PERFORMANCE EVALUATION OF TESSERACT, EASYOCR, AND TROCR MODELS FOR OPTICAL CHARACTER RECOGNITION SYSTEMS

Simple item page
dc.contributor.authorLucas Chu Yen Feng
dc.date.accessioned2026-04-08T07:33:42Z
dc.date.issued2025
dc.descriptionThis research evaluates the performance of three Optical Character Recognition (OCR) methods of Tesseract, EasyOCR, and TrOCR across the Chars74k and Total Text datasets. Through K-fold cross-validation, the study analyzes character and word error rates, inference times, and generalization capabilities. Results highlight the trade-off between traditional and deep learning approaches, with TrOCR excelling in challenging scene text, EasyOCR offering a balance between accuracy and efficiency, and Tesseract excelling on cleaner text. A public survey further explores perceptions of OCR’s usefulness and future relevance. Findings guide future improvements and practical deployments of OCR technologies.
dc.identifier.urihttps://scholarhub.unimas.my/handle/123456789/333
dc.language.isoEnglish
dc.publisherUNIVERSITI MALAYSIA SARAWAK
dc.relation.ispartofseriesFaculty of Computer Science and Information Technology
dc.titlePERFORMANCE EVALUATION OF TESSERACT, EASYOCR, AND TROCR MODELS FOR OPTICAL CHARACTER RECOGNITION SYSTEMS
dc.typeFinal Year Project

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Lucas Chu Yen Feng (79918).pdf
Size:
6.12 MB
Format:
Adobe Portable Document Format
Download

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description:
Download

Collections

Final Year Project Report/IMRaD