作者: M. Bichsel
DOI: 10.1109/34.334396
关键词:
摘要: A new segmentation algorithm is derived, based on an object-background probability estimate exploiting the experimental fact that statistics of local image derivatives show a Laplacian distribution. The objects' simple connectedness included directly into and leads to iterative optimization approach can be implemented efficiently. This avoids early thresholding, explicit edge detection, motion analysis, grouping. >