Implemented a frequency-aware deepfake detection model, FreqNet, which uses convolutional layers within the frequency space and compared its performance with CLIP. The best performing model achieved 99% accuracy.
Trained a siamese network made of VGG-16s and DenseNet to determine whether the two given fingerprints are match or no match. Achieved accuracy of 89%.
Designed and developed a hybrid model that combined ViT, LBP and ResNet/EfficientNet. Achieved 98% accuracy.
Implemented a web application for classifying images using a ResNet-based image classifier. It consists of a Node.js frontend and a FastAPI backend, with Dockerized deployments managed through Kubernetes.
Implemented state-of-the-art 3D reconstruction using Gaussian Splatting technique for high-quality vase modeling. Created interactive 3D visualization demonstrating advanced computer vision and 3D modeling capabilities.
Built a comprehensive Python application for automatic news extraction and display from skynews.au. Features real-time data processing, content filtering, and user-friendly interface for news consumption.
Developed a robust data scraping solution for real estate websites. Implemented advanced parsing techniques, data validation, and export functionality for market analysis and research purposes.
Designed and developed a clean, academic-focused portfolio website featuring responsive design, interactive project showcases, and optimized performance for professional presentation.
Machine Learning, Deep Learning, Computer Vision, Natural Language Processing
Python, C++, MySQL, Unix/Linux, Git, Version Control
PyTorch, TensorFlow, OpenCV, Scikit-learn, NumPy, Pandas
Technical Writing, Communication, Time Management, Attention to Detail, Analytical Thinking