Title :
Some applications of morphological neural networks
Author :
Graña, Manuel ; Raducanu, Bogdan
Author_Institution :
Dept. CCIA, Basque Country Univ., San Sebastian, Spain
Abstract :
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
Keywords :
content-addressable storage; image recognition; mathematical morphology; neural nets; noise; algebraic framework; dilative noise; erosive noise; face localization; grayscale images; heteroassociative morphological memories; mobile robot; morphological neural networks; neural network architecture; noise model robustness; visual self-localization; Associative memory; Electronic mail; Face detection; Gray-scale; Hidden Markov models; Kernel; Mobile robots; Neural networks; Noise robustness; Principal component analysis;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.938763
