TextBoxes++: 一个场景文本检测和识别（CRNN）的应用程序

TextBoxes++: 一个场景文本检测和识别（CRNN）的应用程序

TextBoxes++: A Single-Shot Oriented Scene Text Detector

Introduction

This is an application for scene text detection (TextBoxes++) and recognition (CRNN).

TextBoxes++ is a unified framework for oriented scene text detection with a single network. It is an extended work of TextBoxes. CRNN is an open-source text recognizer. The code of TextBoxes++ is based on SSD and TextBoxes. The code of CRNN is modified from CRNN.

For more details, please refer to our arXiv paper.

Citing the related works

Please cite the related works in your publications if it helps your research:

@article{Liao2018Text, title = {{TextBoxes++}: A Single-Shot Oriented Scene Text Detector}, author = {Minghui Liao, Baoguang Shi and Xiang Bai}, journal = {{IEEE} Transactions on Image Processing}, doi = {10.1109/TIP.2018.2825107}, url = {https://doi.org/10.1109/TIP.2018.2825107}, volume = {27}, number = {8}, pages = {3676--3690}, year = {2018}}@inproceedings{LiaoSBWL17, author = {Minghui Liao and Baoguang Shi and Xiang Bai and Xinggang Wang and Wenyu Liu}, title = {TextBoxes: {A} Fast Text Detector with a Single Deep Neural Network}, booktitle = {AAAI}, year = {2017}}@article{ShiBY17, author = {Baoguang Shi and Xiang Bai and Cong Yao}, title = {An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition}, journal = {{IEEE} TPAMI}, volume = {39}, number = {11}, pages = {2298--2304}, year = {2017}}

Contents

RequirementsInstallationDockerModelsDemoTrain

Requirements

NOTE There is partial support for a docker image. See docker/README.md. (Thank you for the PR from @mdbenito)

Torch7 for CRNN; g++-5; cuda8.0; cudnn V5.1 (cudnn 6 and cudnn 7 may fail); opencv3.0

Please refer to Caffe Installation to ensure other dependencies;

Installation

compile TextBoxes++ (This is a modified version of caffe so you do not need to install the official caffe)

# Modify Makefile.config according to your Caffe installation.cp Makefile.config.example Makefile.configmake -j8# Make sure to include $CAFFE_ROOT/python to your PYTHONPATH.make py

compile CRNN (Please refer to CRNN if you have trouble with the compilation.)

cd crnn/src/sh build_cpp.sh

Docker

(Thanks for the PR from @idotobi)

Build Docke Image

docker build -t tbpp_crnn:gpu .

This can take +1h, so go get a coffee ;)

Once this is done you can start a container via nvidia-docker.

nvidia-docker run -it --rm tbpp_crnn:gpu bash

To check if the GPU is available inside the docker container you can run nvidia-smi.

It's recommendable to mount the ./models and ./crnn/model/ directories to include the downloaded models.

nvidia-docker run -it \ --rm \ -v ${PWD}/models:/opt/caffe/models \ -v ${PWD}/crrn/model:/opt/caffe/crrn/model \ tbpp_crnn:gpu bash

For convenince this command is executed when running ./run.bash.

Models

pre-trained model on SynthText (used for training): Dropbox; BaiduYun model trained on ICDAR 2015 Incidental Text (used for testing): Dropbox; BaiduYun Please place the above models in "./models/" If your data is hugely different from ICDAR 2015 Incidental Text，you'd better train it on your own data based on the pre-trained model on SynthText. CRNN model: Dropbox; BaiduYun Please place the crnn model in "./crnn/model/"

Demo

Download the ICDAR 2015 model and place it in "./models/"

python examples/text/demo.py

The detection results and recognition results are in "./demo_images"

Train

Create lmdb data

convert ground truth into "xml" form: example.xml create train/test lists (train.txt / test.txt) in "./data/text/" with the following form: path_to_example1.jpg path_to_example1.xml path_to_example2.jpg path_to_example2.xml Run "./data/text/creat_data.sh"

Start training

1. modify the lmdb path in modelConfig.py2. Run "python examples/text/train.py"

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。