Convolutional Recurrent Neural Networks(CRNN) for Scene Text Recognition

Overview

CRNN_Tensorflow

This is a TensorFlow implementation of a Deep Neural Network for scene text recognition. It is mainly based on the paper "An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition". You can refer to the paper for architecture details. Thanks to the author Baoguang Shi.

The model consists of a CNN stage extracting features which are fed to an RNN stage (Bi-LSTM) and a CTC loss.

Installation

This software has been developed on Ubuntu 16.04(x64) using python 3.5 and TensorFlow 1.12. Since it uses some recent features of TensorFlow it is incompatible with older versions.

The following methods are provided to install dependencies:

Conda

You can create a conda environment with the required dependencies using:

conda env create -f crnntf-env.yml

Pip

Required packages may be installed with

pip3 install -r requirements.txt

Testing the pre-trained model

Evaluate the model on the synth90k dataset

In this repo you will find a model pre-trained on the Synth 90kdataset. When the tfrecords file of synth90k dataset has been successfully generated you may evaluated the model by the following script

The pretrained crnn model weights on Synth90k dataset can be found here

python tools/evaluate_shadownet.py --dataset_dir PATH/TO/YOUR/DATASET_DIR 
--weights_path PATH/TO/YOUR/MODEL_WEIGHTS_PATH
--char_dict_path PATH/TO/CHAR_DICT_PATH 
--ord_map_dict_path PATH/TO/ORD_MAP_PATH
--process_all 1 --visualize 1

If you set visualize true the expected output during evaluation process is

evaluate output

After all the evaluation process is done you should see some thing like this:

evaluation_result

The model's main evaluation index are as follows:

Test Dataset Size: 891927 synth90k test images

Per char Precision: 0.974325 without average weighted on each class

Full sequence Precision: 0.932981 without average weighted on each class

For Per char Precision:

single_label_accuracy = correct_predicted_char_nums_of_single_sample / single_label_char_nums

avg_label_accuracy = sum(single_label_accuracy) / label_nums

For Full sequence Precision:

single_label_accuracy = 1 if the prediction result is exactly the same as label else 0

avg_label_accuracy = sum(single_label_accuracy) / label_nums

Part of the confusion matrix of every single char looks like this:

evaluation_confusion_matrix

Test the model on the single image

If you want to test a single image you can do it with

python tools/test_shadownet.py --image_path PATH/TO/IMAGE 
--weights_path PATH/TO/MODEL_WEIGHTS
--char_dict_path PATH/TO/CHAR_DICT_PATH 
--ord_map_dict_path PATH/TO/ORD_MAP_PATH

Test example images

Example test_01.jpg

Example image1

Example test_02.jpg

Example image2

Example test_03.jpg

Example image3

Training your own model

Data preparation

Download the whole synth90k dataset here And extract all th files into a root dir which should contain several txt file and several folders filled up with pictures. Then you need to convert the whole dataset into tensorflow records as follows

python tools/write_tfrecords 
--dataset_dir PATH/TO/SYNTH90K_DATASET_ROOT_DIR
--save_dir PATH/TO/TFRECORDS_DIR

During converting all the source image will be scaled into (32, 100)

Training

For all the available training parameters, check global_configuration/config.py, then train your model with

python tools/train_shadownet.py --dataset_dir PATH/TO/YOUR/TFRECORDS
--char_dict_path PATH/TO/CHAR_DICT_PATH 
--ord_map_dict_path PATH/TO/ORD_MAP_PATH

If you wish, you can add more metrics to the training progress messages with --decode_outputs 1, but this will slow training down. You can also continue the training process from a snapshot with

python tools/train_shadownet.py --dataset_dir PATH/TO/YOUR/TFRECORDS
--weights_path PATH/TO/YOUR/PRETRAINED_MODEL_WEIGHTS
--char_dict_path PATH/TO/CHAR_DICT_PATH --ord_map_dict_path PATH/TO/ORD_MAP_PATH

If you has multiple gpus in your local machine you may use multiple gpu training to access a larger batch size input data. This will be supported as follows

python tools/train_shadownet.py --dataset_dir PATH/TO/YOUR/TFRECORDS
--char_dict_path PATH/TO/CHAR_DICT_PATH --ord_map_dict_path PATH/TO/ORD_MAP_PATH
--multi_gpus 1

The sequence distance is computed by calculating the distance between two sparse tensors so the lower the accuracy value is the better the model performs. The training accuracy is computed by calculating the character-wise precision between the prediction and the ground truth so the higher the better the model performs.

