Funding for MVPR from Academy of Finland

The Academy of Finland decided to fund the project Automatic segmentation of overlapping objects for cell image analysis (CellVision)

The CellVision project serves needs of the healthcare and the industry. In industrial and biomedical machine vision applications it is very important to deal with digital images which contain a very large amount of overlapping objects. This lead to very useful applications such as cell imaging in the healthcare for diagnosis of cancer and nanoparticle imaging in the industry for quality control and material research. Our goal is to study automatic segmentation of overlapping objects. Manual segmentation is laborious, slow, and sensitive to interpretations. Images may contain tens of thousands of objects and it is time-consuming to detect attached and overlapping objects accurately. Recent developments in machine learning, especially with deep neural networks have enabled massive computations with large datasets. We have developed the state-of-the-art methods for nanoparticle segmentation mainly for industrial purposes, and now our plan is to extend our approach to cell imaging for the modern digital healthcare using machine vision and machine learning.

This is a collaborative project between MVPR and Professor Alan Bovik from LIVE at University of Texas at Austin (UTA).

The two-year project was started in January 1, 2018. The principal investigator is Prof. Heikki Kälviäinen and the project manager is Adjunct Professor, Dr. Tuomas Eerola. See the COMPHI project page for more information.


Cooperation with MIT started

Finnish Funding Agency for Innovation (Tekes) decided to fund the project Leap of Digitalisation for Sawmill Industry (DigiSaw)

The goal of the DigiSaw project is to develop the sawmill industry significantly via digitalisation. One of the main objectives is to build an information system connecting all the production steps of the mill so that it is possible to track the life cycle of raw material from the beginning to the end product. Raw material and its characteristics become individually traceable (e.g., logs and their parts) in the real-time industrial environment. This makes the use of raw material more efficient. At the same time, resource-efficient processes become more sustainable which benefits conservation of nature, especially in controlling the climate change. Modern sensor systems, new computational methods, and more robust mathematical models enable developing novel machine vision based measurements for quality control systems. The capabilities of the systems can be extended by using measured information from the sawmill processes and raw material. The obtained quality information can be connected via feedback loops to sorting the logs and optimizing the sawing processes. The developed innovations will be tested in the real industrial environment.

The project includes international collaboration with the Computer Graphics Research Group at Brno University of Technology (BUT) and Uncertainty Quantification Group at Massachusetts Institute of Technology (MIT).

The two-year project was started in September 1, 2017. The principal investigator is Prof. Heikki Kälviäinen, the co-investigator Prof. Lasse Lensu, and the project manager is Adjunct Professor, Dr. Tuomas Eerola.

See the DigiSaw project page for further information.


Prof. Adam Herout from Czech Republic visiting MVPR

Prof. Herout from Brno University of Technology building collaboration

Prof. Adam Herout from Brno University of Technology (BUT) from Czech Republic is visiting MVPR during the Easter week, including Erasmus lectures, discussions with MVPR researchers, and planning his course in the LUT summer school. See the link "Computational Engineering and Technical Physics" on the courses page. for further information about the course.

Prof. Herout gave visiting lectures Monday April 10, 2017 about

Striving for Fully Automatic Traffic Surveillance

on the Computer Vision course as a part of his Erasmus exchange visit.


Traffic surveillance cameras can produce a lot of specific data. We are processing the data with the aim to fully automatically obtain as much useful data as possible: camera calibration, make&model fine-grained recognition, speed measurement and other things. Some things work, some things might in the future.

Scientific interests of Professor Adam Herout are in computer vision, videoanalytics, computer graphics, and real-time processing. He has published his research in many forums, e.g., studies on traffic surveillance in CVPR and ICCV.


Visits to St. Petersburg

Prof. Kälviäinen promoting collaboration with ITMO and SPbPU

Professor Heikki Kälviäinen from MVPR visited ITMO University and Peter the Great St.Petersburg Polytechnic University (SPbPU) March 8-10, 2017. The visit included discussions about research collaboration and DD master programs.


Research visits to Czech Republic

Prof. Kälviäinen visiting CTU

Professor Heikki Kälviäinen from MVPR visited Czech Technical Universty (CTU) February 27- March 5, 2017 at Faculty of Electrical Engineering (FEL). His visit included EU Erasmus teacher exchange actitivies, meetings with several research groups related to digital image processing, machine vision, and pattern recognition, and two presentations about MVPR's research actitivies at Department of Telecommunication Engineering and at at Center for Machine Perception (CMP) at Department of Cybernetics. The goal of the visit is to continue currect joint research and to discuss about possibilities for vision-based research collaboration.

The visit was hosted by Dr. Radek Marik from Department of Telecommunication Engineering and Prof. Jiri Matas from CMP.


Visit to Monash University

Prof. Kälviäinen returned from his long-term university visit

Professor Heikki Kälviäinen from MVPR visited Monash University's Malaysian Campus (MUM) September 1, 2015 - June 30, 2016. He worked in School of Information Technology (SIT) as a Professor of Computing. He also served as the deputy head of the school.

SIT is focused on Intelligent Systems, especially using modern methods of Data Science. Professor Heikki Kälviäinen lectured IT research methods, and participated in research, including, e.g., facial expression recognition and intelligent health systems.


Lauri Laaksonen's dissertation

Lauri Laaksonen defended his dissertation successfully

MSc Lauri Laaksonen successfully defended his doctoral thesis "Spectral Retinal Image Processing and Analysis for Ophthalmology". The thesis is related to the project Re-Engineering Retinal Imaging with Photonics and Computational Science (ReVision) funded by the Academy of Finland.

The opponents of the public examination were Professor Ulla Ruotsalainen from Tampere University of Technology, Finland, and Professor Emanuele Trucco, the University of Dundee, Scotland, UK. Lauri Laaksonen's supervisor Professor Lasse Lensu was the custos. For more information, see the press release (in Finnish) and the thesis.


Dr. Eerola promoted

Dr. Eerola was nominated an Adjunct Professor (dosentti)

Dr. Tuomas Eerola was nominated an Adjunct Professor from October 1, 2015.

MVPR congratulates Dr. Eerola.


Ekaterina Riabchenko's dissertation

Ekaterina Riabchenko defended her dissertation successfully

MSc Ekaterina Riabchenko successfully defended her doctoral thesis "Generative Part-Based Gabor Object Detector". The thesis is related to the Gabor Object Detector project (www) where a novel Gabor feature based generative method was developed for learning and detecting visual classes and their poses.

The opponents of the public examination were Professor Ales Leonardis from University of Birmingham, UK, and Dr. Jorma Laaksonen from Aalto University, Finland. Ekaterina Riabchenko's supervisor Professor Joni Kämäräinen was the custos.


New Head of MVPR

Prof. Lasse Lensu new head of MVPR

Professor Lasse Lensu has started as a new head of MVPR since August 1, 2015.

The previous head, Professor Heikki Kälviäinen is going to enjoy his international university visit in Monash University in Kuala Lumpur from September 1, 2015. Professor Lensu has just ended his three-months university visit in Birminghan University in UK and now he returns back to the MVPR head postion which he has done also earlier. Moreover, Professor Lensu has served as Head of Degree Program and Head of Intelligent Computing Major.

MVPR congratulates Prof. Lensu.