Snakes, or active contours, are used extensively in computer vision and image processing applications, particularly in locating object boundaries. Problems associated with initialization and poor convergence to boundary concavities have limited their utility. Gradient vector flow (GVF) snake solved both problems successfully. However, boundaries in noisy images are often blurred even destroyed with smoothing and false results usually occur when such images are processed even with GVF snake model. We have incorporated embedded edge confidence (EEC) into GVF snake model. The improved method can solve this problem when noisy images were processed. © Springer-Verlag Berlin Heidelberg 2004.
CITATION STYLE
Wang, Y., & Yang, J. (2004). Gradient vector flow snake with embedded edge confidence. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3157, pp. 778–786). Springer Verlag. https://doi.org/10.1007/978-3-540-28633-2_82
Mendeley helps you to discover research relevant for your work.