Concurrent Neural Classifiers
for Pattern Recognition with Applications in Biometrics, Satellite Imagery,
and Autonomous Navigation
Professor Victor-Emil Neagoe
Polytechnic University of Bucharest,
Tel.+40 721 23 50 20
Abstract: We present the model of
Concurrent Neural Classifiers (CNC) representing a collection of small
neural networks, which use a global winner-takes-all strategy. Each neural
module is trained to correctly classify the patterns of one class only and
the number of modules equals the number “M” of classes. One considers the
case of choosing the SOM (Self-Organized-Map) as a neural module. The CNC
training technique is a supervised one, but for any individual net, the SOM
specific unsupervised training algorithm is used. We built “M” training
pattern sets and each neural module is trained with the pattern set
characterized by the corresponding class label.
Several presented CNC applications are dedicated to biometrics; first one
has as target the recognition of color facial images and second belongs to
iris recognition. One also considers a CNC application corresponding to the
case of decision fusion by implementation of a multimodal biometric model.
Second series of applications focuse on the CNC model for pattern
recognition in multispectral satellite imagery. The implemented neural
classifiers are evaluated using some LANDSAT ETM+ images composed by a set
of multispectral pixels, each pixel corresponding to one of several
categories (vegetation, buildings, water, and so on).
Third kind of considered CNC applications correspond to visual
identification of road direction of an autonomous vehicle. We present the
experimental results obtained by computer simulation . We have also
performed, trained and tested a real time neural path follower based on CNC
model, implemented on a mobile robot (car toy).
Brief Biography of the Speaker:
Dr. Victor-Emil Neagoe is a Professor of the Department of Electronics,
Telecommunications, and Information Technology at the Polytechnic University
of Bucharest, Romania.
He teaches the following courses : Pattern Recognition and Artificial
Intelligence; Digital Signal Processing; Computational Intelligence ;
Detection and Estimation for Information Processing. He co-ordinates 12
His research interest corresponds to the fields of pattern recognition,
computational intelligence, biometric technology , satellite image analysis
and sampling theory.
Prof. Neagoe is author of more than 110 published papers.
His has internationally recognized results concerning concurrent
self-organized maps, face recognition, optimum color conversion, syntactical
self-organized maps, nonuniform sampling theorems, inversion of the Van der
Monde matrix, predictive ordering and linear approximation for image data
compression, Legendre descriptors for classification of polygonal closed
He has been included in Who’s Who in the World and Europe 500 and he has
been nominated by the American Biographical Institute for American Medal of
Honor and for World Medal of Honor.
He has been a Member IEEE since 1978 and a Senior Member IEEE since 1984.