Some applications of morphological neural networks
Manuel Graña, Bogdan Cristian Raducanu · 2002
The heteroassociative morphological memories are a recently proposed neural network architecture based on the shift of the basic algebraic framework. They possess some robustness to specific noise models (erosive and dilative noise). Here we report on going work on their application to the tasks of face localization in grayscale images and visual self-localization of a mobile robot.