A dynamic programming approach to sequential pattern recognition

This paper presents the dynamic programming approach to the design of optimal pattern recognition systems when the costs of feature measurements describing the pattern samples are of considerable importance. A multistage or sequential pattern classifier which requires, on the average, a substantially smaller number of feature measurements than that required by an equally reliable nonsequential classifier is defined and constructed through the method of recursive optimization. Two methods of reducing the dimensionality in computation are presented for the cases where the observed feature measurements are 1) statistically independent, and 2) Markov dependent. Both models, in general, provide a ready solution to the optimal sequential classification problem. A generalization in the design of optimal classifiers capable of selecting a best sequence of feature measurements is also discussed. Computer simulated experiments in character recognition are shown to illustrate the feasibility of this approach.     

Genetic optimization of GRNN for pattern recognition without feature extraction

This paper describes an approach for pattern recognition using genetic algorithm and general regression neural network (GRNN). The designed system can be used for both 3D object recognition from 2D poses of the object and handwritten digit recognition applications. The system does not require any preprocessing and feature extraction stage before the recognition. In GRNN, placement of centers has significant effect on the performance of the network. The centers and widths of the hidden layer neuron basis functions are coded in a chromosome and these two critical parameters are determined by the optimization using genetic algorithms. Experimental results show that the optimized GRNN provides higher recognition ability compared with that of unoptimized GRNN.     

Genetic design of biologically inspired receptive fields for neural pattern recognition

This paper proposes a new method for the design, through simulated evolution, of biologically inspired receptive fields in feedforward neural networks (NNs). The method is intended to enhance pattern recognition performance by creating new neural architectures specifically tuned for a particular pattern recognition problem. It proposes a combined neural architecture composed of two networks in cascade: a feature extraction network (FEN) followed by a neural classifier. The FEN is composed of several layers with receptive fields constructed by additive superposition of excitatory and inhibitory fields. A genetic algorithm (GA) is used to select receptive field parameters to improve classification performance. The parameters are receptive field size, orientation, and bias as well as the number of different receptive fields in each layer. Based on a random initial population where each individual represents a different neural architecture, the GA creates new enhanced individuals. The method is applied to handwritten digit classification and face recognition. In both problems, results show strong dependency between NN classification performance and receptive field architecture. GA selected parameters of the receptive fields produced improvements in the classification performance on the test set up to 90.8% for the problem of handwritten digit classification and up to 84.2% for the face recognition problem. On the same test sets, results were compared advantageously to standard feedforward multilayer perceptron (MLP) NNs where receptive fields are not explicitly defined. The MLP reached a maximum classification performance of 84.9% and 77.5% in both problems, respectively.     

Genetic programming for multibiometrics

Biometric systems suffer from some drawbacks: a biometric system can provide in general good performances except with some individuals as its performance depends highly on the quality of the capture… One solution to solve some of these problems is to use multibiometrics where different biometric systems are combined together (multiple captures of the same biometric modality, multiple feature extraction algorithms, multiple biometric modalities…). In this paper, we are interested in score level fusion functions application (i.e., we use a multibiometric authentication scheme which accept or deny the claimant for using an application). In the state of the art, the weighted sum of scores (which is a linear classifier) and the use of an SVM (which is a non linear classifier) provided by different biometric systems provide one of the best performances. We present a new method based on the use of genetic programming giving similar or better performances (depending on the complexity of the database). We derive a score fusion function by assembling some classical primitives functions (+, ∗, −, … ). We have validated the proposed method on three significant biometric benchmark datasets from the state of the art.     

Intelligent analysis and pattern recognition in cardiotocographic signals using a tightly coupled hybrid system

In obstetrics, cardiotocograph (CTG) and non-stress test readings are indispensable to antenatal monitoring and assessment. Difficulties in the interpretation of CTG records require methods for computer-assisted analysis. This article describes CAFE (Computer Aided Foetal Evaluator), an intelligent tightly coupled hybrid system developed to overcome the difficulties inherent in CTG analysis. It integrates algorithms (implemented via conventional programming techniques) with Artificial Intelligence (AI) paradigms (rule-based systems and artificial neural networks), in order to automate and perform all the phases involved in real time antenatal monitoring, from the analysis and interpretation of CTG signals to diagnosis. Its architecture, components and functional character will be described in detail. The validation of CAFE over 3450 minutes of signal time corresponding to 53 different patients in a real environment is discussed, and its performance with respect to a group of experts is evaluated. Most of the results obtained reflect acceptable levels of performance—equivalent to expert performance—and thus confirm the suitability of AI techniques to applications in this field.     

Moment invariants for pattern recognition

Invariant combinations of moments of arbitrary order are defined. Application to a vehicle image shows that a reconstructed image having <10% error may be obtained by using invariants formed from moments uop to order eight.     

Artificial data for pattern recognition

The paper describes the generation of three types of artificial data and their use as test material in pattern recognition research. Type A data: The user defines the perfect decision surface. The classes are separable and the pdf's flat. This type is useful in two ways: (i) To investigate whether a learning procedure can achieve a minimal-cost solution. (ii) To compare the powers of two classifiers. Type B data: The user defines the optimal decision surface. The classes are not separable; the degree of overlap between the classes can be controlled by the user. The pdf's are approximately flat, except in regions close to this optimal decision boundary. This type is useful in the following ways: (i) To study the effect of varying the overlap between classes upon a learning procedure. (ii) To compare the powers of two classifiers on a random problem. Type C data: This type is a model of natural, clustered data. The user specifies the location, height, and spread of a number of “hills” in the pdf (for each class). These parameters allow us to calculate the pdf's and hence the Bayes' classification, at any given point. This provides a powerful tool for the objective evaluation of a learning classifier, operating on a realistic problem.     

