DocumentCode :
2710700
Title :
Quantum Morphogenetic System in image recognition
Author :
Resconi, G. ; Loo, C.K. ; Tay, N.W.
Author_Institution :
Dept. of Math. & Physica, Catholic Univ., Brescia, Italy
fYear :
2009
fDate :
14-19 June 2009
Firstpage :
2642
Lastpage :
2648
Abstract :
Hopfield network requires that state vectors of images to be orthogonal to eliminate cross-talk. In practical sense, it cannot be achieved. A solution is to orthogonalize the state vectors with each other as a pre-processing. The QMS (Quantum Morphogenetic System) is a mathematical model devised to give a different more elegant and intuitive perspective of the pre-processing by assuming a non-Euclidean geometry. Input image is projected to the feature vector in terms of its contra-variant components which are interdependent. Image reconstruction is achieved by parallelogram summation of the vector of those components. Besides, an extension to Holonomic brain model and tensor network theory is discussed.
Keywords :
holography; image recognition; image reconstruction; quantum computing; Holonomic brain model; Hopfield network; contravariant components; cross talk elimination; feature vector; image recognition; image reconstruction; mathematical model; non-Euclidean geometry; parallelogram summation; quantum morphogenetic system; tensor network theory; Atom optics; Biological neural networks; Electron optics; Holographic optical components; Holography; Image recognition; Nonlinear optics; Pixel; Quantum computing; Space technology;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2009. IJCNN 2009. International Joint Conference on
Conference_Location :
Atlanta, GA
ISSN :
1098-7576
Print_ISBN :
978-1-4244-3548-7
Electronic_ISBN :
1098-7576
Type :
conf
DOI :
10.1109/IJCNN.2009.5178846
Filename :
5178846
Link To Document :
بازگشت