Giter Club home page Giter Club logo

cnocr's Introduction

English README (out-dated).

cnocr

cnocrPython 3 下的文字识别Optical Character Recognition,简称OCR)工具包,支持中文英文的常见字符识别,自带了多个训练好的识别模型,安装后即可直接使用。欢迎扫码加入QQ交流群:

QQ群二维码

详细文档

CnOcr在线文档

使用场景说明

cnocr 主要针对的是排版简单的印刷体文字图片,如截图图片,扫描件等。目前内置的文字检测和分行模块无法处理复杂的文字排版定位。如果要用于场景文字图片的识别,需要结合其他的场景文字检测引擎使用,例如文字检测引擎 cnstd

示例

图片 OCR结果
docs/examples/helloworld.jpg Hello world!你好世界
docs/examples/chn-00199989.jpg 铑泡胭释邑疫反隽寥缔
docs/examples/chn-00199980.jpg 拇箬遭才柄腾戮胖惬炫
docs/examples/chn-00199984.jpg 寿猿嗅髓孢刀谎弓供捣
docs/examples/chn-00199985.jpg 马靼蘑熨距额猬要藕萼
docs/examples/chn-00199981.jpg 掉江悟厉励.谌查门蠕坑
docs/examples/00199975.jpg nd-chips fructed ast
docs/examples/00199978.jpg zouna unpayably Raqu
docs/examples/00199979.jpg ape fissioning Senat
docs/examples/00199971.jpg ling oughtlins near
docs/examples/multi-line_cn1.png 网络支付并无本质的区别,因为
每一个手机号码和邮件地址背后
都会对应着一个账户--这个账
户可以是信用卡账户、借记卡账
户,也包括邮局汇款、手机代
收、电话代收、预付费卡和点卡
等多种形式。
docs/examples/multi-line_cn2.png 当然,在媒介越来越多的情形下,
意味着传播方式的变化。过去主流
的是大众传播,现在互动性和定制
性带来了新的挑战——如何让品牌
与消费者更加互动。
docs/examples/multi-line_en_white.png This chapter is currently only available in this web version. ebook and print will follow.
Convolutional neural networks learn abstract features and concepts from raw image pixels. Feature
Visualization visualizes the learned features by activation maximization. Network Dissection labels
neural network units (e.g. channels) with human concepts.
docs/examples/multi-line_en_black.png transforms the image many times. First, the image goes through many convolutional layers. In those
convolutional layers, the network learns new and increasingly complex features in its layers. Then the
transformed image information goes through the fully connected layers and turns into a classification
or prediction.

安装

嗯,安装真的很简单。

pip install cnocr

安装速度慢的话,可以指定国内的安装源,如使用豆瓣源:

pip install cnocr -i https://pypi.doubanio.com/simple

注意:请使用 Python3(3.6以及之后版本应该都行),没测过Python2下是否ok。

未来工作

  • 支持图片包含多行文字 (Done)
  • crnn模型支持可变长预测,提升灵活性 (since V1.0.0)
  • 完善测试用例 (Doing)
  • 修bugs(目前代码还比较凌乱。。) (Doing)
  • 支持空格识别(since V1.1.0
  • 尝试新模型,如 DenseNet,进一步提升识别准确率(since V1.1.0
  • 优化训练集,去掉不合理的样本;在此基础上,重新训练各个模型
  • 由 MXNet 改为 PyTorch 架构(since V2.0.0
  • 基于 PyTorch 训练更高效的模型
  • 支持列格式的文字识别

cnocr's People

Contributors

breezedeus avatar diaomin avatar jinnrry avatar myuanz avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.