Universiti Teknologi Malaysia Institutional Repository

A compact deep learning model for khmer handwritten text recognition

Annanurov, B. and Noor, N. (2021) A compact deep learning model for khmer handwritten text recognition. IAES International Journal of Artificial Intelligence, 10 (3). ISSN 2089-4872


Official URL: http://dx.doi.org/10.11591/ijai.v10.i3.pp584-591


The motivation of this study is to develop a compact offline recognition model for Khmer handwritten text that would be successfully applied under limited access to high-performance computational hardware. Such a task aims to ease the ad-hoc digitization of vast handwritten archives in many spheres. Data collected for previous experiments were used in this work. The one-against-all classification was completed with state-of-the-art techniques. A compact deep learning model (2+1CNN), with two convolutional layers and one fully connected layer, was proposed. The recognition rate came out to be within 93-98%. The compact model is performed on par with the state-of-the-art models. It was discovered that computational capacity requirements usually associated with deep learning can be alleviated, therefore allowing applications under limited computational power.

Item Type:Article
Uncontrolled Keywords:character recognition, convolutional neural networks, deep learning
Subjects:T Technology > T Technology (General)
Divisions:Razak School of Engineering and Advanced Technology
ID Code:94987
Deposited By: Narimah Nawil
Deposited On:30 Apr 2022 06:01
Last Modified:30 Apr 2022 06:01

Repository Staff Only: item control page