•
Developed and implemented a Convolutional Neural Network (CNN) based model to detect and classify forged images with high accuracy
•
Collected and preprocessed image datasets, applying techniques such as resizing, normalization, and augmentation for training efficiency
•
Designed the CNN architecture with multiple convolutional, pooling, and fully connected layers to extract and learn deep features of tampered images
•
Trained and evaluated the model using Python, TensorFlow/Keras, achieving improved precision in distinguishing authentic vs. forged images
•
Compared results with traditional methods, demonstrating the effectiveness of deep learning in digital image forensics
•
Documented the system design, workflow, and results, and presented findings as part of the final year engineering project