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
Generic framework for historical document processing

dhSegment dhSegment is a tool for Historical Document Processing. Its generic approach allows to segment regions and extract content from different ty

Digital Humanities Laboratory 343 Dec 24, 2022
Contextual speed detection for python

Speed Prediction using Optical Flow and 2D CNN About the challenge: Comma.AI Speed Challenge This challenge was developed by Comma.AI to predict the s

Mahimana Bhatt 2 Dec 16, 2021
Resizing Canny Countour In Python

Resizing_Canny_Countour Install Visual Studio Code , https://code.visualstudio.com/download Select Python and install with terminal( pip install openc

Walter Ng 1 Nov 07, 2021
~1000 book pages + OpenCV + python = page regions identified as paragraphs, lines, images, captions, etc.

cosc428-structor I had an open-ended Computer Vision assignment to complete, and an out-of-copyright book that I wanted to turn into an ebook. Convent

Chad Oliver 45 Dec 06, 2022
A python screen recorder for low-end computers, provides high quality video output.

RecorderX - v1.0 A screen recorder made in Python with the help of OpenCv, it has ability to record your screen in high quality. No matter what your P

Priyanshu Jindal 4 Nov 10, 2021
CellProfiler is a open-source application for biological image analysis

CellProfiler is a free open-source software designed to enable biologists without training in computer vision or programming to quantitatively measure phenotypes from thousands of images automaticall

CellProfiler 732 Dec 23, 2022
This is a real life mario project using python and mediapipe

real-life-mario This is a real life mario project using python and mediapipe How to run to run this just run - realMario.py file requirements This req

Programminghut 42 Dec 22, 2022
This repository contains codes on how to handle mouse event using OpenCV

Handling-Mouse-Click-Events-Using-OpenCV This repository contains codes on how t

Happy N. Monday 3 Feb 15, 2022
Python rubik's cube solver

This program makes a 3D representation of a rubiks cube and solves it step by step.

Pablo QB 4 May 29, 2022
Run tesseract with the tesserocr bindings with @OCR-D's interfaces

ocrd_tesserocr Crop, deskew, segment into regions / tables / lines / words, or recognize with tesserocr Introduction This package offers OCR-D complia

OCR-D 38 Oct 14, 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
🖺 OCR using tensorflow with attention

tensorflow-ocr 🖺 OCR using tensorflow with attention, batteries included Installation git clone --recursive http://github.com/pannous/tensorflow-ocr

646 Nov 11, 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
A toolbox of scene text detection and recognition

FudanOCR This toolbox contains the implementations of the following papers: Scene Text Telescope: Text-Focused Scene Image Super-Resolution [Chen et a

FudanVIC Team 170 Dec 26, 2022
This tool will help you convert your text to handwriting xD

So your teacher asked you to upload written assignments? Hate writing assigments? This tool will help you convert your text to handwriting xD

Saurabh Daware 4.2k Jan 07, 2023
PianoVisuals - Create background videos synced with piano music using opencv

Steps Record piano video Use Neural Network to do body segmentation (video matti

Solbiati Alessandro 4 Jan 24, 2022
Handwritten Text Recognition (HTR) system implemented with TensorFlow (TF) and trained on the IAM off-line HTR dataset. This Neural Network (NN) model recognizes the text contained in the images of segmented words.

Handwritten-Text-Recognition Handwritten Text Recognition (HTR) system implemented with TensorFlow (TF) and trained on the IAM off-line HTR dataset. T

27 Jan 08, 2023
A curated list of promising OCR resources

Call for contributor(paper summary,dataset generation,algorithm implementation and any other useful resources) awesome-ocr A curated list of promising

wanghaisheng 1.6k Jan 04, 2023
a deep learning model for page layout analysis / segmentation.

OCR Segmentation a deep learning model for page layout analysis / segmentation. dependencies tensorflow1.8 python3 dataset: uw3-framed-lines-degraded-

99 Dec 12, 2022
一键翻译各类图片内文字

一键翻译各类图片内文字 针对群内、各个图站上大量不太可能会有人去翻译的图片设计,让我这种日语小白能够勉强看懂图片 主要支持日语,不过也能识别汉语和小写英文 支持简单的涂白和嵌字

574 Dec 28, 2022