Code for the paper STN-OCR: A single Neural Network for Text Detection and Text Recognition

Overview

STN-OCR: A single Neural Network for Text Detection and Text Recognition

This repository contains the code for the paper: STN-OCR: A single Neural Network for Text Detection and Text Recognition

Please note that we refined our approach and released new source code. You can find the code here

Please use the new code, if you want to experiment with FSNS like data and our approach. It should also be easy to redo the text recognition experiments with the new code, although we did not release any code for that.

Structure of the repository

The folder datasets contains code related to datasets used in the paper. datasets/svhn contains several scripts that can be used to create svhn based ground truth files as used in our experiments reported in section 4.2., please see the readme in this folder on how to use the scripts. datasets/fsns contains scripts that can be used to first download the fsns dataset, second extract the images from the downloaded files and third restructure the contained gt files.

The folder mxnet contains all code used for training our networks.

Installation

In order to use the code you will need the following software environment:

  1. Install python3 (the code might work with python2, too, but this is untested)
  2. it might be a good idea to use a virtualenv
  3. install all requirements with pip install -r requirements.txt
  4. clone and install warp-ctc from here
  5. go into the folder mxnet/metrics/ctc and run python setup.py build_ext --inplace
  6. clone the mxnet repository
  7. checkout the tag v0.9.3
  8. add the warpctc plugin to the project by enabling it in the file config.mk
  9. compile mxnet
  10. install the python bindings of mxnet
  11. You should be ready to go!

Training

You can use this code to train models for three different tasks.

SVHN House Number Recognition

The file train_svhn.py is the entry point for training a network using our purpose build svhn datasets. The file as such is ready to train a network capable of finding a single house number placed randomly on an image.

Example: centered_image

In order to do this, you need to follow these steps:

  1. Download the datasets

  2. Locate the folder generated/centered

  3. open train.csv and adapt the paths of all images to the path on your machine (do the same with valid.csv)

  4. make sure to prepare your environment as described in installation

  5. start the training by issuing the following command:

    python train_svhn.py <path to train.csv> <path to valid.csv> --gpus <gpu id you want to use> --log-dir <where to save the logs> -b <batch size you want ot use> --lr 1e-5 --zoom 0.5 --char-map datasets/svhn/svhn_char_map.json

  6. Wait and enjoy.

If you want to do experiments on more challenging images you might need to update some parts of the code in train_svhn.py. The parts you might want to update are located around line 40 in this file. Here you can change the max. number of house numbers in the image (num_timesteps), the maximum number of characters per house number (labels_per_timestep), the number of rnn layers to use for predicting the localization num_rnn_layers and whether to use a blstm for predicting the localization or not use_blstm.

A quite more challenging dataset is contained in the folder medium_two_digits, or medium in the datasets folder. Example: 2_digits_more_challenge

If you want to follow our experiments with svhn numbers placed in a regular grid you'll need to do the following:

  1. Download the datasets
  2. Locate the folder generated/easy
  3. open train.csv and adapt the paths of all images to the path on your machine (do the same with valid.csv)
  4. set num_timesteps and labels_per_timestep to 4 in train_svhn.py
  5. start the training using the following command: python train_svhn.py <path to train.csv> <path to valid.csv> --gpus <gpu id you want to use> --log-dir <where to save the logs> -b <batch size you want ot use> --lr 1e-5
  6. If you are lucky it will work ;)

Text Recognition

Following our text recognition experiments might be a little difficult, because we can not offer the entire dataset used by us. But it is possible to perform the experiments based on the Synth-90k dataset provided by Jaderberg et al. here. After downloading and extracting this file you'll need to adapt the groundtruth file provided with this dataset to fit to the format used by our code. Our format is quite easy. You need to create a csv file with tabular separated values. The first column is the absolute path to the image and the rest of the line are the labels corresponding to this image.

To train the network you can use the train_text_recognition.py script. You can start this script in a similar manner to the train_svhn.py script.

