Computer vision applications: challenges with domain adaptation, active learning and open set classification

Abstract:  

The presentation considers computer vision and machine learning, especially a point of view of applications. Digital image processing and analysis with machine learning methods enable efficient solutions for various areas of useful data-centric engineering applications. Challenges with domain adaptation, active learning,  open set classification, and metric learning of similarities are considered. Computer Vision and Pattern Recognition Laboratory (CVPRL) at LUT focuses on computer vision applications, biomedical engineering, social signal processing, and data analytics. Different applications are given as examples based on specific data: planktons in the Baltic Sea, Saimaa ringed seals in the Lake Saimaa, logs in the sawmill industry, and roadside videos in traffic sign condition analysis.

Short bio:

Prof. Heikki Kälviäinen has been a Professor of Computer Science and Engineering since 1999. He is the head of the Computer Vision and Pattern Recognition Laboratory (CVPRL) in LUT University, Finland. His research interests include computer vision, pattern recognition, machine learning, and digital image processing and analysis: 28 doctoral theses and 165 master's theses supervised, more than 220 peer-reviewed scientific articles, and 51 research projects (total 6,3 MEUR). Besides LUT, Prof. Kälviäinen has worked more than six years in the following universities: Brno University of Technology, Czech Technical University, Monash University, and University of Surrey. He has served in many academic leader positions, including a Vice Dean, a Head of Department/Degree Program/Laboratory, a Director of East Finland Graduate School in Computer Science and Engineering, and a Deputy Head of School at Monash University Malaysia.