Pattern recognition by neural-network processing in the combined spatial-orientational space

H. Greenspan; M. Fleisher; M. Porat; Y. Y. Zeevi

doi:10.1109/EEIS.1989.720118

Pattern recognition by neural-network processing in the combined spatial-orientational space

H. Greenspan
, M. Fleisher
, M. Porat
, Y. Y. Zeevi

Research output: Contribution to conference › Paper › peer-review

1 Scopus citations

Abstract

A dual stage neural-network architecture is proposed, for the combined local and global processing of visual dot-patterns, in the spatial-orientational space. Dipoles defining local orientation are first determined by a Hopfield-type network. The second stage, consisting of a layered neural network, is then trained by the back propagation algorithm with a new cost function to discriminate between dipole patterns. The network performance in classification tasks is similar to that of human vision.

Original language	English
DOIs	https://doi.org/10.1109/EEIS.1989.720118
State	Published - 1989
Externally published	Yes
Event	16th Conference of Electrical and Electronics Engineers in Israel, EEIS 1989 - Tel-Aviv, Israel Duration: 7 Mar 1989 → 9 Mar 1989

Conference

Conference	16th Conference of Electrical and Electronics Engineers in Israel, EEIS 1989
Country/Territory	Israel
City	Tel-Aviv
Period	7/03/89 → 9/03/89

Access to Document

10.1109/EEIS.1989.720118

Cite this

@conference{34d57f7d6bfe455293900e938533a401,

title = "Pattern recognition by neural-network processing in the combined spatial-orientational space",

abstract = "A dual stage neural-network architecture is proposed, for the combined local and global processing of visual dot-patterns, in the spatial-orientational space. Dipoles defining local orientation are first determined by a Hopfield-type network. The second stage, consisting of a layered neural network, is then trained by the back propagation algorithm with a new cost function to discriminate between dipole patterns. The network performance in classification tasks is similar to that of human vision.",

author = "H. Greenspan and M. Fleisher and M. Porat and Zeevi, \{Y. Y.\}",

note = "Publisher Copyright: {\textcopyright} 1990 IEEE.; 16th Conference of Electrical and Electronics Engineers in Israel, EEIS 1989 ; Conference date: 07-03-1989 Through 09-03-1989",

year = "1989",

doi = "10.1109/EEIS.1989.720118",

language = "English",

}

TY - CONF

T1 - Pattern recognition by neural-network processing in the combined spatial-orientational space

AU - Greenspan, H.

AU - Fleisher, M.

AU - Porat, M.

AU - Zeevi, Y. Y.

PY - 1989

Y1 - 1989

N2 - A dual stage neural-network architecture is proposed, for the combined local and global processing of visual dot-patterns, in the spatial-orientational space. Dipoles defining local orientation are first determined by a Hopfield-type network. The second stage, consisting of a layered neural network, is then trained by the back propagation algorithm with a new cost function to discriminate between dipole patterns. The network performance in classification tasks is similar to that of human vision.

AB - A dual stage neural-network architecture is proposed, for the combined local and global processing of visual dot-patterns, in the spatial-orientational space. Dipoles defining local orientation are first determined by a Hopfield-type network. The second stage, consisting of a layered neural network, is then trained by the back propagation algorithm with a new cost function to discriminate between dipole patterns. The network performance in classification tasks is similar to that of human vision.

UR - https://www.scopus.com/pages/publications/84943727256

U2 - 10.1109/EEIS.1989.720118

DO - 10.1109/EEIS.1989.720118

M3 - Paper

AN - SCOPUS:84943727256

T2 - 16th Conference of Electrical and Electronics Engineers in Israel, EEIS 1989

Y2 - 7 March 1989 through 9 March 1989

ER -

Pattern recognition by neural-network processing in the combined spatial-orientational space

Abstract

Conference

Access to Document

Fingerprint

Cite this