FSNS

In order to redo our experiments on the FSNS dataset you need to perform the following steps:

  1. Download the fsns dataset using the download_fsns.py script located in datasets/fsns

  2. Extract the individual images using the tfrecord_to_image.py script located in datasets/fsns/tfrecord_utils (you will need to install tensorflow for doing that)

  3. Use the transform_gt.py script to transform the original fsns groundtruth, which is based on a single line to a groundtruth containing labels for each word individually. A possible usage of the transform_gt.py script could look like this:

    python transform_gt.py <path to original gt> datasets/fsns/fsns_char_map.json <path to gt that shall be generated>

  4. Because MXNet expects the blank label to be 0 for the training with CTC Loss, you have to use the swap_classes.py script in datasets/fsns and swap the class for space and blank in the gt, by issuing:

    python swap_classes.py <original gt> <swapped gt> 0 133

  5. After performing these steps you should be able to run the training by issuing:

    python train_fsns.py <path to generated train gt> <path to generated validation gt> --char-map datases/fsns/fsns_char_map.json --blank-label 0

Observing the Training Progress

We've added a nice script that makes it possible to see how well the network performs at every step of the training. This progress is normally plotted to disk for each iteration and can later on be used to create animations of the train progress (you can use the create_gif.py and create_video.py scripts located in mxnet/utils for this purpose). Besides this normal plotting to disk it is also possible to directly see this progress while the training is running. In order to see this you have to do the following:

  1. start the show_progress.py script in mxnet/utils

  2. start the training with the following additional command line params:

    --send-bboxes --ip <localhost, or remote ip if you are working on a remote machine> --port <the port the show_progress.py script is running on (default is 1337)

  3. enjoy!

This tool is especially helpful in determining whether the network is learning anything or not. We recommend that you always use this tool while training.

Evaluation

If you want to evaluate already trained models you can use the evaluation scripts provided in the mxnet folder. For evaluating a model you need to do the following:

  1. train or download a model

  2. choose the correct evaluation script an adapt it, if necessary (take care in case you are fiddling around with the amount of timesteps and number of RNN layers)

  3. Get the dataset you want to evaluate the model on and adapt the groundtruth file to fit the format expected by our software. The format expected by our software is defined as a csv (tab separated) file that looks like that: <absolute path to image> \t <numerical labels each label separated from the other by \t>

  4. run the chosen evaluation script like so

    python eval_<type>_model.py <path to model dir>/<prefix of model file> <number of epoch to test> <path to evaluation gt> <path to char map>

You can use eval_svhn_model.py for evaluating a model trained with CTC on the original svhn dataset, the eval_text_recognition_model.py script for evaluating a model trained for text recognition, and the eval_fsns_model.py for evaluating a model trained on the FSNS dataset.

License

This Code is licensed under the GPLv3 license. Please see further details in LICENSE.md.

Citation

If you are using this Code please cite the following publication:

@article{bartz2017stn,
  title={STN-OCR: A single Neural Network for Text Detection and Text Recognition},
  author={Bartz, Christian and Yang, Haojin and Meinel, Christoph},
  journal={arXiv preprint arXiv:1707.08831},
  year={2017}
}

A short note on code quality

The code contains a huge amount of workarounds around MXNet, as we were not able to find any easier way to do what we wanted to do. If you know a better way, pease let us know, as we would like to have code that is better understandable, as now.

text detection mainly based on ctpn model in tensorflow, id card detect, connectionist text proposal network

text-detection-ctpn Scene text detection based on ctpn (connectionist text proposal network). It is implemented in tensorflow. The origin paper can be

Shaohui Ruan 3.3k Dec 30, 2022
This repository lets you train neural networks models for performing end-to-end full-page handwriting recognition using the Apache MXNet deep learning frameworks on the IAM Dataset.

Handwritten Text Recognition (OCR) with MXNet Gluon These notebooks have been created by Jonathan Chung, as part of his internship as Applied Scientis

Amazon Web Services - Labs 422 Jan 03, 2023
Automatic Number Plate Recognition (ANPR) is a highly accurate system capable of reading vehicle number plates without human intervention

ANPR ANPR is therefore the underlying technology used to find a vehicle license/number plate and it, in turn, supplies this information to a next stag

Melih Emin Kılıçoğlu 1 Jan 09, 2022
Detect and fix skew in images containing text

Alyn Skew detection and correction in images containing text Image with skew Image after deskew Install and use via pip! Recommended way(using virtual

Kakul 230 Dec 21, 2022
Just a script for detecting the lanes in any car game (not just gta 5) with specific resolution and road design ( very basic and limited )

GTA-5-Lane-detection Just a script for detecting the lanes in any car game (not just gta 5) with specific resolution and road design ( very basic and

Danciu Georgian 4 Aug 01, 2021
Code release for Hu et al., Learning to Segment Every Thing. in CVPR, 2018.

