Latest Issue
Effect of Different Irrigation Methods on Water Use Efficiency in Rice Soil Column Test
Published: April 30,2025Optimization of Extraction Condition for Oleoresin from Red Pepper Residues
Published: April 30,2025Effect of microwave pretreatment method on essential oil extraction on key lime peel (Citrus × aurantiifolia)
Published: April 30,2025Reducing traffic congestion during flyover construction: A case study of flyover construction at the intersection 2004, Phnom Penh, Cambodia
Published: April 30,2025Effects of Different Bleaching Conditions on Bleaching Efficiency and Physicochemical Characteristics of Cambodian Soybean Oil
Published: April 30,2025Bus Arrival Time Prediction Using Machine Learning Approaches
Published: April 30,2025A Deep Learning Approach for Identifying Individuals Based on Their Handwriting
Published: April 30,2025Utilizing Data Mining And AI To Enhance Cambodian High School Student Performance And Stakeholder Success
Published: April 30,2025Khmer Question-Answering Model by Fine-tuning Pre-trained Model
Published: April 30,2025CNN-based Reinforcement Learning with Policy Gradient for Khmer Chess
Published: April 30,2025Improving Recognition Result Using Character Trigram for Khmer OCR
-
1. Department of Computer Science,
Institute of Technology of Cambodia, Russian Ferderation Blvd., P.O. Box 86, Phnom Penh, Cambodia.
Academic Editor:
Received: January 20,2024 / Revised: / Accepted: January 20,2024 / Available online: June 01,2013
The recognition phase of an Optical Character Recognition (OCR) system produces a ranked list of candidate characters, among which the top one is usally taken as recognition result without taking context into account. Recognition error occurs if the correct character is not at the top, which is mostly due to shape similarity between characters.In this paper we propose to use character trigram, which means that two previous characters are taken into account when choosing the character from the candidate list as recognition result for Khmer OCR.A text corpus of about 300 Mbytes is used to compute character trigrams. Using these trigrams, we test our approach on about 3000 characters. The result shows that this approach can correct about 30% of recognition errors.