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
Open Source Differentiable Computer Vision Library for PyTorch

Kornia is a differentiable computer vision library for PyTorch. It consists of a set of routines and differentiable modules to solve generic computer

kornia 7.6k Jan 04, 2023
Distort a video using Seam Carving (video) and Vibrato effect (sound)

Distort videos Applies a Seam Carving algorithm (aka liquid rescale) on every frame of a video, and a vibrato effect on the audio to distort the video

AlexZeGamer 6 Dec 06, 2022
With the virtual keyboard, you can write on the real time images by combining the thumb and index fingers on the letter you want.

Virtual Keyboard With the virtual keyboard, you can write on the real time images by combining the thumb and index fingers on the letter you want. At

Güldeniz Bektaş 5 Jan 23, 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
This project proposes a camera vision based cursor control system, using hand moment captured from a webcam through a landmarks of hand by using Mideapipe module

This project proposes a camera vision based cursor control system, using hand moment captured from a webcam through a landmarks of hand by using Mideapipe module

Chandru 2 Feb 20, 2022
Using Opencv ,based on Augmental Reality(AR) and will show the feature matching of image and then by finding its matching

Using Opencv ,this project is based on Augmental Reality(AR) and will show the feature matching of image and then by finding its matching ,it will just mask that image . This project ,if used in cctv

1 Feb 13, 2022
OpenCVを用いたカメラキャリブレーションのサンプルです。2021/06/21時点でPython実装のある3種類(通常カメラ向け、魚眼レンズ向け(fisheyeモジュール)、全方位カメラ向け(omnidirモジュール))について用意しています。

OpenCV-CameraCalibration-Example FishEyeCameraCalibration.mp4 OpenCVを用いたカメラキャリブレーションのサンプルです 2021/06/21時点でPython実装のある以下3種類について用意しています。 通常カメラ向け 魚眼レンズ向け(

KazuhitoTakahashi 34 Nov 17, 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
一款基于Qt与OpenCV的仿真数字示波器

一款基于Qt与OpenCV的仿真数字示波器

郭赟 4 Nov 02, 2022
Rotational region detection based on Faster-RCNN.

R2CNN_Faster_RCNN_Tensorflow Abstract This is a tensorflow re-implementation of R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detecti

UCAS-Det 581 Nov 22, 2022
This is a GUI program which consist of 4 OpenCV projects

Tkinter-OpenCV Project Using Tkinter, Opencv, Mediapipe This is a python GUI program using Tkinter which consist of 4 OpenCV projects 1. Finger Counte

Arya Bagde 3 Feb 22, 2022
A python script based on opencv and paddleocr, which can automatically pick up tasks, make cookies, and receive rewards in the Destiny 2 Dawning Oven

A python script based on opencv and paddleocr, which can automatically pick up tasks, make cookies, and receive rewards in the Destiny 2 Dawning Oven

1 Dec 22, 2021
Lightning Fast Language Prediction 🚀

whatthelang Lightning Fast Language Prediction 🚀 Dependencies The dependencies can be installed using the requirements.txt file: $ pip install -r req

Indix 152 Oct 16, 2022
Perspective recovery of text using transformed ellipses

unproject_text Perspective recovery of text using transformed ellipses. See full writeup at https://mzucker.github.io/2016/10/11/unprojecting-text-wit

Matt Zucker 111 Nov 13, 2022
A python programusing Tkinter graphics library to randomize questions and answers contained in text files

RaffleOfQuestions Um programa simples em python, utilizando a biblioteca gráfica Tkinter para randomizar perguntas e respostas contidas em arquivos de

Gabriel Ferreira Rodrigues 1 Dec 16, 2021
Computer vision applications project (Flask and OpenCV)

Computer Vision Applications Project This project is at it's initial phase. This is all about the implementation of different computer vision techniqu

Suryam Thapa 1 Jan 26, 2022
Open Source Computer Vision Library

OpenCV: Open Source Computer Vision Library Resources Homepage: https://opencv.org Courses: https://opencv.org/courses Docs: https://docs.opencv.org/m

OpenCV 65.7k Jan 03, 2023
When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework (CVPR 2021 oral)

MTLFace This repository contains the PyTorch implementation and the dataset of the paper: When Age-Invariant Face Recognition Meets Face Age Synthesis

Hzzone 120 Jan 05, 2023
Fine tuning keras-ocr python package with custom synthetic dataset from scratch

OCR-Pipeline-with-Keras The keras-ocr package generally consists of two parts: a Detector and a Recognizer: Detector is responsible for creating bound

Eugene 1 Jan 05, 2022
Detect textlines in document images

Textline Detection Detect textlines in document images Introduction This tool performs border, region and textline detection from document image data

QURATOR-SPK 70 Jun 30, 2022