Title: Arabic literal amount sub-word recognition using multiple features and classifiers

Authors: Irfan Ahmad; Sameh Awaida; Sabri A. Mahmoud

Addresses: Information and Computer Science Department, KFUPM, Dhahran-31261, Saudi Arabia ' Canada Clean Fuels, 4425 Chesswood Dr, North York, ON M3J 2C2, Canada ' Information and Computer Science Department, KFUPM, Dhahran-31261, Saudi Arabia

Abstract: Bank check processing is an important application of document analysis and recognition. Recognising the literal amounts from the check images is challenging and an open research problem. In this paper, we present our work on Arabic bank check literal amounts' sub-word recognition using four sets of features and three classifiers namely: support vector machine (SVM), neural network (NN), and decision tree forest (DTF) classifiers. In addition, we investigated two different approaches for classifier fusion. We tested our system on the CENPARMI database of Arabic bank check images. Our recognition results outperform previous published results on the same database.

Keywords: Arabic sub-word recognition; bank check processing; feature extraction; cursive script; literal amount recognition; handwritten text recognition; classifier combination; feature fusion; support vector machine; SVM; random forest; artificial neural networks.

DOI: 10.1504/IJAPR.2020.111497

International Journal of Applied Pattern Recognition, 2020 Vol.6 No.2, pp.103 - 123

Received: 22 Dec 2018
Accepted: 03 Dec 2019
Published online: 30 Nov 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article