Dr. Bahar Uddin Mahmud
Computer Vision Researcher | Mixed Reality Expert | AI Consultant
Assistant Professor of Computer Science, Lander University
PhD in Computer Science, Western Michigan University
About
I'm a computer vision and AI researcher specializing in deep learning, mixed reality (AR/VR/MR), and human-AI collaboration.
My research focuses on building intelligent systems for healthcare, agriculture, and spatial computing applications.
As Assistant Professor at Lander University and former Team Lead of the ATOM Lab at Western Michigan University,
I've led federally-funded research projects and developed cutting-edge AI solutions deployed in real-world medical environments.
🚀 Available for consulting and contract research
I help companies build computer vision systems for AR/VR/MR applications, optimize deep learning models for deployment,
and translate research into production-ready AI solutions.
Expertise
Mixed Reality & Computer Vision
- HoloLens 2 application development
- Real-time object detection for AR/VR
- Medical imaging visualization
- 3D volumetric image segmentation
- Spatial computing systems
Deep Learning & AI
- CNN architectures for vision tasks
- Lightweight models for edge deployment
- PyTorch & TensorFlow expertise
- Model optimization & compression
- Real-time inference systems
Applied AI Solutions
- Healthcare AI systems (DHHS-funded)
- Agricultural disease detection
- Human-AI collaboration research
- Production deployment pipelines
- Technical advisory & due diligence
Featured Projects
🏥 Medical Vial Identification System (HoloLens 2)
Led development of mixed reality system for accurate medical vial identification using deep learning and Microsoft HoloLens 2.
Funded by Department of Health and Human Services (DHHS) through AHRQ.
- Real-time object detection and classification in augmented reality
- Custom deep learning model optimized for HoloLens 2 constraints
- Deployed in medical environments for look-alike medication safety
- Published: Future Internet (2025) and Electronics (2024)
🔬 3D Volumetric Image Segmentation
Deep learning-based segmentation of 3D volumetric images for microstructural analysis with applications in
medical imaging and material science.
- Advanced 3D CNN architecture for volumetric medical data
- Efficient processing of CT/MRI scans
- Applications in surgical planning and material characterization
- Published: Sensors (2023)
🌾 AgriNet-Light: Agricultural Disease Detection
Lightweight deep learning model for real-time agricultural disease detection and plant pathology classification.
- Optimized for mobile and edge device deployment
- Fast, accurate mango leaf disease classification
- Practical solution for farmers and agricultural professionals
- Published: Emerging Science Journal (2024) & Springer Nature book chapter (Accepted)
Services
- Computer Vision Consulting: AR/VR vision pipelines, medical imaging AI, real-time object detection systems
- Deep Learning Development: Model architecture design, optimization for edge/mobile deployment, training and production deployment
- Mixed Reality Applications: HoloLens 2 development, Unity integration, spatial computing solutions for healthcare and industry
- Research & Development: Contract research, prototype development, proof-of-concept implementations
- Technical Advisory: AI system architecture review, technical due diligence for investors, grant proposal support
Background & Credentials
Current Position
Assistant Professor of Computer Science - Lander University (2026-Present)
Teaching computer science, programming, computer vision & ML, and AI literacy while conducting research in deep learning and immersive technologies.
Education
PhD in Computer Science - Western Michigan University
- Dissertation: Deep Learning Innovations in Medical Vial Recognition for Mixed Reality Applications
- Team Lead, ATOM Lab - Mixed reality research for medical professionals (DHHS-funded)
- Graduate Research Excellence Award 2023 - Top graduate student for outstanding research
M.S. in Information Technology - University of Dhaka, Bangladesh
B.Sc. in Computer Science & Engineering - Maulana Azad National Institute of Technology, India (Fulbright Scholar)
Publications
10+ peer-reviewed journal articles | 4+ conference papers
Recent publications in Future Internet, Electronics, Sensors, Emerging Science Journal, and ACM Transactions on Multimedia.
View complete publication list →
Technical Skills
Programming: Python, C, C++, MATLAB
Deep Learning: PyTorch, TensorFlow, Keras, OpenCV
Computer Vision: Object Detection, Image Segmentation, 3D Vision, Real-time Processing
Mixed Reality: HoloLens 2, Unity, Spatial Computing, AR/VR Development
Tools & Libraries: NumPy, Pandas, Matplotlib, Scipy, LaTeX, Git
Contact
Interested in collaborating on computer vision, AI, or mixed reality projects? Let's discuss how I can help.
Get in Touch
📍 Based in South Carolina, USA | Available for remote consulting worldwide
💼 Open to consulting, contract research, and technical advisory roles