The present study describes a model which, by using pattern recognition procedures, detects defects on the external surface of pieces and industrial products, especially those whose borders are indefinite. In addition to describing the model, a practical application and the results obtained are described, including an important extension of this work, i.e. the comparison of pieces with standard...

Manual stratigraphic interpretation of modern 3-D seismic images is extremely timeconsuming. We present a method based on nonstationary predictive signal/noise separation for automatically recognizing the occurence of a predefined pattern in seismic images. The method is tested on 2-D synthetic and real seismic images, and is shown to reliably detect the presence of unconformities in both.

Function-Described Graphs (FDGs) have been introduced as a representation of an ensemble of Attributed Graphs (AGs) for structural pattern recognition and a distance measure using restrictions between AGs and FDGs has been reported. Nevertheless, in real applications, AGs can be distorted by some external noise, and therefore some constraints have to be relaxed. To gain more flexibility and rob...

In many pattern recognition tasks we may be interested in asking questions about the behavior of sequences of observations on a particular random vector. Given that we have observed the sequence of feature vectors x1, x2, ..., xi, at i discrete points in time, for example, how likely is it that x will take the value xi+1 at time i+1. We may be interested in asking questions about the behavior o...

Feature extraction is a crucial step for pattern recognition. In this paper, a nonlinear feature extraction method is proposed. The objective function of the proposed method is formed by combining the ideas of locally linear embedding (LLE) and linear discriminant analysis (LDA). Optimizing the objective function in a kernel feature space, nonlinear features can be extracted. A major advantage ...

This paper presents an experimental system capable of recognizing forms and printed characters positioned on cylindrical objects in an industrial application. Forms are classified with structural pattern recognition methods while characters are recognized with a hybrid classifier utilizing both statistical and structural information. Training of form and character classifiers is performed using...

An application of the syntactic method to recognition of electrocardiogram (ECG) and to the measurement of ECG parameters is presented. Solutions to the subproblems of primitive pattern selection, primitive pattern extraction, linguistic representation, and pattern grammar formulation are given. Attribute grammars are used as the model for the pattern grammar because of their descriptive power,...

In subspace pattern recognition, the basis vectors represent the features of the data and define the class. In the previous works, standard principal component analysis is used to derive the basis vectors. Compared with standard PCA, Nonlinear PCA can provide the high-order statistics and result in non-orthogonal basis vectors. We combine Nonlinear PCA and a subspace classifier to extract the e...