Shape description by image foresting transform

Abstract

The image foresting transform (IFT) is a unified and effective graph-based approach to the design of image-processing operations, often with considerable efficiency gains over published algorithms. This paper extends the applications of the Euclidean IFT to two recently proposed shape descriptors: saliences and multiscale fractal dimension. It explains how to obtain the salience information and the multiscale fractal dimension of contours and skeletons and presents their comparison in terms of robustness and separability.