Latest Issue
Design Of Buck Converter For Low Power Application A Comparative Study For Selecting The Semiconductor Devices
Published: April 30,2026Determination of Mechanical Properties of Cambodian Sandstone using the Brazilian Test and the Semi Circular Bending Test
Published: April 30,2026Quality Evaluation of Cambodian Rice Seeds Under Organic Tillage and Green Manure Production Systems
Published: April 30,2026Assessing the Impact of Motorcycle Emissions on Urban Air Quality: A Case Study at the Institute of Technology of Cambodia
Published: April 30,2026Characterization of Antimicrobial Resistance Profiles and Extended-Spectrum Beta-Lactamase Resistance Genes in Salmonella Isolates from Different Food Matrices in Cambodia
Published: April 30,2026Impact of rice agro-system on aroma accumulation of Phka Rumdoul rice variety in Cambodia
Published: April 30,2026Evaluation of The Susceptibility of Rice Germplasms In Cambodia To The Rice Root-Knot Nematode, Meloidogyne Graminicola
Published: April 30,2026Correlation Between Dynamic Cone Penetrometer (DCP) and California Bearing Ratio (CBR) for Subgrade Soil Material in Cambodia
Published: April 30,2026Effect of Storage Conditions on the Stability of Rice Fragrance and Protein Content in Phka Rumdoul Rice Variety
Published: April 30,2026Assessment of Hydraulic Transport of Pesticides at the Watershed: Case study Tonle Sap and Mekong River
Published: April 30,2026Improving 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.