Edge Detection Using Lateral Inhibition Neural Network
Zhou Wen · Journal of Nanjing Institute of Posts and Telecommunications · 2003
The paper proposes a method for edge detection based upon a lateral inhibition neural network. Two types of onedimensional input patterns, a bar and Mach bands are studied. The model is then generalized to two dimensions to show how to extract the boundary of a twodimensional object. Finally. All the models have been developed in a multipurpose neural network environment and simulated on a PC.