KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Subject: search.filters.subject.EasyOCR

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    An OCR-Based Framework for Automated Verification of Thai and English Academic Transcripts
    (2025-01-01)
    Wattanacheep, Bhattarabhorn
    ;
    Komkris, Pannathorn
    ;
    Heymun, Issariyapon
    ;
    Srimontrisanga, Wongsawan
    Academic transcripts are essential documents for employment and higher education but remain susceptible to forgery and manipulation, creating a need for efficient and reliable verification methods. Traditional verification is often time-consuming due to the structural complexity of transcripts and the challenges of extracting information from PDF and image formats. This study presents an OCR-based framework for automated transcript verification that integrates preprocessing and postprocessing techniques to enhance data extraction quality. English transcripts were evaluated using OCR models PaddleOCR, Tesseract, and EasyOCR, while Thai transcripts were assessed with Tesseract and EasyOCR. Experimental results demonstrate that preprocessing substantially improves extraction accuracy and that postprocessing further refines the outputs. Among the evaluated models, PaddleOCR achieved the highest performance on English transcripts with an overall accuracy of 81.87%, whereas Tesseract yielded the best accuracy for Thai transcripts at 81.11%. These findings underscore the effectiveness of combining OCR with tailored preprocessing and postprocessing strategies to support reliable and efficient transcript verification in academic settings.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Automated Verification of English Proficiency Test Scores Using OCR for Graduation Qualification
    (2025-01-01)
    Titijaroonroj, Taravichet
    ;
    Maliwan, Thitiwut
    ;
    Jaimetha, Nattakamon
    ;
    Wattanacheep, Bhattarabhorn
    An algorithm is proposed to verify English proficiency scores using OCR for graduation qualification, aiming to reduce errors and workload in the current manual verification process of officer. Score reports in image or PDF format, including TOEIC and KMITL-TEP, are processed using two deep learning-based document classifiers that identify the test type and score type prior to OCR execution. Preprocessing techniques such as noise reduction, contrast enhancement, and skew correction are applied to improve OCR accuracy. Three OCR models-Tesseract, TrOCR, and EasyOCR-are evaluated for text extraction performance. The extracted textual data are then converted into structured JSON, enabling automated rule-based comparison against graduation criteria. Evaluation performance is measured using Accuracy, F1-Score, Character Error Rate (CER), and Word Error Rate (WER). Experimental results show that the proposed system achieves 99% accuracy, demonstrating both high reliability and adaptability to institutional scoring standards. The integration of OCR significantly reduces processing time while maintaining flexibility to accommodate future changes in assessment policies.