Comparative Analysis of Outcomes of Tesseract OCR for Different Languages
Kartik Joshi, Harshal Arolkar
Abstract
Hindi and Gujarati are Devanagari scripts that have contributed to the culture of India in the form of literature and human interactions. Due to aging, the textually rich literature of these languages may not exist for future generations. To preserve them, the technological solution known as an optical character recognition engine is used. Tesseract OCR engine supports the conversion of Hindi and Gujarati language-based images to equivalent text outputs. Major challenge in generating better quality of text outputs is acquisition of high resolution and noise free images. This study has compared the working of the Tesseract OCR engine for the Gujarati and Hindi languages and determined how effective it is for real-time applications.