Learning to Segment Every Thing This repository contains the code for the following paper: R. Hu, P. Dollár, K. He, T. Darrell, R. Girshick, Learning

Ronghang Hu 417 Oct 03, 2022
Convert scans of handwritten notes to beautiful, compact PDFs

Convert scans of handwritten notes to beautiful, compact PDFs

Matt Zucker 4.8k Jan 01, 2023
A program that takes in the hand gesture displayed by the user and translates ASL.

Interactive-ASL-Recognition Using the framework mediapipe made by google, OpenCV library and through self teaching, I was able to create a program tha

Riddhi Bajaj 3 Nov 22, 2021
Detect handwritten words in a text-line (classic image processing method).

Word segmentation Implementation of scale space technique for word segmentation as proposed by R. Manmatha and N. Srimal. Even though the paper is fro

Harald Scheidl 190 Jan 03, 2023
POT : Python Optimal Transport

This open source Python library provide several solvers for optimization problems related to Optimal Transport for signal, image processing and machine learning.

Python Optimal Transport 1.7k Jan 04, 2023
Python tool that takes the OCR.space JSON output as input and draws a text overlay on top of the image.

OCR.space OCR Result Checker = Draw OCR overlay on top of image Python tool that takes the OCR.space JSON output as input, and draws an overlay on to

a9t9 4 Oct 18, 2022
Python Computer Vision Aim Bot for Roblox's Phantom Forces

Python-Phantom-Forces-Aim-Bot Python Computer Vision Aim Bot for Roblox's Phanto

drag0ngam3s 2 Jul 11, 2022
TextBoxes: A Fast Text Detector with a Single Deep Neural Network https://github.com/MhLiao/TextBoxes 基于SSD改进的文本检测算法,textBoxes_note记录了之前整理的笔记。

TextBoxes: A Fast Text Detector with a Single Deep Neural Network Introduction This paper presents an end-to-end trainable fast scene text detector, n

zhangjing1 24 Apr 28, 2022
CNN+LSTM+CTC based OCR implemented using tensorflow.

CNN_LSTM_CTC_Tensorflow CNN+LSTM+CTC based OCR(Optical Character Recognition) implemented using tensorflow. Note: there is No restriction on the numbe

Watson Yang 356 Dec 08, 2022
Recognizing cropped text in natural images.

ASTER: Attentional Scene Text Recognizer with Flexible Rectification ASTER is an accurate scene text recognizer with flexible rectification mechanism.

Baoguang Shi 681 Jan 02, 2023
A real-time dolly zoom camera effect

Dolly-Zoom I've always been amazed by the gradual perspective change of dolly zoom, and I have some experience in python and OpenCV, so I decided to c

Dylan Kai Lau 52 Dec 08, 2022
BD-ALL-DIGIT - This Is Bangladeshi All Sim Cloner Tools

BANGLADESHI ALL SIM CLONER TOOLS INSTALL TOOL ON TERMUX $ apt update $ apt upgra

MAHADI HASAN AFRIDI 2 Jan 19, 2022
LEARN OPENCV IN 3 HOURS USING PYTHON - INCLUDING EXAMPLE PROJECTS

LEARN OPENCV IN 3 HOURS USING PYTHON - INCLUDING EXAMPLE PROJECTS

Murtaza Hassan 815 Dec 29, 2022
Captcha Recognition

The objective of this project is to recognize the target numbers in the captcha images correctly which would tell us how good or bad a captcha system has been built.

Mohit Kaushik 5 Feb 20, 2022
Code for CVPR2021 paper "Learning Salient Boundary Feature for Anchor-free Temporal Action Localization"

AFSD: Learning Salient Boundary Feature for Anchor-free Temporal Action Localization This is an official implementation in PyTorch of AFSD. Our paper

Tencent YouTu Research 146 Dec 24, 2022