Chinese_ocr

CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras
Alternatives To Chinese_ocr
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
Keras57,713330a day ago68May 13, 2022372apache-2.0Python
Deep Learning for humans
Data Science Ipython Notebooks23,924
5 months ago26otherPython
Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
Mask_rcnn22,777
15 days ago5March 05, 20191,933otherPython
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Netron21,73646321 hours ago489July 04, 202222mitJavaScript
Visualizer for neural network, deep learning, and machine learning models
100 Days Of Ml Code17,892
a year ago9mitJupyter Notebook
100-Days-Of-ML-Code中文版
D2l En16,954
8 days ago83otherPython
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 400 universities from 60 countries including Stanford, MIT, Harvard, and Cambridge.
Ncnn16,728
7 hours ago19July 01, 2022959otherC++
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Onnx14,33014824520 hours ago26June 18, 2022370apache-2.0Python
Open standard for machine learning interoperability
Horovod13,13320102 days ago72June 21, 2022344otherPython
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
Best Of Ml Python13,088
3 days ago15cc-by-sa-4.0
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
Alternatives To Chinese_ocr
Select To Compare


Alternative Project Comparisons
Readme

简介

基于Tensorflow和Keras实现端到端的不定长中文字符检测和识别

  • 文本检测:CTPN
  • 文本识别:DenseNet + CTC

环境部署

sh setup.sh
  • 注:CPU环境执行前需注释掉for gpu部分,并解开for cpu部分的注释

Demo

将测试图片放入test_images目录,检测结果会保存到test_result中

python demo.py

模型训练

CTPN训练

详见ctpn/README.md

DenseNet + CTC训练

1. 数据准备

数据集:https://pan.baidu.com/s/1QkI7kjah8SPHwOQ40rS1Pw (密码:lu7m)

  • 共约364万张图片,按照99:1划分成训练集和验证集
  • 数据利用中文语料库(新闻 + 文言文),通过字体、大小、灰度、模糊、透视、拉伸等变化随机生成
  • 包含汉字、英文字母、数字和标点共5990个字符
  • 每个样本固定10个字符,字符随机截取自语料库中的句子
  • 图片分辨率统一为280x32

图片解压后放置到train/images目录下,描述文件放到train目录下

2. 训练

cd train
python train.py

3. 结果

val acc predict model
0.983 8ms 18.9MB
  • GPU: GTX TITAN X
  • Keras Backend: Tensorflow

4. 生成自己的样本

可参考SynthText_Chinese_versionTextRecognitionDataGeneratortext_renderer

效果展示

参考

[1] eragonruan/text-detection-ctpn

[2] senlinuc/caffe_ocr

[3] chineseocr/chinese-ocr

[4] xiaomaxiao/keras_ocr

Popular Keras Projects
Popular Tensorflow Projects
Popular Machine Learning Categories

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Python
Tensorflow
Keras
Chinese
Renderer
Ocr
Densenet
Ctc