Deep LearningImage Captcha 2

Overview

滑动验证码深度学习识别

本项目使用深度学习 YOLOV3 模型来识别滑动验证码缺口,基于 https://github.com/eriklindernoren/PyTorch-YOLOv3 修改。

只需要几百张缺口标注图片即可训练出精度高的识别模型,识别效果样例:

克隆项目

运行命令:

git clone https://github.com/Python3WebSpider/DeepLearningSlideCaptcha.git

数据准备

使用 LabelImg 工具标注自行标注一批数据,大约 200 张以上即可训练出不错的效果。

LabelImg:https://github.com/tzutalin/labelImg

标注要求:

  • 圈出验证码目标滑块区域的完整完整矩形,无需标注源滑块。
  • 目标矩形命名为 target 这个类别。
  • 建议使用 LabelImg 的快捷键提高标注效率。

环境准备

建议在 GPU 环境和虚拟 Python 环境下执行如下命令:

pip3 install -r requirements.txt

预训练模型下载

YOLOV3 的训练要加载预训练模型才能有不错的训练效果,预训练模型下载:

bash prepare.sh

下载完成之后会在 weights 文件夹下出现模型权重文件,供训练使用。

训练

本项目已经提供了标注好的数据集,在 data/captcha,可以直接使用。

如果要训练自己的数据,数据格式准备见:https://github.com/eriklindernoren/PyTorch-YOLOv3#train-on-custom-dataset

当前数据训练脚本:

bash train.sh

实测 P100 训练时长约 15 秒一个 epoch,大约几分钟即可训练出较好效果。

测试

训练完毕之后会在 checkpoints 文件夹生成 pth 文件,可直接使用模型来预测生成标注结果。

此时 checkpoints 文件夹会生成训练好的 pth 文件。

当前数据测试脚本:

sh detect.sh

该脚本会读取 captcha 下的 test 文件夹所有图片,并将处理后的结果输出到 test 文件夹。

运行结果样例:

Performing object detection:
        + Batch 0, Inference Time: 0:00:00.044223
        + Batch 1, Inference Time: 0:00:00.028566
        + Batch 2, Inference Time: 0:00:00.029764
        + Batch 3, Inference Time: 0:00:00.032430
        + Batch 4, Inference Time: 0:00:00.033373
        + Batch 5, Inference Time: 0:00:00.027861
        + Batch 6, Inference Time: 0:00:00.031444
        + Batch 7, Inference Time: 0:00:00.032110
        + Batch 8, Inference Time: 0:00:00.029131

Saving images:
(0) Image: 'data/captcha/test/captcha_4497.png'
        + Label: target, Conf: 0.99999
(1) Image: 'data/captcha/test/captcha_4498.png'
        + Label: target, Conf: 0.99999
(2) Image: 'data/captcha/test/captcha_4499.png'
        + Label: target, Conf: 0.99997
(3) Image: 'data/captcha/test/captcha_4500.png'
        + Label: target, Conf: 0.99999
(4) Image: 'data/captcha/test/captcha_4501.png'
        + Label: target, Conf: 0.99997
(5) Image: 'data/captcha/test/captcha_4502.png'
        + Label: target, Conf: 0.99999
(6) Image: 'data/captcha/test/captcha_4503.png'
        + Label: target, Conf: 0.99997
(7) Image: 'data/captcha/test/captcha_4504.png'
        + Label: target, Conf: 0.99998
(8) Image: 'data/captcha/test/captcha_4505.png'
        + Label: target, Conf: 0.99998

样例结果:

协议

本项目基于开源 GNU 协议 ,另外本项目不提供任何有关滑动轨迹相关模拟和 JavaScript 逆向分析方案。

本项目仅供学习交流使用,请勿用于非法用途,本人不承担任何法律责任。

如有侵权请联系个人删除,谢谢。

Owner
Python3WebSpider
Python3WebSpider
OpenCV-Erlang/Elixir bindings

evision [WIP] : OS : arch Build Status Ubuntu 20.04 arm64 Ubuntu 20.04 armv7 Ubuntu 20.04 s390x Ubuntu 20.04 ppc64le Ubuntu 20.04 x86_64 macOS 11 Big

Cocoa 194 Jan 05, 2023
Captcha Recognition

The objective of this project is to recognize the target numbers in the captcha images correctly which would tell us how good or bad a captcha system has been built.

