Robust threshold estimation for images with unimodal histograms

This article introduces a method to determine in a robust manner the threshold in highly noisy gradient images. To enhance the robustness, the proposed technique is based on a piecewise linear regression to fit the whole descending slope of the histogram, rather than the search of some specific points. The algorithm gives a reliable estimation of the threshold, and is practically insensitive to the noise distribution, to the quantity of edge pixels to segment, and to random histogram fluctuations. (C) 2010 Elsevier B.V. All rights reserved.