeding",

}

Islam, KT, Mujtaba, G, Raj, RG & Nweke, HF 2017, Handwritten digits recognition with artificial neural network. in MI Sulaiman, AF Ramli, AS Mohamad, MHM Rusli, S Ngah & H Harun (eds), 2017 International Conference on Engineering Technology and Technopreneurship (ICE2T 2017). IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 248-251, International Conference on Engineering Technology and Technopreneurship (ICET) 2017, Kuala Lumpur, Malaysia, 18/09/17. https://doi.org/10.1109/ICE2T.2017.8215993

Handwritten digits recognition with artificial neural network. / Islam, Kh Tohidul; Mujtaba, Ghulam; Raj, Ram Gopal et al.
2017 International Conference on Engineering Technology and Technopreneurship (ICE2T 2017). ed. / Mohamad Ismail Sulaiman; Aizat Faiz Ramli; Ahmad Sabry Mohamad; Mohd Hazli Mohd Rusli; Suhaiza Ngah; Harlisya Harun. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 248-251.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Handwritten digits recognition with artificial neural network

AU - Islam, Kh Tohidul

AU - Mujtaba, Ghulam

AU - Raj, Ram Gopal

AU - Nweke, Henry Friday

PY - 2017

Y1 - 2017

N2 - In a computer vision system, handwritten digits recognition is a complex task that is central to a variety of emerging applications. It has been widely used by machine learning and computer vision researchers for implementing practical applications like computerized bank check numbers reading. In this study, we implemented a multi-layer fully connected neural network with one hidden layer for handwritten digits recognition. The testing has been conducted from publicly available MNIST handwritten database. From the MNIST database, we extracted 28,000 digits images for training and 14,000 digits images for performing the test. Our multi-layer artificial neural network has an accuracy of 99.60% with test performance.

AB - In a computer vision system, handwritten digits recognition is a complex task that is central to a variety of emerging applications. It has been widely used by machine learning and computer vision researchers for implementing practical applications like computerized bank check numbers reading. In this study, we implemented a multi-layer fully connected neural network with one hidden layer for handwritten digits recognition. The testing has been conducted from publicly available MNIST handwritten database. From the MNIST database, we extracted 28,000 digits images for training and 14,000 digits images for performing the test. Our multi-layer artificial neural network has an accuracy of 99.60% with test performance.

KW - Artificial neural network

KW - Computer vision

KW - Handwritten digits

KW - Recognition

UR - https://www.scopus.com/pages/publications/85046426112

U2 - 10.1109/ICE2T.2017.8215993

DO - 10.1109/ICE2T.2017.8215993

M3 - Conference Paper

AN - SCOPUS:85046426112

SN - 9781538618080

SP - 248

EP - 251

BT - 2017 International Conference on Engineering Technology and Technopreneurship (ICE2T 2017)

A2 - Sulaiman, Mohamad Ismail

A2 - Ramli, Aizat Faiz

A2 - Mohamad, Ahmad Sabry

A2 - Rusli, Mohd Hazli Mohd

A2 - Ngah, Suhaiza

A2 - Harun, Harlisya

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - International Conference on Engineering Technology and Technopreneurship (ICET) 2017

Y2 - 18 September 2017 through 20 September 2017

ER -

Islam KT, Mujtaba G, Raj RG, Nweke HF. Handwritten digits recognition with artificial neural network. In Sulaiman MI, Ramli AF, Mohamad AS, Rusli MHM, Ngah S, Harun H, editors, 2017 International Conference on Engineering Technology and Technopreneurship (ICE2T 2017). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2017. p. 248-251 doi: 10.1109/ICE2T.2017.8215993

Handwritten digits recognition with artificial neural network

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this