# EAST : An Efficient and Accurate Scene Text Detector
### Introduction
This is a tensorflow implemention of EAST. I only reimplement the RBOX part of the paper, which achieves an F1 score
of 80.8 on the ICDAR 2015 dataset (which is about two points better than the result of pvanet in the paper, see http://rrc.cvc.uab.es/?ch=4&com=evaluation&task=1). The running speed is about 150ms (network) + 300ms (NMS) per image on a K40 card. The nms part is too slow because of the use of shapely in python, and can be further improved.
Thanks for the author's ([@zxytim](https://github.com/zxytim)) help!
Please site his [paper](https://arxiv.org/abs/1704.03155v2) if you find this useful.
### Contents
1. [Installation](#installation)
2. [Download](#download)
3. [Test](#train)
4. [Train](#test)
5. [Examples](#examples)
### Installation
1. I think any version of tensorflow version > 1.0 should be ok.
### Download
1. Models trained on ICDAR 2013 (training set) + ICDAR 2015 (training set): [BaiduYun link](http://pan.baidu.com/s/1jHWDrYQ)
2. Resnet V1 50 provided by tensorflow slim: [slim resnet v1 50](http://download.tensorflow.org/models/resnet_v1_50_2016_08_28.tar.gz)
### Train
If you want to train the model, you should provide the dataset path, in the dataset path, a separate gt text file should be provided for each image
and run
```
python multigpu_train.py --gpu_list=0 --input_size=512 --batch_size=14 --checkpoint_path=/tmp/east_icdar2015_resnet_v1_50_rbox/ \
--text_scale=512 --training_data_path=/data/ocr/icdar2015/ --geometry=RBOX --learning_rate=0.0001 --num_readers=24 \
--pretrained_model_path=/tmp/resnet_v1_50.ckpt
```
If you have more than one gpu, you can pass gpu ids to gpu_list
**Note: you should change the gt text file of icdar2015's filename to img_\*.txt instead of gt_img_\*.txt(or you can change the code in icdar.py), and some extra characters should be removed from the file.**
### Test
run
```
python eval.py --test_data_path=/tmp/images/ --gpu_list=0 --checkpoint_path=/tmp/east_icdar2015_resnet_v1_50_rbox/ \
--output_path=/tmp/
```
a text file will be then written to the output path.
### Examples
Here is some test examples on icdar2015, enjoy the beautiful text boxes!
![image_1](Examples/img_2.jpg)
![image_2](Examples/img_10.jpg)
![image_3](Examples/img_14.jpg)
![image_4](Examples/img_26.jpg)
![image_5](Examples/img_75.jpg)
Please let me know if you encounter any issues(my email boostczc@gmail dot com).
自然场景下文字识别(EAST AND RCNN(CTC))
需积分: 50 183 浏览量
2019-04-14
14:17:17
上传
评论 5
收藏 1.16MB RAR 举报
thanghan20
- 粉丝: 12
- 资源: 6
最新资源
- Screenshot_20240427_031602.jpg
- 网页PDF_2024年04月26日 23-46-14_QQ浏览器网页保存_QQ浏览器转格式(6).docx
- 直接插入排序,冒泡排序,直接选择排序.zip
- 在排序2的基础上,再次对快排进行优化,其次增加快排非递归,归并排序,归并排序非递归版.zip
- 实现了7种排序算法.三种复杂度排序.三种nlogn复杂度排序(堆排序,归并排序,快速排序)一种线性复杂度的排序.zip
- 冒泡排序 直接选择排序 直接插入排序 随机快速排序 归并排序 堆排序.zip
- 课设-内部排序算法比较 包括冒泡排序、直接插入排序、简单选择排序、快速排序、希尔排序、归并排序和堆排序.zip
- Python排序算法.zip
- C语言实现直接插入排序、希尔排序、选择排序、冒泡排序、堆排序、快速排序、归并排序、计数排序,并带图详解.zip
- 常用工具集参考用于图像等数据处理
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