An extension of min/max flow framework.

Abstract

In this paper, the min/max flow scheme for image restoration is revised. The novelty consists of the fol- 24 lowing three parts. The first is to analyze the reason of the speckle generation and then to modify the 25 original scheme. The second is to point out that the continued application of this scheme cannot result 26 in an adaptive stopping of the curvature flow. This is followed by modifications of the original scheme 27 through the introduction of the Gradient Vector Flow (GVF) field and the zero-crossing detector, so as 28 to control the smoothing effect. Our experimental results with image restoration show that the proposed 29 schemes can reach a steady state solution while preserving the essential structures of objects. The third is 30 to extend the min/max flow scheme to deal with the boundary leaking problem, which is indeed an 31 intrinsic shortcoming of the familiar geodesic active contour model. The min/max flow framework pro- 32 vides us with an effective way to approximate the optimal solution. From an implementation point of 33 view, this extended scheme makes the speed function simpler and more flexible. The experimental 34 results of segmentation and region tracking show that the boundary leaking problem can be effectively 35 suppressed.