|
|
|
|
|
|
Help | Seminars List | Add Seminar | Edit Seminars | Tips for organisers | RSS | ics Calendar | Search | Send comments about this website to seminar-master@cecs.anu.edu.au
Contact: Jochen.Trumpf@anu.edu.au COMPUTER VISION AND ROBOTICS SERIES
Automatic Dry Eye DetectionTamir Yedidya (The Australian National University)DATE: 2009-10-15 TIME: 16:00:00 - 17:00:00 LOCATION: RSISE Seminar Room, ground floor, building 115, cnr. North and Daley Roads, ANU ABSTRACT: Dry Eye Syndrome is a common disease in the western world, with effects from uncomfortable itchiness to permanent damage to the ocular surface. Nevertheless, there is still no objective test that provides reliable results. The most common test used by clinicians these days is the Fluorescein Break Up Time (FBUT). However, results vary a lot between clinicians. We have defined a new method for a robust, automatic detection of the FBUT and for evaluating the degree of dryness.
In the talk, I will explain our technique and the various dryness signs we are detecting. I will also demonstrate how our 2D images are extended to a 3D spatio-temporal volume segmentation problem. Using a multi-label graph-cuts approach, the whole volume is simultaneously segmented for dryness. In addition, we enforce a temporal monotonic constraint in the graph-cut algorithm, so the results are less sensitive to noise, hence a more accurate FBUT estimation. |