A new supervised classification algorithm of a heavily distorted pattern (shape) obtained from noisy observations of nonstationary signals is proposed in the paper. Based on the Gabor transform of 1-D non-stationary signals, 2-D shapes of signals are formulated and the classification formula is developed using the pattern matching idea, which is the simplest case of a pattern recognition task. In the pattern matching problem, where a set of known patterns creates predefined classes, classification relies on assigning the examined pattern to one of the classes. Classical formulation of a Bayes decision rule requires a priori knowledge about statistical features characterising each class, which are rarely known in practice. In the proposed algorithm, the necessity of the statistical approach is avoided, especially since the probability distribution of noise is unknown. In the algorithm, the concept of discriminant functions, represented by Frobenius inner products, is used. The classification rule relies on the choice of the class corresponding to the max discriminant function. Computer simulation results are given to demonstrate the effectiveness of the new classification algorithm. It is shown that the proposed approach is able to correctly classify signals which are embedded in noise with a very low SNR ratio. One of the goals here is to develop a pattern recognition algorithm as the best possible way to automatically make decisions. All simulations have been performed in Matlab. The proposed algorithm can be applied to non-stationary frequency modulated signal classification and non-stationary signal recognition.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
The paper presents novel morphological approach to binary pattern recognition based on morphological image processing. Depending on its spatial properties, each pixel belonging to binary pattern is assigned to one of four spatial classes using the morphological classification approach. Based on it, the class distribution functions are produced, normalized and sampled to obtain feature vector consisting of morphological features. The effectiveness of the proposed method was validated using nearest neighbour classification on the reference set of patterns.
PL
Wartykule przedstawiono nowe podejście do rozpoznawania wzorców binarnych wykorzystujące morfologiczne przetwarzanie obrazów. Każdemu pikselowi wzorca binarnego jest przypisywana jedna z czterech klas przestrzennych. W oparciu o tę klasyfikację generowane są funkcje dystrybutywne klas, które są następnie normalizowane i próbkowane w celu uzyskania wektora cech zawierającego cechy morfologiczne. Skuteczność metody została potwierdzona eksperymentalnie z wykorzystaniem klasyfikacji najbliższego sąsiada na referencyjnym zbiorze wzorców.
3
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
This paper presents a new set of bivariate discrete orthogonal moments which are based on bivariate Hahn polynomials with non-separable basis. The polynomials are scaled to ensure numerical stability. Their computational aspects are discussed in detail. The principle of parameter selection is established by analyzing several plots of polynomials with different kinds of parameters. Appropriate parameters of binary images and a grayscale image are obtained through experimental results. The performance of the proposed moments in describing images is investigated through several image reconstruction experiments, including noisy and noise-free conditions. Comparisons with existing discrete orthogonal moments are also presented. The experimental results show that the proposed moments outperform slightly separable Hahn moments for higher orders.
4
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
In the paper, infinite information systems are considered which are used in pattern recognition, discrete optimization, computational geometry. Depth and size of deterministic and nondeterministic decision trees over such information systems are studied. Two classes of infinite information systems are investigated. Systems from these classes are best from the point of view of time complexity and space complexity of deterministic as well as nondeterministic decision trees. In proofs methods of test theory and rough set theory are used.
5
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
In this paper we review occlusion culling techniques appeared in the last decade. These techniques are used for achieving real/interactive time rendering. The characteristics of these techniques are outlined and a synopsis table is given at the end.
6
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Moment invariants have found wide applications in image recognition since they were proposed. The recognition problem is often connected with image reconstruction technique to determine a desired set of invariants for use their in a recognition system. For image reconstruction low order moments are important because they contain information about general shape of the image. But these moments are not efficient for recognition because general shapes of different objects can be very similar and do not allow to distinguish one object from another. The main difficulty in the application of the moment invariants is the absence of theoretical methods for estimating their efficiency in recognition tasks. In this paper, our goal is to analyse the significance of Zernike moments of different orders from the viewpoint of pattern recognition theory. We propose simple intuitive method of optimal filtering in invariant domain, namely, to select image features in order to minimize errors (misclassification rates) excluding noise sensitive and unstable features.
In this work, a modified version of the elastic bunch graph matching (EBGM) algorithm for face recognition is introduced. First, faces are detected by using a fuzzy skin detector based on the RGB color space. Then, the fiducial points for the facial graph are extracted automatically by adjusting a grid of points to the result of an edge detector. After that, the position of the nodes, their relation with their neighbors and their Gabor jets are calculated in order to obtain the feature vector defining each face. A self-organizing map (SOM) framework is shown afterwards. Thus, the calculation of the winning neuron and the recognition process are performed by using a similarity function that takes into account both the geometric and texture information of the facial graph. The set of experiments carried out for our SOM-EBGM method shows the accuracy of our proposal when compared with other state-of the-art methods.
