AI vs Real Image Classifier

This project aims to distinguish between AI-generated and real images using a Convolutional Neural Network (CNN) model. The workflow is divided into three key stages:

1. Image Scraping: Collection of a diverse dataset of AI-generated and real images.
2. Model Training: Training a CNN to classify images as either AI-generated or real.
3. Deployment: Developing an interactive web application using Streamlit for real-time image classification.

Technologies Used

• Selenium
• Streamlit

Setup Instructions

1. Clone the repository:

   git clone https://github.com/Anand-shreya/Image-Classification.git

2. Navigate to the project directory:

   cd Image-Classification

3. Install dependencies:

   pip install -r requirements.txt

4. Run the Streamlit application:

   cd Developement
   streamlit run app_model1.py

Useful links

1. Dataset 1 (cat's images) used in training of model1: https://drive.google.com/drive/folders/1DdK5twcPrub0LTmiPbSJcE_8MTh4LerO?usp=sharing

2. Dataset 2 (General images): https://drive.google.com/drive/folders/1prn0DgGpEmvf6nYz6JxjcWB6UgCaGwRY?usp=sharing

NOTE

• It's good to create a virtual environment before package installation to manage different versions and to avoid any conflict.

To create and activate a virtual environment, use the following commands:

Create a virtual environment:

python -m venv venv

Activation

On Windows

.\venv\Scripts\activate

On macOS

source venv/bin/activate

Made with 💙 by :

• @Rajeshwari Rajiv Jadhav
• @Pranathi Nidadavolu
• @Rajeev Verma
• @Anurag Pandey
• @Shreya Anand