PHND: Pashtu Handwritten Numerals Database and deep learning benchmark

Khalil Khan; Byeong-Hee Roh; Jehad Ali; Rehan Ullah Khan; Irfan Uddin; Saqlain Hassan; Rabia Riaz; Nasir Ahmad

doi:10.1371/journal.pone.0238423

PHND: Pashtu Handwritten Numerals Database and deep learning benchmark

PLoS One. 2020 Sep 2;15(9):e0238423. doi: 10.1371/journal.pone.0238423. eCollection 2020.

Authors

Khalil Khan¹, Byeong-Hee Roh², Jehad Ali², Rehan Ullah Khan³, Irfan Uddin⁴, Saqlain Hassan⁵, Rabia Riaz⁶, Nasir Ahmad⁷

Affiliations

¹ Department of Electrical Engineering, University of Azad Jammu and Kashmir, Muzaffarabad, Pakistan.
² Department of Computer Engineering, Ajou University, Suwon, South Korea.
³ Department of Information Technology, College of Computer, Qassim University, Al-Mulaida, Saudi Arabia.
⁴ Department of Information Technology, Superior University, Lahore, Pakistan.
⁵ Institute of Culture and Society, University of Navarra, Pamplona, Spain.
⁶ Department of Computer Science, University of Azad Jammu and Kashmir, Jammu and Kashmir, Muzaffarabad, Pakistan.
⁷ Department of Computer Systems Engineering, University of Engineering and Technology, Peshawar, Pakistan.

Abstract

In this paper we introduce a real Pashtu handwritten numerals dataset (PHND) having 50,000 scanned images and make publicly available for research and scientific use. Although more than fifty million people in the world use this language for written and oral communication, no significant efforts are devoted to the Pashtu Optical Character Recognition (POCR). We present a new approach for Pahstu handwritten numerals recognition (PHNR) based on deep neural networks. We train Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) on high-frequency numerals for feature extraction and classification. We evaluated the performance of the proposed algorithm on the newly introduced Pashtu handwritten numerals database PHND and Bangla language number database CMATERDB 3.1.1. We obtained best recognition rate of 98.00% and 98.64% on PHND and CMATERDB 3.1.1. respectively.

Publication types

Dataset
Research Support, Non-U.S. Gov't

MeSH terms

Adult
Aged
Algorithms
Deep Learning
Female
Handwriting
Humans
Image Processing, Computer-Assisted / methods*
Male
Middle Aged
Neural Networks, Computer
Pattern Recognition, Automated / methods*
Writing / standards*

Grants and funding

This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2020-2018-0-01431) supervised by the IITP (Institute for Information & communications Technology Promotion.