HEAL DSpace

Invariant image recognition using triple correlations and neural networks

Αποθετήριο DSpace/Manakin

Εμφάνιση απλής εγγραφής

dc.contributor.author Tirakis, A en
dc.contributor.author Delopoulos, A en
dc.contributor.author Kollias, S en
dc.date.accessioned 2014-03-01T02:41:01Z
dc.date.available 2014-03-01T02:41:01Z
dc.date.issued 1994 en
dc.identifier.uri https://dspace.lib.ntua.gr/xmlui/handle/123456789/30329
dc.subject Computational Complexity en
dc.subject Efficient Implementation en
dc.subject Image Recognition en
dc.subject Image Representation en
dc.subject Neural Network en
dc.subject.other Computational complexity en
dc.subject.other Computer architecture en
dc.subject.other Correlation methods en
dc.subject.other Data reduction en
dc.subject.other Feature extraction en
dc.subject.other Image analysis en
dc.subject.other Image understanding en
dc.subject.other Invariance en
dc.subject.other Neural networks en
dc.subject.other Optical correlation en
dc.subject.other Vector quantization en
dc.subject.other Vectors en
dc.subject.other Invariant recognition en
dc.subject.other Multiresolution neural networks en
dc.subject.other Triple correlation based image representations en
dc.subject.other Object recognition en
dc.title Invariant image recognition using triple correlations and neural networks en
heal.type conferenceItem en
heal.identifier.primary 10.1109/ICNN.1994.374863 en
heal.identifier.secondary http://dx.doi.org/10.1109/ICNN.1994.374863 en
heal.publicationDate 1994 en
heal.abstract Triple-correlation-based image representations were previously (Delopoulos, Tirakis, and Kollias, 1994) combined with neural network architectures for deriving an invariant, with respect to translation, rotation and dilation, robust classification scheme. Efficient implementations are described in this paper, which reduce the computational complexity of the method. Hierarchical, multiresolution neural networks are proposed as an effective architecture for achieving this purpose en
heal.publisher IEEE, Piscataway, NJ, United States en
heal.journalName IEEE International Conference on Neural Networks - Conference Proceedings en
dc.identifier.doi 10.1109/ICNN.1994.374863 en
dc.identifier.volume 6 en
dc.identifier.spage 4055 en
dc.identifier.epage 4060 en


Αρχεία σε αυτό το τεκμήριο

Αρχεία Μέγεθος Μορφότυπο Προβολή

Δεν υπάρχουν αρχεία που σχετίζονται με αυτό το τεκμήριο.

Αυτό το τεκμήριο εμφανίζεται στην ακόλουθη συλλογή(ές)

Εμφάνιση απλής εγγραφής