Fractal analysis of remotely sensed images: A review of methods and applications

Abstract

Mandelbrot's fractal geometry has sparked considerable interest in the remote sensing community since the publication of his highly influential book in 1977. Fractal models have been used in several image processing and pattern recognition applications such as texture analysis and classification. Applications of fractal geometry in remote sensing rely heavily on estimation of the fractal dimension. The fractal dimension (D) is a central construct developed in fractal geometry to describe the geometric complexity of natural phenomena as well as other complex forms. This paper provides a survey of several commonly used methods for estimating the fractal dimension and their applications to remote sensing problems. Methodological issues related to the use of these methods are summarized. Results from empirical studies applying fractal techniques are collected and discussed. Factors affecting the estimation of fractal dimension are outlined. Important issues for future research are also identified and discussed.