Mohit Kaushik 5 Feb 20, 2022
Deskewing images with slanted content

skew_correction De-skewing images with slanted content by finding the deviation using Canny Edge Detection. To Run: In python 3.6, from deskew import

13 Aug 27, 2022
WACV 2022 Paper - Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching

Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching Code based on our WACV 2022 Accepted Paper: https://arxiv.org/pdf/

Andres 13 Dec 17, 2022
An easy to use an (hopefully useful) captcha solution for pyTelegramBotAPI

pyTelegramBotCAPTCHA An easy to use and (hopefully useful) image CAPTCHA soltion for pyTelegramBotAPI. Installation: pip install pyTelegramBotCAPTCHA

29 Dec 26, 2022
Convert scans of handwritten notes to beautiful, compact PDFs

Convert scans of handwritten notes to beautiful, compact PDFs

Matt Zucker 4.8k Jan 01, 2023
3点クリックで円を指定し、極座標変換を行うサンプルプログラム

click-warpPolar 3点クリックで円を指定し、極座標変換を行うサンプルプログラムです。 Requirements OpenCV 3.4.2 or Later Usage 実行方法は以下です。 起動後、マウスで3点をクリックし円を指定してください。 python click-warpPol

KazuhitoTakahashi 17 Dec 30, 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
EAST for ICPR MTWI 2018 Challenge II (Text detection of network images)

EAST_ICPR2018: EAST for ICPR MTWI 2018 Challenge II (Text detection of network images) Introduction This is a repository forked from argman/EAST for t

QichaoWu 49 Dec 24, 2022
✌️Using this you can control your PC/Laptop volume by Hand Gestures created with Python.

Hand Gesture Volume Controller ✋ Hand recognition 👆 Finger recognition 🔊 you can decrease and increase volume Demo Code Firstly I have created a Mod

Abbas Ataei 19 Nov 17, 2022
Creating of virtual elements of the graphical interface using opencv and mediapipe.

Virtual GUI Creating of virtual elements of the graphical interface using opencv and mediapipe. Element GUI Output Description Button By default the b

Aleksei 4 Jun 16, 2022
ISI's Optical Character Recognition (OCR) software for machine-print and handwriting data

VistaOCR ISI's Optical Character Recognition (OCR) software for machine-print and handwriting data Publications "How to Efficiently Increase Resolutio

ISI Center for Vision, Image, Speech, and Text Analytics 21 Dec 08, 2021
A tensorflow implementation of EAST text detector

EAST: An Efficient and Accurate Scene Text Detector Introduction This is a tensorflow re-implementation of EAST: An Efficient and Accurate Scene Text

2.9k Jan 02, 2023
scene-linear test images

Scene-Referred Image Collection A collection of OpenEXR Scene-Referred images, encoded as max 2048px width, DWAA 80 compression. All exrs are encoded

Gralk Klorggson 7 Aug 25, 2022
The first open-source library that detects the font of a text in a image.

Typefont Typefont is an experimental library that detects the font of a text in a image. Usage Import the main function and invoke it like in the foll

Vasile Pește 1.6k Feb 24, 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 our ICCV 2021 paper "DeepCAD: A Deep Generative Network for Computer-Aided Design Models"

DeepCAD This repository provides source code for our paper: DeepCAD: A Deep Generative Network for Computer-Aided Design Models Rundi Wu, Chang Xiao,

Rundi Wu 85 Dec 31, 2022
Text layer for bio-image annotation.

napari-text-layer Napari text layer for bio-image annotation. Installation You can install using pip: pip install napari-text-layer Keybindings and m

6 Sep 29, 2022
Morphological edge detection or object's boundary detection using erosion and dialation in OpenCV python

Morphologycal-edge-detection-using-erosion-and-dialation the task is to detect object boundary using erosion or dialation . Here, use the kernel or st

Tamzid hasan 3 Nov 25, 2022
A PyTorch implementation of ECCV2018 Paper: TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes

TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes A PyTorch implement of TextSnake: A Flexible Representation for Detecting

Prince Wang 417 Dec 12, 2022