Umi-OCR
by hiroi-sora
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。
AI summary
Offline OCR software
An offline OCR software with efficient offline recognition engine and built-in multi-language libraries.
- stars
- 28K
- forks
- 2.8K
- watching
- 149
Similar projects
Found by comparing what the projects do, not just their names.
Data structures library
A collection of data structure implementations and algorithms from a C programming textbook
tisfeng/easydict7.6K
Dictionary app
A dictionary and translator macOS App that supports multiple translation services and offline OCR capabilities.
Penetration testing guide
Translation of a penetration testing guide for security professionals
Deep Learning Book
Translation of a popular deep learning book into Chinese, aiming to improve accuracy and accessibility.
OS project
A 30-day project to develop a simple operating system from scratch using C and assembly languages
thudm/chatglm313.6K
NLP toolkit
Develops a range of open-source models and frameworks for natural language processing tasks
esbatmop/mnbvc3.6K
Chinese text corpus
A massive corpus of Chinese text data covering various forms and styles
Chat model
A bilingual chat model for human-like conversation
bbfamily/abu12.3K
Family relationship model
A modular C++ framework for building and optimizing family relationships models with complex interactions between individuals.
Chatbot
An open-source chatbot project built on Solid.js and OpenAI's GPT technology, with features like PWA support and customizable prompts.
CAPTCHA recognizer
Automated image recognition system using convolutional neural networks to recognize character-based CAPTCHAs.
Copywriting guidelines
Guidelines for writing Chinese copywriting in various contexts
Log library
An ultra-lightweight C/C++ log library designed for resource-constrained systems with high-performance logging capabilities
Cloud native guide
A comprehensive guide to Kubernetes and cloud-native applications
OCR toolkit
An OCR toolkit that provides a robust and efficient framework for developing and deploying optical character recognition models.
