Faculty of Informatics Vienna University of Technology Institute of Computer Aided Automation PRIP Home PRIP Home
Personal tools
You are here: Home Teaching PRIP-Talks Cristian Smochina: Microscopic image processing techniques and segmentation evaluation
Navigation
 

Cristian Smochina: Microscopic image processing techniques and segmentation evaluation

The presentation contains two parts. In the first part a quality measure for evaluating the performance of segmentation algorithms is presented. This discrepancy method is based on object-by-object comparison of a segmented image (machine segmentation) versus ground-truth segmentation (reference image). The error measure takes into consideration the interior of the object and eliminates the inconveniences that appear in the case of the concave objects. A weighted shape fitting score is used: the score of the segmented contour is enhanced by a factor which indicates the similarity between these two curves. The second part contains automatic segmentation techniques for detecting cell nuclei in images taken from tissues with colon carcinoma. The region growing method is used to obtain accurate background detection. New approaches are proposed to detect the separation areas between clustered/touching cell nuclei. These regions are validated based on their link with the background. The watershed segmentation algorithm followed by a merging criterion is used to completely delimit the nuclei boundaries.

What
  • Presentation
When Feb 15, 2011
from 05:00 pm to 05:30 pm
Where Library HC 04 07
Contact Name Cristian Smochina
Contact Email
Add event to calendar vCal
iCal
Document Actions