MEETING-DATE:February 17, 2010
MEETING-LOCATION:DC 1304
MEETING-TIME:1:30
MEETING-CHAIR:Matthew Kay
MEETING-CHAIRPIC:mattkay.jpg
COFFEE-HOUR-LAST-WEEK:Philippe
COFFEE-HOUR-THIS-WEEK:Volunteers?
COFFEE-HOUR-NEXT-WEEK:Volunteers?
FORTH-DATE1:February 24, 2010
FORTH-DATE2:March 3, 2010
FORTH-DATE3:March 10, 2010
FORTH-DATE4:March 17, 2010
FORTH-LOCATION1:DC 1304 1:30
FORTH-LOCATION2:DC 1304 1:30
FORTH-LOCATION3:DC 1304 1:30
FORTH-LOCATION4:DC 1304 1:30
FORTH-CHAIR1:Ben Lafreniere
FORTH-CHAIR2:Philippe Lamoureux
FORTH-CHAIR3:Stephen Mann
FORTH-CHAIR4:Zainab Meraj
FORTH-CHAIRPIC1:ben.jpg
FORTH-CHAIRPIC2:nopic.jpg
FORTH-CHAIRPIC3:
FORTH-CHAIRPIC4:
FORTH-TP1:Craig Kaplan
FORTH-TP2:Matthew Kay
FORTH-TP3:Ben Lafreniere
FORTH-TP4:Philippe Lamoureux
FORTH-TPPIC1:craig.jpg
FORTH-TPPIC2:mattkay.jpg
FORTH-TPPIC3:
FORTH-TPPIC4:
TPNAME:Tiffany Inglis 
TPTITLE:Multilevel image segmentation
TPABSTRACT:A multilevel aggregation method is applied to the problem of segmenting live cell bright field microscope images.<nl>The method employed is a variant of the so-called `Segmentation by Weighted Aggregation' technique, which itself is based on Algebraic Multigrid methods. The variant of the method used is described in detail, and it is explained how it is tailored to the application at hand.<nl>In particular, a new scale-invariant `saliency measure' is proposed for deciding when aggregates of pixels constitute salient segments that should not be grouped further.<nl>It is shown how segmentation based on multilevel intensity similarity alone does not lead to satisfactory results for bright field cells. However, the addition of multilevel intensity variance (as a measure of texture) to the feature vector of each aggregate leads to correct cell segmentation.<nl>Preliminary results are presented for applying the multilevel aggregation algorithm in space-time to temporal sequences of microscope images, with the goal of obtaining space-time segments (`object tunnels') that track individual cells. The advantages and drawbacks of the space-time aggregation approach for segmentation and tracking of live cells in sequences of microscope images are presented, followed by a discussion of how this approach may be used in future work as a building block in a complete and robust segmentation and tracking system.
TPPIC:t3chao.jpg
DIONE:
DITWO:
DITHREE:
DIFOUR:
AIONE:We need a new CGL poster to replace the ancient one. 
AITWO:Thurs Feb 25 lab tours
AITHREE:March break lab tours
AIFOUR:
DMONE:
DMTWO:
DMTHREE:
DMFOUR:
SEMINARS:<pre><nl>    * 2010 Feb 17, 10:30 - Computer Science Seminar<nl>      Rafae Bhatti, Oracle, U.S.A.<nl>      Security and Privacy For Healthcare Applications: Does Policy mean Protection?<nl>    * 2010 Feb 18, 13:00 - Computer Systems Group PhD Thesis Defence<nl>      Rolando Maldonado Blanco, PhD candidate, David R. Cheriton School of Comp. Sci., Univ. Waterloo<nl>      Process Models for Distributed Event-Based Systems<nl>    * 2010 Feb 26, 13:30 - Cryptography, Security, and Privacy (CrySP) Group Seminar<nl>      Rosario Gennaro (IBM Research)<nl>      Non-Interactive Verifiable Computing: Outsourcing Computation to Untrusted Workers<nl></pre>