keras复现场景文本检测网络CPTN: 《Detecting Text in Natural Image with Connectionist Text Proposal Network》;欢迎试用,关注,并反馈问题...

Overview

keras-ctpn

[TOC]

  1. 说明
  2. 预测
  3. 训练
  4. 例子
    4.1 ICDAR2015
    4.1.1 带侧边细化
    4.1.2 不带带侧边细化
    4.1.3 做数据增广-水平翻转
    4.2 ICDAR2017
    4.3 其它数据集
  5. toDoList
  6. 总结

说明

​ 本工程是keras实现的CPTN: Detecting Text in Natural Image with Connectionist Text Proposal Network . 本工程实现主要参考了keras-faster-rcnn ; 并在ICDAR2015和ICDAR2017数据集上训练和测试。

​ 工程地址: keras-ctpn

​ cptn论文翻译:CTPN.md

效果

​ 使用ICDAR2015的1000张图像训练在500张测试集上结果为:Recall: 37.07 % Precision: 42.94 % Hmean: 39.79 %; 原文中的F值为61%;使用了额外的3000张图像训练。

关键点说明:

a.骨干网络使用的是resnet50

b.训练输入图像大小为720*720; 将图像的长边缩放到720,保持长宽比,短边padding;原文是短边600;预测时使用1024*1024

c.batch_size为4, 每张图像训练128个anchor,正负样本比为1:1;

d.分类、边框回归以及侧边细化的损失函数权重为1:1:1;原论文中是1:1:2

e.侧边细化与边框回归选择一样的正样本anchor;原文中应该是分开选择的

f.侧边细化还是有效果的(注:网上很多人说没有啥效果)

g.由于有双向GRU,水平翻转会影响效果(见样例做数据增广-水平翻转)

h.随机裁剪做数据增广,网络不收敛

预测

a. 工程下载

git clone https://github.com/yizt/keras-ctpn

b. 预训练模型下载

​ ICDAR2015训练集上训练好的模型下载地址: google drive百度云盘 取码:wm47

c.修改配置类config.py中如下属性

	WEIGHT_PATH = '/tmp/ctpn.h5'

d. 检测文本

python predict.py --image_path image_3.jpg

评估

a. 执行如下命令,并将输出的txt压缩为zip包

python evaluate.py --weight_path /tmp/ctpn.100.h5 --image_dir /opt/dataset/OCR/ICDAR_2015/test_images/ --output_dir /tmp/output_2015/

b. 提交在线评估 将压缩的zip包提交评估,评估地址:http://rrc.cvc.uab.es/?ch=4&com=mymethods&task=1

训练

a. 训练数据下载

#icdar2013
wget http://rrc.cvc.uab.es/downloads/Challenge2_Training_Task12_Images.zip
wget http://rrc.cvc.uab.es/downloads/Challenge2_Training_Task1_GT.zip
wget http://rrc.cvc.uab.es/downloads/Challenge2_Test_Task12_Images.zip
#icdar2015
wget http://rrc.cvc.uab.es/downloads/ch4_training_images.zip
wget http://rrc.cvc.uab.es/downloads/ch4_training_localization_transcription_gt.zip
wget http://rrc.cvc.uab.es/downloads/ch4_test_images.zip
#icdar2017
wget -c -t 0 http://datasets.cvc.uab.es/rrc/ch8_training_images_1~8.zip
wget -c -t 0 http://datasets.cvc.uab.es/rrc/ch8_training_localization_transcription_gt_v2.zip
wget -c -t 0 http://datasets.cvc.uab.es/rrc/ch8_test_images.zip

b. resnet50与训练模型下载

wget https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5

c. 修改配置类config.py中,如下属性

	# 预训练模型
    PRE_TRAINED_WEIGHT = '/opt/pretrained_model/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'

    # 数据集路径
    IMAGE_DIR = '/opt/dataset/OCR/ICDAR_2015/train_images'
    IMAGE_GT_DIR = '/opt/dataset/OCR/ICDAR_2015/train_gt'

d.训练

python train.py --epochs 50

例子

ICDAR2015

带侧边细化

不带侧边细化

做数据增广-水平翻转

ICDAR2017

其它数据集

toDoList

  1. 侧边细化(已完成)
  2. ICDAR2017数据集训练(已完成)
  3. 检测文本行坐标映射到原图(已完成)
  4. 精度评估(已完成)
  5. 侧边回归,限制在边框内(已完成)
  6. 增加水平翻转(已完成)
  7. 增加随机裁剪(已完成)

总结

  1. ctpn对水平文字检测效果不错
  2. 整个网络对于数据集很敏感;在2017上训练的模型到2015上测试效果很不好;同样2015训练的在2013上测试效果也很差
  3. 推测由于双向GRU,网络有存储记忆的缘故?在使用随机裁剪作数据增广时网络不收敛,使用水平翻转时预测结果也水平对称出现
Owner
mick.yi
keyword:数据挖掘,深度学习,计算机视觉
mick.yi
A facial recognition program that plays a alarm (mp3 file) when a person i seen in the room. A basic theif using Python and OpenCV

