Repository containing unpaper build for Windows users.
Perspective correction and image alignment tool for OCR/AI preprocessing. Straighten skewed documents. Pure HTML/JS.
将 PDF 逐页转为高清 PNG 并返回图片链接。支持 fileUrl / fileBase64 二选一，单次最多 100 页，适合作为 OCR 与档案流程的预处理步骤。
Pre-OCR Image Normalization — perspective correction, deskew, denoise for medical scans
Preflight checks for document extraction pipelines — validate, render, and screen PDFs before they reach your LLM. Pure-Python wheel, in-memory only.
OpenCV-based document scanner with perspective correction, adaptive binarization, de-shadowing, batch processing and scan quality assessment.
Convert multi-page PDFs into clean, OCR-ready images... CLI, watch folder, web UI, and optional Google Drive sync.
Segment medical documents from smartphone photos using U²-Net, with tools for annotation, fine-tuning, and OCR-ready preprocessing.
Add a description, image, and links to the ocr-preprocessing topic page so that developers can more easily learn about it.
To associate your repository with the ocr-preprocessing topic, visit your repo's landing page and select "manage topics."