RIS ID
109092
Abstract
Engineering-based edge detection techniques generally use local intensity information to identify whether a pixel location is part of a boundary. Boundaries are presumed present where sharp transitions in the observed intensities occur. Unfortunately, these approaches are sensitive to error and hidden partial boundaries, which hinders the determination of closed object boundaries. In this research, a method to obtain statistically optimal closed object boundaries is presented.
Publication Details
Helterbrand, J. D. & Cressie, N. A C. (1993). Stochastic recognition of closed object boundaries in images. Proceedings of SPIE - The International Society for Optical Engineering (pp. 240-251).