Evaluating the Impact of Khmer Font Types on Text Recognition

TL;DR

This paper evaluates how 19 different Khmer fonts affect OCR accuracy, highlighting the importance of font choice for improving Khmer text recognition systems.

Contribution

It systematically assesses the impact of various Khmer fonts on OCR performance, providing insights for enhancing recognition accuracy.

Findings

Khmer, Odor MeanChey, Siemreap, Sithi Manuss, and Battambang fonts yield high OCR accuracy.

iSeth First, Bayon, and Dangrek fonts perform poorly in OCR recognition.

Font selection significantly influences Khmer text recognition effectiveness.

Abstract

Text recognition is significantly influenced by font types, especially for complex scripts like Khmer. The variety of Khmer fonts, each with its unique character structure, presents challenges for optical character recognition (OCR) systems. In this study, we evaluate the impact of 19 randomly selected Khmer font types on text recognition accuracy using Pytesseract. The fonts include Angkor, Battambang, Bayon, Bokor, Chenla, Dangrek, Freehand, Kh Kompong Chhnang, Kh SN Kampongsom, Khmer, Khmer CN Stueng Songke, Khmer Savuth Pen, Metal, Moul, Odor MeanChey, Preah Vihear, Siemreap, Sithi Manuss, and iSeth First. Our comparison of OCR performance across these fonts reveals that Khmer, Odor MeanChey, Siemreap, Sithi Manuss, and Battambang achieve high accuracy, while iSeth First, Bayon, and Dangrek perform poorly. This study underscores the critical importance of font selection in optimizing Khmer text recognition and provides valuable insights for developing more robust OCR systems.