Open AccessA Nobel Hybrid Approach for Edge Detection
Author(s) -
P. Ithaya Rani,
Poonam Tanwar
Publication year - 2013
Publication title -
international journal of computer science and engineering survey
Language(s) - English
Resource type - Journals
eISSN - 0976-3252
pISSN - 0976-2760
DOI - 10.5121/ijcses.2013.4203
Subject(s) - computer science , thresholding , artificial neural network , smoothing , artificial intelligence , canny edge detector , edge detection , enhanced data rates for gsm evolution , pattern recognition (psychology) , deriche edge detector , set (abstract data type) , image (mathematics) , phase (matter) , algorithm , computer vision , image processing , chemistry , organic chemistry , programming language
The objective of this paper is to present the hybrid approach for edge detection. Under this technique, edgedetection isperformed in two phase. In first phase,Canny Algorithm is applied for image smoothing and insecond phase neural network is to detecting actual edges. Neural network is a wonderful tool for edgedetection. As it is a non-linear network with built-in thresholding capability. Neural Network can be trainedwith back propagation technique using few training patterns but the most important and difficult part is toidentify the correct and proper training set