A Coarse-to-Fine Deformable Contour Optimization Framework
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
We present a system that extracts and tracks 2D mid-sagital tongue surfaces from ultrasound image sequencesproduced by a Head and Transducer Support System(HATS). Such a system can be a valuable and practical tool for speech and swallowing research. We extendour previous work by introducing a deformable contourmodel to impose restrictions of spatiotemporal coherencyby assuming that the 2D mid-sagital tongue surface contours sweep a coherent 3D structure in spatiotemporal3D space. Another novel contribution of this paper isa dynamic programming minimization method to optimize the new energy functional, which can be employedin general snake minimization tasks. We tested this system on a number of speech and swallowing sequenceseach containing 24 to 30 frames. We verified with speechexperts and found that our system produces promisingresults, especially for the swallowing sequences, whichare more problematic.