Revista Brasileira de Cartografia (Dec 2004)
Canny-EDP detector: A Combination between Canny and non-linear anisotropic diffusion theories
Abstract
This paper proposes a methodology for edge detection in digital images using the Canny detector, but associated to a previous edge structure focusing by a non-linear anisotropic diffusion via Partial Differential Equation (PDE). This strategy aims at minimizing the effect of the well-know duality of Canny detector, by which is not possible to simultaneously enhance the insensitiveness to image noises and the localization precision of detected edges. The process of anisotropic diffusion via PDE is used to previously focus the edge structure due to its notable characteristic in selectively smoothing the image, leaving the homogeneous regions strongly smoothed and mainly preserving the physical edges, i.e., those that are really related to objects presented on the image. The solution for the mentioned duality consists in applying the Canny detector in fine gaussian scale but only along the edge regions focused by the process of anisotropic diffusion via PDE. The obtained results showed that the method is appropriated for application involving automatic feature extraction, as it allowed the high-precision localization of thinned edges, which are usually related to objects presented on the image.