Motion Saliency Based Automatic Delineation of Glottis Contour in High-speed Digital Images
This work addresses a bottleneck in computer-aided diagnosis of voice pathologies and voice production research, though it appears incremental as it builds upon an existing Saliency Network.
The paper tackles the challenge of automatic glottis segmentation in high-speed videoendoscopy images by proposing an improved Saliency Network that incorporates Motion Saliency based on edge velocities, resulting in enhanced delineation of the glottis contour.
In recent years, high-speed videoendoscopy (HSV) has significantly aided the diagnosis of voice pathologies and furthered the understanding the voice production in recent years. As the first step of these studies, automatic segmentation of glottal images till presents a major challenge for this technique. In this paper, we propose an improved Saliency Network that automatically delineates the contour of the glottis from HSV image sequences. Our proposed additional saliency measure, Motion Saliency (MS), improves upon the original Saliency Network by using the velocities of defined edges. In our results and analysis, we demonstrate the effectiveness of our approach and discuss its potential applications for computer-aided assessment of voice pathologies and understanding voice production.