COMPHI - Segmentation of Overlapping Objects

The goal is to analyze overlapping objects in an image, usually at microscopic level and for industrial and medical purposes. The task consists of the following research topics: to detect objects which are possibly attached and/or overlapping and to segment the objects, i.e. estimate their contours. This project is a part of LUT Center of Excellence in Research, called Computational Photonics Imaging (COMPHI), in co-operation with LUT Applied Mathematics Laboratory, being associated with Academy of Finland's Center of Excellence in Research in Inverse Mathematics.

The project includes international collaboration with the Laboratory for Image and Video Engineering (LIVE) at The University of Texas at Austin (UT) led by Professor Alan C. Bovik.

Sahar Zafari	visiting UT		Doctoral student
Tuomas Eerola	Office: 2422	Tel: +358 40 139 3405	Post-Doctoral Researcher, Adjunct Professor
Jouni Sampo	Office: 2508	Tel: +358 44 337 5672	University Lecturer
Heikki Kälviäinen	Office: 2415	Tel: +358 40 586 7552	Professor
Heikki Haario	Office: 2409	Tel: +358 400 814 092	Professor

Segmentation of Overlapping Convex Objects

By Sahar Zafari, Master's Thesis, Lappeenranta University of Technology, 2014.

The thesis presents a framework for segmentation of clustered overlapping convex objects.

Download: PDF

Segmentation of Overlapping Elliptical Objects in Silhouette Images

By Sahar Zafari, Tuomas Eerola, Jouni Sampo, Heikki Kälviäinen, and Heikki Haario, In IEEE Transactions on Image Processing 24 (12), 5942 - 5952, 2015.

This paper presents a radial symmetry based method for segmentation of clustered partially overlapping objects with a shape that can be approximated using an ellipse.

Download: PDF DOI code

Segmentation of Partially Overlapping Nanoparticles Using Concave Points

By Sahar Zafari, Tuomas Eerola, Jouni Sampo, Heikki Kälviäinen, and Heikki Haario, In International Symposium on Visual Computing (ISVC 2015), 2015.

This paper presents a method to segment multiple partially overlapping nanoparticles in images using concave points and ellipse properties.

Download: PDF DOI code

Segmentation of Partially Overlapping Convex Objects Using Branch and Bound Algorithm

By Sahar Zafari, Tuomas Eerola, Jouni Sampo, Heikki Kälviäinen, and Heikki Haario, In Asian Conference on Computer Vision (ACCV) workshop on mathematical and computational methods in biomedical imaging and image analysis (MCBMIIA2016), 2016.

This paper presents a method to segment multiple partially overlapping nanoparticles in images by formulating the task as a discrete optimization problem and by solving it using branch and bound algorithm.

Download: PDF DOI code

Comparison of Concave Point Detection Methods for Overlapping Convex Objects Segmentation

By Sahar Zafari, Tuomas Eerola, Jouni Sampo, Heikki Kälviäinen, and Heikki Haario, In the 20th Scandinavian Conference on Image Analysis (SCIA 2017), 2017.

This paper presents a comprehensive comparison of existing concave point detection methods that provide an essential cue for segmentation of partially overlapping convex objects.

Download: PDF DOI

Software relases

1. A radial symmetry based method for segmentation of overlapping objects
   Download the MATLAB code here.
   Please cite the following paper in any published work if you use this software.
   S. Zafari, T. Eerola, J. Sampo, H. Kalviainen, and H. Haario, Segmentation of Overlapping Elliptical Objects in Silhouette Images, IEEE Transactions on in Image Processing 24(12), 5942-5952, 2015.
2. A method to segment overlapping nanoparticles using concave points
   Download the MATLAB code here.
   Please cite the following paper in any published work if you use this software.
   S. Zafari, T. Eerola, J. Sampo, H. Kalviainen, and H. Haario, Segmentation of Partially Overlapping Nanoparticles Using Concave Points, in International Symposium on Visual Computing (ISVC 2015), 2015.
3. A method to segment overlapping nanoparticles using branch and bound algorithm
   Download the MATLAB code here.
   Please cite the following paper in any published work if you use this software.
   S. Zafari, T. Eerola, J. Sampo, H. Kalviainen, and H. Haario, Segmentation of Partially Overlapping Convex Objects Using Branch and Bound Algorithm, in Workshop on Mathematical and Computational Methods in Biomedical Imaging and Image Analysis (MCBMIIA2016), 2016.