Rotated Box Is Back : Accurate Box Proposal Network for Scene Text Detection

Overview

Rotated Box Is Back : Accurate Box Proposal Network for Scene Text Detection

overview

This material is supplementray code for paper accepted in ICDAR 2021

  1. We highly recommend to use docker image because our model contains custom operation which depends on framework and cuda version.
  2. We provide trained model for ICDAR 2017, 2013 which is in final_checkpoint_ch8 and for ICDAR 2015 which is in final_checkpoint_ch4
  3. This code is mainly focused on inference. To train our model, training gpu like V100 is needed. please check our paper in detail.

REQUIREMENT

  1. Nvidia-docker
  2. Tensorflow 1.14
  3. Miminum GPU requirement : NVIDIA GTX 1080TI

INSTALLATION

  • Make docker image and container
docker build --tag rbimage ./dockerfile
docker run --runtime=nvidia --name rbcontainer -v /rotated-box-is-back-path:/rotated-box-is-back -i -t rbimage /bin/bash
  • build custom operations in container
cd /rotated-box-is-back/nms 
cmake ./
make
./shell.sh

SAMPLE IMAGE INFERENCE

cd /rotated-box-is-back/
python viz.py --test_data_path=./sample --checkpoint_path=./final_checkpoint_ch8 --output_dir=./sample_result  --thres 0.6 --min_size=1600 --max_size=2000

ICDAR 2017 INFERENCE

  1. please replace icdar_testset_path to your-icdar-2017-testset-folder path.
python viz.py --test_data_path=icdar_testset_path --checkpoint_path=./final_checkpoint_ch8 --output_dir=./ic17  --thres 0.6 --min_size=1600 --max_size=2000

ICDAR 2015 INFERENCE

  1. please replace icdar_testset_path to your-icdar-2015-testset-folder path.
  2. To converting evalutation format. Convert result text file like below
python viz.py --test_data_path=icdar_testset_path --checkpoint_path=./final_checkpoint_ch4 --output_dir=./ic15  --thres 0.7 --min_size=1100 --max_size=2000
python text_postprocessing.py -i=./ic15/ -o=./ic15_format/ -e True

ICDAR 2013 INFERENCE

  1. please replace icdar_testset_path to your-icdar-2013-testset-folder path.
  2. To converting evalutation format. Convert result text file like below
python viz.py --test_data_path=icdar_testset_path --checkpoint_path=./final_checkpoint_ch8 --output_dir=./ic13  --thres 0.55 --min_size=700 --max_size=900
python text_postprocessing.py -i=./ic13/ -o=./ic13_format/ -e True -m rec

EVALUATION TABLE

IC13 IC15 IC17
P R F P R F P R F
95.9 89.1 92.4 89.7 84.2 86.9 83.4 68.2 75.0

TRAINING

  1. It can be trained below command line
python train_refine_estimator.py --input_size=1024 --batch_size=2 --checkpoint_path=./finetuning --training_data_path=your-image-path --training_gt_path=your-gt-path  --learning_rate=0.00001 --max_epochs=500  --save_summary_steps=1000 --warmup_path=./final_checkpoint_ch8

ACKNOWLEDGEMENT

This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 1711125972, Audio-Visual Perception for Autonomous Rescue Drones).

CITATION

If you found it is helpfull for your research, please cite:

Lee J., Lee J., Yang C., Lee Y., Lee J. (2021) Rotated Box Is Back: An Accurate Box Proposal Network for Scene Text Detection. In: Lladós J., Lopresti D., Uchida S. (eds) Document Analysis and Recognition – ICDAR 2021. ICDAR 2021. Lecture Notes in Computer Science, vol 12824. Springer, Cham. https://doi.org/10.1007/978-3-030-86337-1_4

You might also like...
[CVPR 2022] Back To Reality: Weak-supervised 3D Object Detection with Shape-guided Label Enhancement
[CVPR 2022] Back To Reality: Weak-supervised 3D Object Detection with Shape-guided Label Enhancement

Back To Reality: Weak-supervised 3D Object Detection with Shape-guided Label Enhancement Announcement 🔥 We have not tested the code yet. We will fini

This repository contains the code for "Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP".

