TY - JOUR
T1 - Associative gray level pattern processing using binary decomposition and αβ memories
AU - Sossa, Humberto
AU - Barrón, Ricardo
AU - Cuevas, Francisco
AU - Aguilar, Carlos
N1 - Funding Information:
The authors would like to thank the reviewers for their appropriate comment that allowed improving the content and presentation of this work. We would like also to thank Héctor Cortés for his help with some of the experiments. This work was economically supported by CGPI-IPN under grants 20020214, 20030658, 20040646 and 20050156 and CONACYT by means of grants 41529 and 46805.
PY - 2005/8
Y1 - 2005/8
N2 - In this note we show how a binary memory can be used to recall gray-level patterns. We take as example the α β associative memories recently proposed in Yáñez, Associative Memories based on order Relations and Binary Operators(In Spanish), PhD Thesis, Center for computing Research, February of 2002, only useful in the binary case. Basically, the idea consists on that given a set of gray-level patterns to be first memorized: (1) Decompose them into their corresponding binary patterns, and (2) Build the corresponding binary associative memory (one memory for each binary layer) with each training pattern set (by layers). A given pattern or a distorted version of it, it is recalled in three steps: (1) Decomposition of the pattern by layers into its binary patterns, (2) Recalling of each one of its binary components, layer by layer also, and (3) Reconstruction of the pattern from the binary patterns already recalled in step 2. The proposed methodology operates at two phases: training and recalling. Conditions for perfect recall of a pattern either from the fundamental set or from a distorted version of one them are also given. Experiments where the efficiency of the proposal is tested are also given.
AB - In this note we show how a binary memory can be used to recall gray-level patterns. We take as example the α β associative memories recently proposed in Yáñez, Associative Memories based on order Relations and Binary Operators(In Spanish), PhD Thesis, Center for computing Research, February of 2002, only useful in the binary case. Basically, the idea consists on that given a set of gray-level patterns to be first memorized: (1) Decompose them into their corresponding binary patterns, and (2) Build the corresponding binary associative memory (one memory for each binary layer) with each training pattern set (by layers). A given pattern or a distorted version of it, it is recalled in three steps: (1) Decomposition of the pattern by layers into its binary patterns, (2) Recalling of each one of its binary components, layer by layer also, and (3) Reconstruction of the pattern from the binary patterns already recalled in step 2. The proposed methodology operates at two phases: training and recalling. Conditions for perfect recall of a pattern either from the fundamental set or from a distorted version of one them are also given. Experiments where the efficiency of the proposal is tested are also given.
KW - Associative memories
KW - Pattern recognition
KW - αβ object recognition
UR - http://www.scopus.com/inward/record.url?scp=23844556623&partnerID=8YFLogxK
U2 - 10.1007/s11063-005-2902-6
DO - 10.1007/s11063-005-2902-6
M3 - Artículo de revisión
SN - 1370-4621
VL - 22
SP - 85
EP - 111
JO - Neural Processing Letters
JF - Neural Processing Letters
IS - 1
ER -