Francesco La Rosa
||Vision Systems: Segmentation and Pattern Recognition
||INTECH Open Access Publisher, 2007
In this work we have described a re-formulation of a 2D still-image segmentation algorithm, implemented on a single-layer CNN, previously proposed (Iannizzotto, 2003). This algorithm is able to step-over limitation inherent to the class of active contours: sensitivity to insignificant false edges or "edge fragmentation". The approach features an iterative process of uniform shrinking and deformation of the active contour. Guided by statistical properties of edgeness of the image pixels, the chain adapts itself to the image contours. Undesirable smoothing of the edges of the objects are prevented by the absence of any particular rigidity constraints on the chain. The technique used for uniform shrinking, which automatically handles any splitting, allows the presence of any nested edges to... be detected.