https://github.com/mohammadshabazuddin/secure-image-classification---deep-learning-for-image-based-authentication

This project implements a CNN to classify CAPTCHA images. The code preprocesses images, applies Otsu's thresholding, and uses morphological transformations for character separation. The CNN model includes convolutional, batch normalization, dropout, and fully connected layers. Training, validation, and testing are performed on labeled datasets.
https://github.com/mohammadshabazuddin/secure-image-classification---deep-learning-for-image-based-authentication

keras numpy opencv pandas pil python tensorflow

Last synced: 6 days ago
JSON representation

This project implements a CNN to classify CAPTCHA images. The code preprocesses images, applies Otsu's thresholding, and uses morphological transformations for character separation. The CNN model includes convolutional, batch normalization, dropout, and fully connected layers. Training, validation, and testing are performed on labeled datasets.

• Host: GitHub
• URL: https://github.com/mohammadshabazuddin/secure-image-classification---deep-learning-for-image-based-authentication
• Owner: MohammadShabazuddin
• Created: 2023-04-09T19:58:09.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-05-30T19:13:37.000Z (9 months ago)
• Last Synced: 2024-12-24T02:36:37.152Z (about 2 months ago)
• Topics: keras, numpy, opencv, pandas, pil, python, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 36 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Secure CAPTCHA Image Classifier 🤖🔍

## Overview

This project implements a Convolutional Neural Network (CNN) to classify CAPTCHA images. The code preprocesses images, applies Otsu's thresholding, and uses morphological transformations for character separation. The CNN model includes convolutional, batch normalization, dropout, and fully connected layers. Training, validation, and testing are performed on labeled datasets. Predictions are saved in a CSV file.

## Technologies Used

- Python 🐍

- TensorFlow, Keras 🧠

- NumPy, pandas 📊

- OpenCV, PIL 🖼️

## Usage

1. Install dependencies: `pip install -r requirements.txt`

2. Run the main script: `python image_classifier.py`

## Model Architecture

- Convolutional layers 🎛️

- Batch normalization 📊

- Dropout layers 🚀

- Fully connected layers 🔗

## Training

- 30 epochs 🕒

- Adam optimizer 🔄

- Sparse categorical crossentropy loss 📉

- Accuracy metrics 📈

## Prediction

- Test set predictions 🔮

- Save results in `submission12.csv` 📄

## Directory Structure

```

- /kaggle/input/fiu-cap5610-spring-2023

  - images/

    - (CAPTCHA images)

  - train.csv

  - test.csv

- image_classifier.py

- submission12.csv

- README.md

```

## Contact

_Connect with me through various portals :_

  

    

    Social Media

    Username

    Link

  

  

    

    Email

    [email protected]

    Email

  

  

    

    LinkedIn

    Shabazuddin Mohammad

    LinkedIn

  

  

    

    Instagram

    shabaz_uddin

    Instagram

  

  

    

    Facebook

    Shabaz

    Facebook

  

  

    

    Twitter

    shabazuddin786

    Twitter

  

I'm always open to collaboration and new opportunities! Feel free to reach out and connect with me. 🌟

Feel free to explore and contribute! 🚀