Introducing a new Feature in AI vs realtime image classification

[anushkasaxena07]

Deep Learning Simplified Repository (Proposing new issue)

:red_circle: Project Title AI vs real image classification:
:red_circle: Aim :
The aim of this project is to develop a robust Convolutional Neural Network (CNN) model that can accurately classify images as either AI-generated or real. By leveraging deep learning techniques and a well-structured dataset, the model aims to identify subtle differences between AI-generated art and real artwork, achieving high accuracy and reliability in distinguishing these two categories. The ultimate goal is to create a tool that can assist in the automatic identification of AI-generated content, which can be valuable in various applications such as content verification, digital art analysis, and understanding AI's impact on creative industries. :red_circle: Approach : The approach used in your project is a Convolutional Neural Network (CNN) for classifying AI-generated images versus real images. It involves:

1. Data Preparation: Loading, normalizing, and combining AI-generated and real images into a single dataset.
2. Data Splitting: Dividing the data into training, testing, and validation sets.
3. Model Architecture: Building a CNN model with multiple convolutional, max-pooling, and dense layers, using the ELU activation function and batch normalization.
4. Training and Evaluation: Training the model with binary cross-entropy loss and the Nadam optimizer, implementing callbacks for model checkpointing and learning rate reduction, and evaluating model performance through accuracy and loss metrics.

This CNN approach leverages deep learning techniques for effective image classification, focusing on distinguishing between AI-generated and real images.

---

📍 Follow the Guidelines to Contribute in the Project :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

:red_circle::yellow_circle: Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

:white_check_mark: To be Mentioned while taking the issue :

• Full name : Anushka Saxena

• GitHub Profile : anushkasaxena07

• Email ID :anushka.gghs@gmail.com

• Participant ID (if applicable):

• Approach for this Project : To enhance your CNN model for detecting AI-generated and real images, consider adding Grad-CAM (Gradient-weighted Class Activation Mapping) as a new feature. Grad-CAM provides visual explanations for the decisions made by CNN models by highlighting regions of the image that are important for predictions. This can help you understand what parts of the images are contributing to the classification decision, making the model more interpretable

• What is your participant role? (Mention the Open Source program) GSSOC open source contributor

  ---

  Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[github-actions[bot]]

Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! 😊

[anushkasaxena07]

@abhisheks008 plz assign me this issue

[abhisheks008]

Already present in this repository. Closing this issue as similar problem statement existing in the repository.