Title: Improvement of the performance of optical handwritten digit recognition by incorporating cross-domain autoencoder-based image to image translation technique

Authors: N.S.M. Rezaur Rahman; Rashedur M. Rahman

Addresses: Department of Electrical and Computer Engineering, North South University, Basundhara, Dhaka, 1229, Bangladesh ' Department of Electrical and Computer Engineering, North South University, Basundhara, Dhaka, 1229, Bangladesh

Abstract: The paper represents a novel approach that improves the performance of optical handwritten digit recognition incorporating image to image translation technique in a way - that it translates the input image of handwritten domain to some model domain so that the performance of any specified classier improves. In this paper, we have done image to image translation using two pretrained autoencoders, one of them is an autoencoder of a handwritten domain and other is an autoencoder of a model domain. We have bonded together the encoder of handwritten domain and the decoder of model domain and a neural network for feature translation in between in order to train the whole neural network for the translation of an image from handwritten domain to the image of a model domain. Also, an analysis has been shown regarding how well our method improves the performance of optical handwritten digit recognition for both Bengali and English digits.

Keywords: autoencoder; image to image translation; deep learning; convolutional neural network; CNN; machine learning; ML; artificial neural network; ANN; computer vision; optical character recognition; OCR; classification.

DOI: 10.1504/IJKESDP.2020.112632

International Journal of Knowledge Engineering and Soft Data Paradigms, 2020 Vol.7 No.1, pp.45 - 56

Received: 05 Jul 2020
Accepted: 08 Sep 2020
Published online: 25 Jan 2021 *

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