Home-Security-Demo A facial recognition program that plays a alarm (mp3 file) when a person is seen in the room. A basic theif using Python and OpenCV

SysKey 4 Nov 02, 2021
ocroseg - This is a deep learning model for page layout analysis / segmentation.

ocroseg This is a deep learning model for page layout analysis / segmentation. There are many different ways in which you can train and run it, but by

NVIDIA Research Projects 71 Dec 06, 2022
Image processing is one of the most common term in computer vision

Image processing is one of the most common term in computer vision. Computer vision is the process by which computers can understand images and videos, and how they are stored, manipulated, and retri

Happy N. Monday 3 Feb 15, 2022
BoxToolBox is a simple python application built around the openCV library

BoxToolBox is a simple python application built around the openCV library. It is not a full featured application to guide you through the w

František Horínek 1 Nov 12, 2021
A python scripts that uses 3 different feature extraction methods such as SIFT, SURF and ORB to find a book in a video clip and project trailer of a movie based on that book, on to it.

A python scripts that uses 3 different feature extraction methods such as SIFT, SURF and ORB to find a book in a video clip and project trailer of a movie based on that book, on to it.

tooraj taraz 3 Feb 10, 2022
Here use convulation with sobel filter from scratch in opencv python .

Here use convulation with sobel filter from scratch in opencv python .

Tamzid hasan 2 Nov 11, 2021
Code for the "Sensing leg movement enhances wearable monitoring of energy expenditure" paper.

EnergyExpenditure Code for the "Sensing leg movement enhances wearable monitoring of energy expenditure" paper. Additional data for replicating this s

Patrick S 42 Oct 26, 2022
A tool combining EasyOCR and LaMa to automatically detect text and replace it with an inpainted background.

EasyLaMa (WIP) This is a tool combining EasyOCR and LaMa to automatically detect text and replace it with an inpainted background. Installation For GP

3 Sep 17, 2022
天池2021"全球人工智能技术创新大赛"【赛道一】:医学影像报告异常检测 - 第三名解决方案

天池2021"全球人工智能技术创新大赛"【赛道一】:医学影像报告异常检测 比赛链接 个人博客记录 目录结构 ├── final------------------------------------决赛方案PPT ├── preliminary_contest--------------------

19 Aug 17, 2022
Application that instantly translates sign-language to letters.

Sign Language Translator Project Description The main purpose of project is translating sign-language to letters. In accordance with this purpose we d

3 Sep 29, 2022
A dataset handling library for computer vision datasets in LOST-fromat

A dataset handling library for computer vision datasets in LOST-fromat

8 Dec 15, 2022
Text to QR-CODE

QR CODE GENERATO USING PYTHON Author : RAFIK BOUDALIA. Installation Use the package manager pip to install foobar. pip install pyqrcode Usage from tki

Rafik Boudalia 2 Oct 13, 2021
A buffered and threaded wrapper for the OpenCV VideoCapture object. Can speed up video decoding significantly. Supports

A buffered and threaded wrapper for the OpenCV VideoCapture object. Can speed up video decoding significantly. Supports "with"-syntax.

Patrice Matz 0 Oct 30, 2021
Repository of conference publications and source code for first-/ second-authored papers published at NeurIPS, ICML, and ICLR.

Repository of conference publications and source code for first-/ second-authored papers published at NeurIPS, ICML, and ICLR.

Daniel Jarrett 26 Jun 17, 2021
Introduction to Augmented Reality (AR) with Python 3 and OpenCV 4.2.

Introduction to Augmented Reality (AR) with Python 3 and OpenCV 4.2.

fernanda rodríguez 85 Jan 02, 2023
Turn images of tables into CSV data. Detect tables from images and run OCR on the cells.

Table of Contents Overview Requirements Demo Modules Overview This python package contains modules to help with finding and extracting tabular data fr

Eric Ihli 311 Dec 24, 2022
Source code of RRPN ---- Arbitrary-Oriented Scene Text Detection via Rotation Proposals

Paper source Arbitrary-Oriented Scene Text Detection via Rotation Proposals https://arxiv.org/abs/1703.01086 News We update RRPN in pytorch 1.0! View

428 Nov 22, 2022
Camera Intrinsic Calibration and Hand-Eye Calibration in Pybullet

This repository is mainly for camera intrinsic calibration and hand-eye calibration. Synthetic experiments are conducted in PyBullet simulator. 1. Tes

CAI Junhao 7 Oct 03, 2022
Pixel art search engine for opengameart

Pixel Art Reverse Image Search for OpenGameArt What does the final search look like? The final search with an example can be found here. It looks like

Eivind Magnus Hvidevold 92 Nov 06, 2022
Thresholding-and-masking-using-OpenCV - Image Thresholding is used for image segmentation

Image Thresholding is used for image segmentation. From a grayscale image, thresholding can be used to create binary images. In thresholding we pick a threshold T.

Grace Ugochi Nneji 3 Feb 15, 2022