A dynamic programming based algorithm for optimal edge detection in medical images

摘要

This paper explores a novel dynamic programming (DP) based optimal technique in ultrasound image (USI) edge detection, which is less constrained now than previous. Dynamic programming is an optimal approach in multistage decision-making. In an image segmentation system, we want to find a global optimal contour with connectedness and closeness. The DP algorithms process the object image to get the minimum cumulative cost matrix to tracing a global optimal edge. Combined with LUM nonlinear enhancement filter and Gaussian preprocessor, this method shows robustness on noisy image edge detection.