Boosting segmentation results by contour relaxation
Alvaro Guevara, Christian Conrad, Rudolf Mester · 2011
This paper presents a versatile algorithmic building block that allows to significantly improve intermediate and final results of numerous variations of segmentation. The segmentation `context' can be very different in terms of the used data modality (gray scale, color, texture features, depth data, motion, ...), in terms of single frame vs. sequence segmentation, and in terms of the used initialization (measurement space clustering vs. `blind' initialization vs. interactively `sketching' the segmentation). For all these mentioned variations, the contour relaxation approach presented here offers the capability of very efficiently obtaining a segmentation result that is both visually pleasing as well as locally optimal with respect to a statistically well justified target functional.