8
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
The problem of observation space reordering is presented as a novel approach to pattern recognition based on non-parametric, combinatorial statistical tests. It consists in linearly ordering the elements of a discrete multi-dimensional observation space along a curve such that elements belonging to different similarity classes are as close to each other as possible, the similarity classes are mutually separated, and the length of the curve is kept to minimum. The problem is NP-difficult and it is shown how its approximate solution can be reached by a series of transformations improving the initial lexicographic linear order of a discrete observation space. Recommendations are formulated for linear order improvement leading to a pattern recognition algorithm based on serial statistical test.
9
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
The analysis of prostate images is one of the most complex tasks in medical images interpretation. It is sometimes very difficult to detect early prostate cancer using currently available diagnostic methods. But the examination based on perfusion computed tomography (p-CT) may avoid such problems even in particularly difficult cases. However, the lack of computational methods useful in the interpretation of perfusion prostate images makes it unreliable because the diagnosis depends mainly on the doctor's individual opinion and experience. In this paper some methods of automatic analysis of prostate perfusion tomographic images are presented and discussed. Some of the presented methods are adopted from papers of other researchers, and some are elaborated by the authors. This presentation of the method and algorithms is important, but it is not the master scope of the paper. The main purpose of this study is computational (deterministic and independent) verification of the usefulness of the p-CT technique in a specific case. It shows that it is possible to find computationally attainable properties of p-CT images which allow pointing out the cancerous lesion and can be used in computer aided medical diagnosis.
Combining the outputs of multiple neural networks has been used in Ensemble architectures to improve the decision accuracy in many applications fields, including pattern recognition, in particular for the case of fingerprints. In this paper, we describe a set of experiments performed in order to find the optimal individual networks in terms of the architecture and training rule. In the second step, we used the fuzzy Sugeno Integral to integrate results of the ensemble neural networks. This method combines objective evidence in the form of the network's outputs, with subjective measures of their performance. In the third step, we used a Fuzzy Inference System for the decision process of finding the output of the ensemble neural networks, and finally a comparison of experimental results between Fuzzy Sugeno Integral and the Fuzzy Inference System are presented.
We describe in this paper a comparative study between Fuzzy Inference Systems as methods of integration in modular neural networks for multimodal biometry. These methods of integration are based on techniques of type-1 fuzzy logic and type-2 fuzzy logic. Also, the fuzzy systems are optimized with simple genetic algorithms. First, we considered the use of type-1 fuzzy logic and later the approach with type-2 fuzzy logic. The fuzzy systems were developed using genetic algorithms to handle fuzzy inference systems with different membership functions, like the triangular, trapezoidal and Gaussian; since these algorithms generate the fuzzy systems automatically. Then the response integration of the modular neural network was tested with the optimized fuzzy integration systems. The comparative study of type-1 and type-2 fuzzy inference systems was made to observe the behavior of the two different integration methods for modular neural networks for multimodal biometry.
12
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
A new methodology for improving the performance and training of neural network classifiers employed in diagnostics is presented. The main idea is based on using redundant classifiers in an ensemble in order to guarantee the best generalisation ability of the diagnosis system. A brief survey of some commonly used methods for combining outputs in the ensemble is made. As compared to previous designs, a novel method for output combination is introduced. The proposed technique consist in considering the classes independently of one another and calculating the importance parameters, i.e. the weights, for individual outputs of the networks. In order to draw a comparison with previous methods, a real data medical benchmark is used. To improve the results of the ensemble, Negative Correlation Learning was applied.
13
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
As one of the key techniques for futuristic human computer interaction, facial expression recognition has received much attention in recent years. A method of facial expression recognition based on selective feature extraction and rule matching is presented in this paper. In this method we classify expressions roughly into three kinds according to the deformation of mouth firstly. Then we select some expression features which contribute much to each kind expression according to the rough classification results and extract features for them. Lastly we classify expressions finely using method based on rule matching. Experiments show that facial expression recognition based on selective feature extraction and rule matching can get high recognition rate and has strong robustness.
The paper deals with the analysis of process stability with the use of process control charts. A new idea of pattern recognition and two original methods of data processing, called OTT and MW have been described. The software application CCAUS (Control Charts - Analysis Unnatural Symptoms) supporting process control charts analysis withOTT and MW has been presented as well. Also the paper contains the results of the verification of the proposed methods performed on the basis of data obtained from two machining operations.
15
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
This paper presents a significant modification to the AdaSS (Adaptive Splitting and Selection) algorithm, which was developed several years ago. The method is based on the simultaneous partitioning of the feature space and an assignment of a compound classifier to each of the subsets. The original version of the algorithm uses a classifier committee and a majority voting rule to arrive at a decision. The proposed modification replaces the fairly simple fusion method with a combined classifier, which makes a decision based on a weighted combination of the discriminant functions of the individual classifiers selected for the committee. The weights mentioned above are dependent not only on the classifier identifier, but also on the class number. The proposed approach is based on the results of previous works, where it was proven that such a combined classifier method could achieve significantly better results than simple voting systems. The proposed modification was evaluated through computer experiments, carried out on diverse benchmark datasets. The results are very promising in that they show that, for most of the datasets, the proposed method outperforms similar techniques based on the clustering and selection approach.
