A method for automatic detection and localization of faces on digital images is proposed. The method is based on learning by example and multi-resolution analysis of digital images. Special emphasis is put on the management of the learning data, in order to improve the performances. Various experimental results, obtained by using a Multi-Layer Perceptron (MLP) as a classier, are provided.

This paper presents a new approach for automatic image color correction, based on statistical learning. The method both parameterizes color independently of illumination and corrects color for changes of illumination. The motivation for using a learning approach is to deal with changes of lighting typical of indoor environments such as home and office. The method is based on learning color inva...

Feature projection by non-linear discriminant analysis (NLDA) can substantially increase classification performance. In automatic speech recognition (ASR) the projection provided by the pre-squashed outputs from a one hidden layer multi-layer perceptron (MLP) trained to recognise speech subunits (phonemes) has previously been shown to significantly increase ASR performance. An analogous approac...

We address a contrastive study between the well known Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) neural networks and a SOM based supervised architecture in a number of data classification tasks. Well known databases like Breast Cancer, Parkinson and Iris were used to evaluate the three architectures by constructing confusion matrices. The results are encouraging and indicate t...

Feature selection methods have been explored in the literature for the classification techniques, among which correlated feature, information gain, mutual information and chi-square are considered more effective. The leaf images contain inherent noise due to imaging equipment, operating environment and position of the image during image acquisition. In this paper, a method for classification of...

We suggest to apply the hybrid neural network based on multi layer perceptron (MLP) and adaptive resonance theory (ART-2) for solving of navigation task of mobile robots. This approach provides semi supervised learning in unknown environment with incremental learning inherent to ART and capability of adaptation to transformation of images inherent to MLP. Proposed approach is evaluated in exper...

| In this paper, we describe important improvements that were recently introduced in our Discriminative Stochastic Segment Model (DSSM) speech recognizer. We propose a new presegmen-tation algorithm and we optimize the structure of the Multi-Layer Perceptron (MLP) that estimates the phone probabilities. Additionally, we describe a cascade MLP combination technique that relaxes the drawbacks of ...

Artificial Neural Network (ANN) is one of the modern computational methods proposed to solve increasingly complex problems in the real world (Xie et al., 2006 and Chau, 2007). ANN is characterized by its pattern of connections between the neurons (called its architecture), its method of determining the weights on the connections (called its training, or learning, algorithm), and its activation ...

nowadays, software cost estimation (sce) with machine learning techniques are more performance than other traditional techniques which were based on algorithmic techniques. in this paper, we present a new hybrid model of multi-layer perceptron (mlp) artificial neural network (ann) and ant colony optimization (aco) algorithm for high accuracy in sce called multilayer perceptron ant colony optimi...

this paper is based on a combination of the principal component analysis (pca), eigenface and support vector machines. using n-fold method and with respect to the value of n, any person’s face images are divided into two sections. as a result, vectors of training features and test features are obtain ed. classification precision and accuracy was examined with three different types of kernel and...