11 results for “topic:surya-ocr”
Egyptian ID Card Recognition System 💳 A Python-based application to detect and process Egyptian ID cards using YOLO and EasyOCR.
Convert scanned PDFs into searchable text locally using Vision LLMs (olmOCR). 100% private, offline, and free. Features a modern Web UI & CLI.
OCR web-server on FastAPI with OCR models: EasyOCR, TesseractOCR, PaddleOCR и SuryaOCR
Advanced PDF processing, OCR, and AI vision analysis nodes for ComfyUI. Extract images from PDFs, perform multilingual OCR with Surya, detect objects with Florence-2, and analyze document layouts.
A pipeline for turning digital collections into structured data -- an LLM assisted, IIIF-native tool to jump into working with sources like digitized print directories.
OSPA SuryaOCR – Advanced document processing framework for historical sources using Surya OCR and DocLayout-YOLO. Developed within TÜBİTAK Project 323K372.
🎓 Production-grade RAG Tutor for handwritten notes. Features Hybrid Search (BGE-M3 + BM25), Cross-Encoder Reranking, and an LLM-based OCR cleaning pipeline.
Simple ocr service using surya engine
Internship Project - IIT Bombay
HeySeen là ứng dụng chuyển đổi PDF (bài báo khoa học, sách chuyên ngành) thành thư mục gồm file TeX và ảnh (nếu có).
👁️ Convert PDFs to editable LaTeX files with images offline on macOS, optimized for Apple Silicon and secure with no cloud dependency.