Tensorflow Serving

Thanks for Eldon's contribution of tensorflow service function:)

Since tensorflow model server is a very powerful tools to serve the DL model in industry environment. Here's a script for you to convert the checkpoints model file into tensorflow saved model which can be used with tensorflow model server to serve the CRNN model. If you can not run the script normally you may need to check if the checkpoint file path is correct in the bash script.

bash tfserve/export_crnn_saved_model.sh

To start the tensorflow model server you may check following script

bash tfserve/run_tfserve_crnn_gpu.sh

There are two different ways to test the python client of crnn model. First you may test the server via http/rest request by running

python tfserve/crnn_python_client_via_request.py ./data/test_images/test_01.jpg

Second you may test the server via grpc by running

python tfserve/crnn_python_client_via_grpc.py

Experiment

The original experiment run for 2000000 epochs, with a batch size of 32, an initial learning rate of 0.01 and exponential decay of 0.1 every 500000 epochs. During training the train loss dropped as follows

Training loss

The val loss dropped as follows

Validation_loss

2019.3.27 Updates

I have uploaded a newly trained crnn model on chinese dataset which can be found here. Sorry for not knowing the owner of the dataset. But thanks for his great work. If someone knows it you're welcome to let me know. The pretrained weights can be found here

Before start training you may need reorgnize the dataset's label information according to the synth90k dataset's format if you want to use the same data feed pip line mentioned above. Now I have reimplemnted a more efficient tfrecords writer which will accelerate the process of generating tfrecords file. You may refer to the code for details. Some information about training is listed bellow:

image size: (280, 32)

classes nums: 5824 without blank

sequence length: 70

training sample counts: 2733004

validation sample counts: 364401

testing sample counts: 546601

batch size: 32

training iter nums: 200000

init lr: 0.01

Test example images

Example test_01.jpg

Example image1

Example test_02.jpg

Example image2

Example test_03.jpg

Example image3

training tboard file

Training loss

The val loss dropped as follows

Validation_loss

2019.4.10 Updates

Add a small demo to recognize chinese pdf using the chinese crnn model weights. If you want to have a try you may follow the command:

cd CRNN_ROOT_REPO
python tools/recongnize_chinese_pdf.py -c ./data/char_dict/char_dict_cn.json 
-o ./data/char_dict/ord_map_cn.json --weights_path model/crnn_chinese/shadownet.ckpt 
--image_path data/test_images/test_pdf.png --save_path pdf_recognize_result.txt

You should see the same result as follows:

The left image is the recognize result displayed on console and the right image is the origin pdf image.

recognize_result_console

The left image is the recognize result written in local file and the right image is the origin pdf image. recognize_result_file

TODO

  • Add new model weights trained on the whole synth90k dataset
  • Add multiple gpu training scripts
  • Add new pretrained model on chinese dataset
  • Add an online toy demo
  • Add tensorflow service script

Acknowledgement

Please cite my repo CRNN_Tensorflow if you use it.

Contact

Scan the following QR to disscuss :) qr

Owner
MaybeShewill-CV
Engineer from Baidu
MaybeShewill-CV
It is a image ocr tool using the Tesseract-OCR engine with the pytesseract package and has a GUI.

OCR-Tool It is a image ocr tool made in Python using the Tesseract-OCR engine with the pytesseract package and has a GUI. This is my second ever pytho

Khant Htet Aung 4 Jul 11, 2022
A bot that extract text from images using the Tesseract OCR.

Text from image (OCR) @ocr_text_bot A simple bot to extract text from images. Usage What do I need? A AWS key configured locally, see here. NodeJS. I

Weverton Marques 4 Aug 06, 2021
Python Computer Vision from Scratch

This repository explores the variety of techniques commonly used to analyze and interpret images. It also describes challenging real-world applications where vision is being successfully used, both f

Milaan Parmar / Милан пармар / _米兰 帕尔马 221 Dec 26, 2022
Official PyTorch implementation for "Mixed supervision for surface-defect detection: from weakly to fully supervised learning"

Mixed supervision for surface-defect detection: from weakly to fully supervised learning [Computers in Industry 2021] Official PyTorch implementation

ViCoS Lab 169 Dec 30, 2022
📷 This repository is focused on having various feature implementation of OpenCV in Python.