Self-Diagnosis and Self-Debiasing This repository contains the source code for Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based

A pytorch-version implementation codes of paper:
A pytorch-version implementation codes of paper: "BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation"

BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation A pytorch-version implementation

Code for CVPR 2021 oral paper
Code for CVPR 2021 oral paper "Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts"

Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts The rapid progress in 3D scene understanding has come with growing dem

 Neural Scene Graphs for Dynamic Scene (CVPR 2021)
Neural Scene Graphs for Dynamic Scene (CVPR 2021)

Implementation of Neural Scene Graphs, that optimizes multiple radiance fields to represent different objects and a static scene background. Learned representations can be rendered with novel object compositions and views.

A weakly-supervised scene graph generation codebase. The implementation of our CVPR2021 paper ``Linguistic Structures as Weak Supervision for Visual Scene Graph Generation''
A weakly-supervised scene graph generation codebase. The implementation of our CVPR2021 paper ``Linguistic Structures as Weak Supervision for Visual Scene Graph Generation''

README.md shall be finished soon. WSSGG 0 Overview 1 Installation 1.1 Faster-RCNN 1.2 Language Parser 1.3 GloVe Embeddings 2 Settings 2.1 VG-GT-Graph

Official PyTorch code of DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization (ICCV 2021 Oral).
Official PyTorch code of DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization (ICCV 2021 Oral).

DeepPanoContext (DPC) [Project Page (with interactive results)][Paper] DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context G

Code for the paper
Code for the paper "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021)

MASTER-PyTorch PyTorch reimplementation of "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021). This projec

This project is a re-implementation of MASTER: Multi-Aspect Non-local Network for Scene Text Recognition by MMOCR
This project is a re-implementation of MASTER: Multi-Aspect Non-local Network for Scene Text Recognition by MMOCR

This project is a re-implementation of MASTER: Multi-Aspect Non-local Network for Scene Text Recognition by MMOCR,which is an open-source toolbox based on PyTorch. The overall architecture will be shown below.

Owner
NCSOFT
NCSOFT Open Sources
NCSOFT
Omnidirectional Scene Text Detection with Sequential-free Box Discretization (IJCAI 2019). Including competition model, online demo, etc.

Box_Discretization_Network This repository is built on the pytorch [maskrcnn_benchmark]. The method is the foundation of our ReCTs-competition method

Yuliang Liu 266 Nov 24, 2022
Pytorch re-implementation of Paper: SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition (CVPR 2022)

SwinTextSpotter This is the pytorch implementation of Paper: SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text R

mxin262 183 Jan 3, 2023
A unofficial pytorch implementation of PAN(PSENet2): Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network

Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network Requirements pytorch 1.1+ torchvision 0.3+ pyclipper opencv3 gcc

zhoujun 400 Dec 26, 2022
CVPR2021: Temporal Context Aggregation Network for Temporal Action Proposal Refinement

Temporal Context Aggregation Network - Pytorch This repo holds the pytorch-version codes of paper: "Temporal Context Aggregation Network for Temporal

Zhiwu Qing 63 Sep 27, 2022
git《FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding》(CVPR 2021) GitHub: [fig8]

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding (CVPR 2021) This repo contains the implementation of our state-of-the-art fewshot ob

null 233 Dec 29, 2022
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud, CVPR 2019.

PointRCNN PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud Code release for the paper PointRCNN:3D Object Proposal Generation a

Shaoshuai Shi 1.5k Dec 27, 2022
[TIP 2020] Multi-Temporal Scene Classification and Scene Change Detection with Correlation based Fusion

Multi-Temporal Scene Classification and Scene Change Detection with Correlation based Fusion Code for Multi-Temporal Scene Classification and Scene Ch

Lixiang Ru 33 Dec 12, 2022
Pytorch implementation of Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors

Make-A-Scene - PyTorch Pytorch implementation (inofficial) of Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors (https://arxiv.org/

Casual GAN Papers 259 Dec 28, 2022
A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution (CVPR2022)

A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution (CVPR2022) https://arxiv.org/abs/2203.09388 Jianqi Ma, Zheto

MA Jianqi, shiki 104 Jan 5, 2023
(CVPR 2021) Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds

BRNet Introduction This is a release of the code of our paper Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds,

null 86 Oct 5, 2022