TY - GEN
T1 - Morphological Auto-associative memories applied to true-color image patterns
AU - Vazquez, Roberto A.
AU - Sossa, Humberto
PY - 2009
Y1 - 2009
N2 - Morphological associative memories (MAMs) are a special type of associative memory which exhibit optimal absolute storage capacity and one-step convergence. This associative model substitutes the additions and multiplications used in the classical models by additions/subtractions and maximums/minimums depending on the proposed model. MAMs have been applied to different pattern recognition problems including face localization and gray scale image restoration. Despite of his power, it has not been applied in problems that involve true-color patterns. In this paper we show how a Morphological Auto-associative Memory (MAAM) can be applied to restore true-color patterns. We present a study of the behavior of this associative model with a benchmark of 14400 images altered by different type of noises.
AB - Morphological associative memories (MAMs) are a special type of associative memory which exhibit optimal absolute storage capacity and one-step convergence. This associative model substitutes the additions and multiplications used in the classical models by additions/subtractions and maximums/minimums depending on the proposed model. MAMs have been applied to different pattern recognition problems including face localization and gray scale image restoration. Despite of his power, it has not been applied in problems that involve true-color patterns. In this paper we show how a Morphological Auto-associative Memory (MAAM) can be applied to restore true-color patterns. We present a study of the behavior of this associative model with a benchmark of 14400 images altered by different type of noises.
UR - http://www.scopus.com/inward/record.url?scp=70449455914&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2009.5178733
DO - 10.1109/IJCNN.2009.5178733
M3 - Contribución a la conferencia
AN - SCOPUS:70449455914
SN - 9781424435531
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 3196
EP - 3203
BT - 2009 International Joint Conference on Neural Networks, IJCNN 2009
T2 - 2009 International Joint Conference on Neural Networks, IJCNN 2009
Y2 - 14 June 2009 through 19 June 2009
ER -