Name
Abstract | ||
|---|---|---|
We present a system to segment the medial edges of the vocal folds from stroboscopic video. The system has two components. The first learns a color transformation that op- timally discriminates, according to the Fisher linear crite- rion, between the trachea and vocal folds. Using this trans- formation, it is able to make a coarse segmentation of vocal fold boundaries. The second component uses an active con- tour formulation recently developed for the Insight Toolkit to refine detected contours. Rather than tune the internal energy of our active contours to bias for specific shapes, we optimize image energy so as to highlight boundaries of in- terest. This transformation of image energy simplifies the contour extraction process and suppresses noisy artifacts, which may confound standard implementations. We evaluate our system on stroboscopic video of sus- tained phonation. Our evaluation compares points on auto- matically extracted contours with manually supplied points at perceived vocal fold edges. Mean deviations for points located on the minor axes of the vocal folds averaged 2.2 pixels across all subjects, with a standard deviation of 3.6. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1109/ISBI.2004.1398662 | ISBI |
Keywords | Field | DocType |
mean deviation,noise shaping,shape,image segmentation,active contour,edge detection,stroboscopes,biomedical imaging,point location,standard deviation | Active contour model,Computer vision,Vocal folds,Pattern recognition,Segmentation,Computer science,Edge detection,Image segmentation,Pixel,Artificial intelligence,Phonation,Stroboscope | Conference |
Citations | PageRank | References |
7 | 1.09 | 4 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sonya Allin | 1 | 62 | 7.74 |
| J.M. Galeotti | 2 | 75 | 13.90 |
| George D. Stetten | 3 | 146 | 22.70 |
| Seth Dailey | 4 | 7 | 1.09 |