scan, split, OCR, prepare for LLM

Historik

Evgeniy Ierusalimov 57152efb4b updated discovered self skills		3 dagar sedan
..
AGENTS.md	initial release with base split functionality	1 vecka sedan
AI_RULES.md	refactored code	1 vecka sedan
ARCHITECTURE.md	renamed inage_split to image_prepare, fixed some code and parameters	4 dagar sedan
CODE_STYLE.md	polishing the code and docs	5 dagar sedan
DEVELOPMENT.md	refactored code	1 vecka sedan
IMAGE_PROCESSING.md	refactored code	1 vecka sedan
README.md	initial release with base split functionality	1 vecka sedan
REQUIREMENTS.md	initial release with base split functionality	1 vecka sedan
SKILLS.md	updated discovered self skills	3 dagar sedan
SOLID_AUDIT.md	polishing the code and docs	5 dagar sedan
TASKS.md	initial release with base split functionality	1 vecka sedan
VLM_OFFLOAD.md	polishing the code and docs	5 dagar sedan

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