scan, split, OCR, prepare for LLM

Evgeniy Ierusalimov 25992f0ef6 renamed inage_split to image_prepare, fixed some code and parameters		2ヶ月前
..
AGENTS.md	initial release with base split functionality	2ヶ月前
AI_RULES.md	refactored code	2ヶ月前
ARCHITECTURE.md	renamed inage_split to image_prepare, fixed some code and parameters	2ヶ月前
CODE_STYLE.md	polishing the code and docs	2ヶ月前
DEVELOPMENT.md	refactored code	2ヶ月前
IMAGE_PROCESSING.md	refactored code	2ヶ月前
README.md	initial release with base split functionality	2ヶ月前
REQUIREMENTS.md	initial release with base split functionality	2ヶ月前
SOLID_AUDIT.md	polishing the code and docs	2ヶ月前
TASKS.md	initial release with base split functionality	2ヶ月前
VLM_OFFLOAD.md	polishing the code and docs	2ヶ月前

Offline Document Pipeline

Назначение проекта

Преобразование больших технических документов, полученных после печати и сканирования, в структурированный HTML без использования облачных сервисов.

Поддерживается полностью offline работа.

Pipeline

JPEG/TIFF/PDF

↓

Split pages

↓

Deskew

↓

Crop

↓

PaddleOCR

↓

HTML

Вне scope проекта