Khmer printed character recognition using attention-based Seq2Seq network

Rina Buoy (), Nguonly Taing, Sovisal Chenda and Sokchea Kor
Additional contact information
Rina Buoy: Techo Startup Center, Phnom Penh, Cambodia
Nguonly Taing: Techo Startup Center, Phnom Penh, Cambodia
Sovisal Chenda: Techo Startup Center, Phnom Penh, Cambodia
Sokchea Kor: Royal University of Phnom Penh, Phnom Penh, Cambodia

HO CHI MINH CITY OPEN UNIVERSITY JOURNAL OF SCIENCE - ENGINEERING AND TECHNOLOGY, 2022, vol. 12, issue 1, 3-16

Abstract: This paper presents an end-to-end deep convolutional recurrent neural network solution for Khmer optical character recognition (OCR) task. The proposed solution uses a sequence-to-sequence (Seq2Seq) architecture with attention mechanism. The encoder extracts visual features from an input text-line image via layers of convolutional blocks and a layer of gated recurrent units (GRU). The features are encoded in a single context vector and a sequence of hidden states which are fed to the decoder for decoding one character at a time until a special end-of-sentence (EOS) token is reached. The attention mechanism allows the decoder network to adaptively select relevant parts of the input image while predicting a target character. The Seq2Seq Khmer OCR network is trained on a large collection of computer-generated text-line images for multiple common Khmer fonts. Complex data augmentation is applied on both train and validation dataset. The proposed model’s performance outperforms the state-of-art Tesseract OCR engine for Khmer language on the validation set of 6400 augmented images by achieving a character error rate (CER) of 0.7% vs 35.9%.

Keywords: Khmer; Optical Character Recognition; Deep Learning; Neural Network (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journalofscience.ou.edu.vn/index.php/tech-en/article/view/2217/1678 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bjw:techen:v:12:y:2022:i:1:p:3-16

DOI: 10.46223/HCMCOUJS.tech.en.12.1.2217.2022

Access Statistics for this article

HO CHI MINH CITY OPEN UNIVERSITY JOURNAL OF SCIENCE - ENGINEERING AND TECHNOLOGY is currently edited by Nguyen Thuan

More articles in HO CHI MINH CITY OPEN UNIVERSITY JOURNAL OF SCIENCE - ENGINEERING AND TECHNOLOGY from HO CHI MINH CITY OPEN UNIVERSITY JOURNAL OF SCIENCE, HO CHI MINH CITY OPEN UNIVERSITY
Bibliographic data for series maintained by Vu Tuan Truong ().