16
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
A hybrid unsupervised learning algorithm, termed as rough-fuzzy c-means, is proposed in this paper. It comprises a judicious integration of the principles of rough sets and fuzzy sets. While the concept of lower and upper approximations of rough sets deals with uncertainty, vagueness, and incompleteness in class definition, the membership function of fuzzy sets enables efficient handling of overlapping partitions. The concept of crisp lower bound and fuzzy boundary of a class, introduced in rough-fuzzy c-means, enables efficient selection of cluster prototypes. Several quantitative indices are introduced based on rough sets for evaluating the performance of the proposed c-means algorithm. The effectiveness of the algorithm, along with a comparison with other algorithms, has been demonstrated on a set of real life data sets.
The paper proposes different approaches for the analysis of data and for the performance evaluation of the organization and management inside industry clusters all over Europe. The models adopted for the analysis of the data are derived from different disciplines ranging from statistic multivariate analysis to operational research. The data collection was gathered as an outcome for the European Project CODESNET devoted to the research in the domain of the demand and supply networks. Industry clusters belong to a wide number of European countries and were chosen without any limitations on the kind of activity carried on by the participating industries. Data were collected in the framework of a meta-model of the cluster organization which includes three macro areas: Operation Structure, Organization Arrangement and Interaction with Socio-Economic Environment. After a description of a logical arrangement of available information, a pattern recognition procedure useful to fully analyse an industrial network, using both data/information from existing SME networks and technical/scientific reports, is presented.
18
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Decision algorithms useful in classifying meteorological volumetric radar data are the subject of described in the paper experiments. Such data come from the Radar Decision Support System (RDSS) database of Environment Canada and concern summer storms created in this country. Some research groups used the data completed by RDSS for verifying the utility of chosen methods in volumetric storm cells classification. The paper consists of a review of experiments that were made on the data from RDSS database of Environment Canada and presents the quality of particular classifiers. The classification accuracy coefficient is used to express the quality. For five research groups that led their experiments in a similar way it was possible to compare received outputs. Experiments showed that the Support Vector Machine (SVM) method and rough set algorithms which use object oriented reducts for rule generation to classify volumetric storm data perform better than other classifiers.
19
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
This article introduces structural aspects in an ontology of approximate reason. The basic assumption in this ontology is that approximate reason is a capability of an agent. Agents are designed to classify information granules derived from sensors that respond to stimuli in the environment of an agent or received from other agents. Classification of information granules is carried out in the context of parameterized approximation spaces and a calculus of granules. Judgment in agents is a faculty of thinking about (classifying) the particular relative to decision rules derived from data. Judgment in agents is reflective, but not in the classical philosophical sense (e.g., the notion of judgment in Kant). In an agent, a reflective judgment itself is an assertion that a particular decision rule derived from data is applicable to an object (input). That is, a reflective judgment by an agent is an assertion that a particular vector of attribute (sensor) values matches to some degree the conditions for a particular rule. In effect, this form of judgment is an assertion that a vector of sensor values reflects a known property of data expressed by a decision rule. Since the reasoning underlying a reflective judgment is inductive and surjective (not based on a priori conditions or universals), this form of judgment is reflective, but not in the sense of Kant. Unlike Kant, a reflective judgment is surjective in the sense that it maps experimental attribute values onto the most closely matching descriptors (conditions) in a derived rule. Again, unlike Kant's notion of judgment, a reflective judgment is not the result of searching for a universal that pertains to a particular set of values of descriptors. Rather, a reflective judgment by an agent is a form of recognition that a particular vector of sensor values pertains to a particular rule in some degree. This recognition takes the form of an assertion that a particular descriptor vector is associated with a particular decision rule. These considerations can be repeated for other forms of classifiers besides those defined by decision rules.
20
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
This paper presents the use of ROC analysis for the assessment of the classifiers’ performance. Either linear or quadratic discriminant analysis assigns objects to classes on the basis of parametric model. Fitting decision boundary according to nonparametric ROC curve allows to achieve demanded criteria like maximum accuracy, minimum risk or Neyman-Pearson’s criterion. This method was applied to measure the quality of bayesian classifiers of PERG signal real data base.
PL
Artykuł przedstawia wykorzystanie analizy ROC do oceny działania klasyfikatorów. Zarówno liniowa, jak i kwadratowa analiza dyskryminacyjna przyporządkowuje obiekty do klas na podstawie modelu parametrycznego. Dopasowanie granicy decyzyjnej zgodnie z nieparametryczną krzywą ROC pozwala osiągnąć pożądane kryterium: maksymalną skuteczność, minimalne ryzyko lub kryterium Neymana-Pearsona. Metodę tę zastosowano do oceny jakości klasyfikatorów bayesowskich rzeczywistej bazy danych sygnałów PERG.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.