Bangla text analysis
OCR
Tool 01 / Web application
Academic language toolBangla Assignment Plagiarism Checker
A Bengali-language plagiarism checking application that accepts PDF files or text, extracts Bengali content with OCR, and compares submissions for similarity.
- Built a Bengali-focused plagiarism workflow for an area where most existing tools primarily support English content.
- Implemented PDF and image text extraction using Tesseract OCR, pytesseract, Pillow, and Bengali trained data.
- Used Levenshtein distance and NLTK-assisted text processing to calculate similarity between submitted content.
- Supported text input and multiple-file workflows through a Django and Bootstrap web interface.
- Received the Best Project Award as a university final-year project.
PythonDjangoTesseract OCRNLTKPillowBootstrap
Open GitHub repository