Nazeli Ter-Petrosyan, Davit Gyulnazaryan

Temporal Resolution Enhancement for Cell Tracking in Microscopy Image Sequences

Bio:

Nazeli Ter-Petrosyan is a Research Assistant at the American University of Armenia, where she earned her BSc in Computer Science. Her research focuses on hyperspectral image classification for cardiac surgery, spatiotemporal reconstruction in super-resolution microscopy, and interpretable electronic nose systems for odor classification. She also works as a Data Scientist and Innovation Engineer at Opply, a London-based startup optimizing food and beverage supply chains, and is a founding member of the fashion-tech startup Wearify.

 

 

 

Davit Gyulnazaryan is an aspiring researcher and recent graduate of the American University of Armenia, working on AI systems for multimodal information retrieval. Davit is passionate about building practical AI tools to solve complex, real-world problems. His research interests include information retrieval, semantic search, ontology-based systems, knowledge graphs, multimodal question answering, and applications of machine learning in biology.

 

Description of the Talk:

The talk presents a novel multispectral decomposition pipeline that transforms standard RGB imagery into high-fidelity spectral bands, enabling advanced analysis without expensive multispectral sensors. The method integrates spectral interpolation, task-aware band selection, and lightweight deep learning models for UAV and edge applications. Results demonstrate strong performance across diverse environmental conditions, supporting practical use in renewable energy monitoring and other remote sensing tasks.