📷 This repository is focused on having various feature implementation of OpenCV in Python. The aim is to have a minimal implementation of all OpenCV features together, under one roof.

Aditya Kumar Gupta 128 Dec 04, 2022
Controlling the computer volume with your hands // OpenCV

HandsControll-AI Controlling the computer volume with your hands // OpenCV Step 1 git clone https://github.com/Hayk-21/HandsControll-AI.git pip instal

Hayk 1 Nov 04, 2021
Um simples projeto para fazer o reconhecimento do captcha usado pelo jogo bombcrypto

CaptchaSolver - LEIA ISSO 😓 Para iniciar o codigo: pip install -r requirements.txt python captcha_solver.py Se você deseja pegar ver o resultado das

Kawanderson 50 Mar 21, 2022
Markup for note taking

Subtext: markup for note-taking Subtext is a text-based, block-oriented hypertext format. It is designed with note-taking in mind. It has a simple, pe

Gordon Brander 224 Jan 01, 2023
Code for the paper "Controllable Video Captioning with an Exemplar Sentence"

SMCG Code for the paper "Controllable Video Captioning with an Exemplar Sentence" Introduction We investigate a novel and challenging task, namely con

10 Dec 04, 2022
pyntcloud is a Python library for working with 3D point clouds.

pyntcloud is a Python library for working with 3D point clouds.

David de la Iglesia Castro 1.2k Jan 07, 2023
Histogram specification using openCV in python .

histogram specification using openCV in python . Have to input miu and sigma to draw gausssian distribution which will be used to map the input image . Example input can be miu = 128 sigma = 30

Tamzid hasan 6 Nov 17, 2021
Document Image Dewarping

Document image dewarping using text-lines and line Segments Abstract Conventional text-line based document dewarping methods have problems when handli

Taeho Kil 268 Dec 23, 2022
Handwritten Number Recognition using CNN and Character Segmentation

Handwritten-Number-Recognition-With-Image-Segmentation Info About this repository This Repository is aimed at reading handwritten images of numbers an

Sparsha Saha 17 Aug 25, 2022
Optical character recognition for Japanese text, with the main focus being Japanese manga

Manga OCR Optical character recognition for Japanese text, with the main focus being Japanese manga. It uses a custom end-to-end model built with Tran

Maciej Budyś 327 Jan 01, 2023
https://arxiv.org/abs/1904.01941

Character-Region-Awareness-for-Text-Detection- https://arxiv.org/abs/1904.01941 Train You can train SynthText data use python source/train_SynthText.p

DayDayUp 120 Dec 28, 2022
Automatically fishes for you while you are afk :)

Dank-memer-afk-script A simple and quick way to make easy money in Dank Memer! How to use Open a discord channel which has the Dank Memer bot enabled.

Pranav Doshi 9 Nov 11, 2022
Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition:

Multi-Type-TD-TSR Check it out on Source Code of our Paper: Multi-Type-TD-TSR Extracting Tables from Document Images using a Multi-stage Pipeline for

Pascal Fischer 178 Dec 27, 2022
基于Paddle框架的PSENet复现

PSENet-Paddle 基于Paddle框架的PSENet复现 本项目基于paddlepaddle框架复现PSENet,并参加百度第三届论文复现赛,将在2021年5月15日比赛完后提供AIStudio链接~敬请期待 AIStudio链接 参考项目: whai362-PSENet 环境配置 本项目

QuanHao Guo 4 Apr 24, 2022
textspotter - An End-to-End TextSpotter with Explicit Alignment and Attention

An End-to-End TextSpotter with Explicit Alignment and Attention This is initially described in our CVPR 2018 paper. Getting Started Installation Clone

Tong He 323 Nov 10, 2022
CVPR 2021 Oral paper "LED2-Net: Monocular 360˚ Layout Estimation via Differentiable Depth Rendering" official PyTorch implementation.

LED2-Net This is PyTorch implementation of our CVPR 2021 Oral paper "LED2-Net: Monocular 360˚ Layout Estimation via Differentiable Depth Rendering". Y

Fu-En Wang 83 Jan 04, 2023