R Brunelli, D Falavigna - IEEE transactions on pattern analysis …, 1995 - ieeexplore.ieee.org
This paper presents a person identification system based on acoustic and visual features. The system is organized as a set of non-homogeneous classifiers whose outputs are …
In this paper we compare to the standard correlation coefficient three estimators of similarity for visual patterns which are based on the L2and L1 norms. The emphasis of the …
This paper describes a multisensorial person-identification system in which visual and acoustic cues are used jointly for person identification. A simple approach, based on the …
This paper analyzes properties of a certain class of approximation techniques—HyperBF networks—in face perception tasks. The problem of gender classification and identification is …
R Battiti, G Tecchiolli - Neurocomputing, 1994 - Elsevier
In this paper different algorithms for training multilayer perceptron architectures are applied to a significant discrimination task in high energy physics. The One-Step Secant technique is …
L Stringa - Applied Artificial Intelligence an International Journal, 1993 - Taylor & Francis
A correlation-based approach to automatic face recognition requires adequate normalization techniques. If the positioning of the face in the image is accurate, the need for …
This paper describes an Automatic Speech Understanding (ASU) system used in a human- robot interface for the remote control of a mobile robot. The intended application is that of an …
The revival of multilayer neural networks in the mid 1980s originated from the discovery of the back propagation technique as a feasible training procedure. In spite of its shortcomings …
M Boninsegna, M Rossi - Pattern Recognition Letters, 1994 - Elsevier
A similarity measure is needed in many Computer Vision problems. Although Euclidean distance has traditionally been used, median distance was recently proposed as an …