Skip to main content
Usami Laboratory

Research

Usami Laboratory works on image processing, computer vision, and machine learning through four research themes.

Research Framework

Our research is organized around two connected directions: understanding principles and building applications.

We develop fundamental technologies for extracting, understanding, and using information from images and videos, while applying them to medicine, manufacturing, infrastructure, and real-world problems.

We value not only accuracy, but also why a method works, where it fails, and how it can be evaluated in a reproducible and useful way.

Principles x Applications

The laboratory combines foundational modeling with applied research for real-world deployment.

Principle-oriented research

Image understanding grounded in optics, physics, geometry, and mathematics.

  • Physics-based image analysis
  • Spatiotemporal modeling
  • Generative model evaluation

Application-oriented research

Technical development for concrete problems in medicine, industry, and society.

  • Medical image diagnosis support
  • Visual inspection
  • Action recognition systems

Evaluation Philosophy

We evaluate research outcomes from multiple viewpoints, not only by a single quantitative metric.

- Reproducibility: clear experimental conditions and traceable evaluation. - Generalization: robustness beyond a single dataset or imaging condition. - Interpretability: understanding why a method works and where it breaks. - Social impact: whether the result creates value in actual workflows.