Computer Vision • Generative AI • Trustworthy & Ethical AI
I’m an AI/ML practitioner passionate about transforming research ideas into real-world intelligent systems.
My work blends deep learning, image forensics, and human-centric AI, with a strong focus on clarity, reproducibility, and impact.
- 🧠 Exploring Deep Learning & Applied AI
- 🔬 Designing systems aligned with IEEE-style research
- 🛠️ Building end-to-end ML pipelines (data → model → UI)
- ✨ Clean code, meaningful experiments, honest evaluation
DeepReveal is a research-oriented deep learning framework designed to identify pixel-wise AI-generated or manipulated regions within images, rather than only giving a global label.
✨ What makes DeepReveal unique
- 🧩 Pixel-level localization of AI-generated or tampered content
- 🙂 Face-aware region analysis using integrated face detection for focused inspection
- 🎯 Highlights where manipulation occurs, not just whether it exists
- 🌐 Interactive Flask-based interface for visual inspection
- 📈 Built with research extensibility and dataset scalability in mind
📌 Applications:
Digital image forensics • Deepfake localization • Media authentication • Misinformation analysis
🖼️ Deepfake Detection Web Application
MobileNetV3-Large + multi-feature extraction for detecting GAN-generated images, deployed with Streamlit. A CNN-based classification system that determines whether an image is real or fake.
Built using MobileNetV3 and deployed with a Streamlit web interface for real-time inference.
- 🔍 Trustworthy & explainable AI
- 📊 High-quality datasets & preprocessing
- 🔁 Reproducible ML experiments
- 📝 Clear documentation & technical writing
💻 GitHub • 💼 LinkedIn • 📧 Email
⭐ If you find my work useful, consider starring a repository — it truly helps!