Edge Detection based on Local-Friis-Radiation-Magnitude-Ratio (LFRMR)

Abstract

The advent of computer-vision based systems has given rise to the need for efficient edge detection algorithms. This paper presents a novel approach called the Local-Friis-Radiation-Magnitude-Ratio (LFRMR) for edge detection. LFRMR incorporates the renowned Friis Equation of antenna radiation and extends it to the grid of image pixels to establish a relation among the pixels residing in a local neighbourhood, to extract accurate illumination-invariant and noise resistant edge maps. Quantitative and qualitative experimental results on BSDS500 dataset depicts that the proposed scheme can extract true edges with utmost precision and recall. Furthermore, the proposed scheme is quite robust against Gaussian channel noise and Salt & Pepper noise. A detailed mathematical investigation has also been carried out to prove that the proposed framework is illumination-invariant and robust in noisy environments. Optimum algorithm parameters are decided via experimental analysis. A comparison with the latest state-of-the-art methods is also presented.