Multiscale Gradient Maps Augmented Fisher Information-Based Image Edge Detection

Image edge detection is an important task in image processing and pattern recognition. Edges in digital images signify image discontinuities and traditionally gradient information is utilized in finding possible edge pixels. In this work, we consider a fusion approach using multiscale gradient maps along with non-parametric Fisher information which is recently used in edge detection. By using multiscale gradient maps we obtain better edge localization and robust edge maps and local thresholding with Fisher information helps obtain better detection. Experimental results on a variety of digital images and performance evaluation undertaken in comparison with edge detectors from the literature show the advantage of the proposed approach.