Some methods for pattern recognition

The present study is dedicated to pattern recognition of alphabetical and numerical symbols. A recognition method based on modification of Hausdorff metrics is presented; then, another method named the method of radial neighborhoods is described. A series of experiments on test patterns are conducted.     

MicroARTMAP for pattern recognition problems

Pattern recognition is an important aspect of a dominant technology such as machine intelligence. Domain specific fuzzy-neuro models particularly for the ‘black box’ implementation of pattern recognition applications have recently been investigated. In this paper, Sanchez’s MicroARTMAP has been discussed as a pattern recognizer/classifier for the image processing problems. The model inherently recognizes only noise free patterns and in case of noise perturbations (rotations/scaling/translation) misclassifies the images. To tackle this problem, a conventional Hu’s moment based rotation/scaling/translation invariant feature extractor has been employed. The potential of this model has been demonstrated on two problems, namely, recognition of alphabets and words and prediction of load from yield pattern of elasto-plastic analysis. The second example concerns with color images dealing with colored patterns. MicroARTMAP is also applied to other two civil engineering problems, namely (a) Indian Standard (IS) classification of soil and (b) prediction of earthquake parameters from the response spectrum in which no feature extractor step is necessary.     

Image normalization for pattern recognition

In general, there are four basic forms of distortion in the recognition of planar patterns: translation, rotation, scaling and skew. In this paper, a normalization algorithm has been developed which transforms pattern into its normal form such that it is invariant to translation, rotation, scaling and skew. After normalization, the recognition can be performed by a simple matching method. In the algorithm, we first compute the covariance matrix of a given pattern. Then we rotate the pattern according to the eigenvectors of the covariance matrix, and scale the pattern along the two eigenvectors according to the eigenvalues to bring the pattern to its most compact form. After the process, the pattern is invariant to translation, scaling and skew. Only the rotation problem remains unsolved. By applying the tensor theory, we find a rotation angle which can make the pattern invariant to rotation. Thus, the resulting pattern is invariant to translation, rotation, scaling and skew. The planar image used in this algorithm may be curved, shaped, a grey-level image or a coloured image, so its applications are wide, including recognition problems about curve, shape, grey-level and coloured patterns. The technique suggested in this paper is easy, does not need much computation, and can serve as a pre-processing step in computer vision applications.     

Genetic programming for iterative numerical methods

Genetic Programming and Evolvable Machines - We introduce GPLS (Genetic Programming for Linear Systems) as a GP system that finds mathematical expressions defining an iteration matrix. Stationary...     

Genetic programming for prediction and control

The relatively new field of genetic programming has received a lot of attention during the last few years. This is because of its potential for generating functions which are able to solve specific problems. This paper begins with an extensive overview of the field, highlighting its power and limitations and providing practical tips and techniques for the successful application of genetic programming in general domains. Following this, emphasis is placed on the application of genetic programming to prediction and control. These two domains are of extreme importance in many disciplines. Results are presented for an oral cancer prediction task and a satellite attitude control problem. Finally, the paper discusses how the convergence of genetic programming can be significantly speeded up through bulk synchronous model parallelisation.     

Syntactic pattern recognition for the recognition of bright spots

Syntactic pattern recognition techniques are applied to the analysis of one-dimensional seismic traces and two-dimensional seismograms for the detection of bright spots. The calculation between error probability and Levenshtein distance is proposed. The system for two-dimensional seismic analysis includes three kinds of string distance computation to test the continuity of a bright spot pattern.     

Weighted logical inference for pattern recognition

Boolean control systems with some non-observable unknown parameters are considered here. In this study, these parameters have been evaluated by consideration of some variables associated to the system. An algorithm is suggested by means of which the values of the parameters can be found.     

Using SEEK for multichannel pattern recognition

The author's work on computerized analysis of the 2-channel, 24-hr electrocardiogram has previously resulted in the development of multichannel signal processing systems that learn by observation. A new tool for implementing such algorithms is described: the pattern recognition language SEEK. Programs written in SEEK build a knowledge base containing treelike data structures, each of which stores acquired information about a particular multichannel waveform. Input data are interpreted by performing an efficient parallel evaluation of the structures in the knowledge base. The work is applicable to a wide variety of pattern recognition problems that arise in medical signal processing. The approach is illustrated with examples drawn from ECG analysis.     

Using interpoint distances for pattern recognition

The simplest problem of pattern recognition is considered, viz., recognition of two classes of objects given by points in Euclidean space; the recognition is fulfilled using the fraction of samples that fall within a ball of radius r with the center at the specified point. The interpoint distances are considered both within the totalities and between them. Their pairwise asymptotic independence is proved, which allows reducing the multidimensional distribution to one-dimensional, where simple yet important problems can be solved. For instance, one can check the significance of the difference between the class distributions, choose the optimal value of radius r, and stably estimate the error of recognition. Aleksandr Mikhailovich Shurygin. Born 1931. Graduated from Moscow State University, Faculty of Geology (1949–1954) and Faculty of Mechanics and Mathematics (1960–1965). Received candidate’s degree in Geology and Mineralogy (Tectonics) in 1959 and doctoral degree (Information Theory) in 2002. Since 1970, he has had the title of Senior Researcher. He works as a leading researcher at the Faculty of Computational Mathematics and Cybernetics of MSU and as a senior researcher at the Scientific Council of Cybernetics of the RAS. Author of more than 130 scientific publications, including five monographs.