Preserving-the-past-with-AI

Aren-AiKing/Preserving-the-past-with-AI

AI system auto-analyzes scanned Armenian newspapers: YOLO detects/rotates sections & assesses quality. OCR extracts text; GPT cleans, classifies topics, summarizes in Armenian. Metrics (blur, brightness, contrast, entropy) via visual UI. Export DOCX/TXT/JSON. For archives/libraries/history.

Python Stars: 0 Forks: 0 ML/AI

Summary

An AI-powered system for analyzing scanned Armenian newspapers using computer vision (YOLO for section detection, OpenCV for image correction/quality metrics), OCR (Tesseract for Armenian text extraction), and NLP (GPT for text cleaning, topic classification, and summarization). Features a Streamlit web UI for upload, analysis, and export to DOCX/TXT/JSON. Aimed at digital archives and historical research.

Similar Projects