Deriving an informative data representation is an important prerequisite when designing road-sign classifiers. A frequently used strategy for road-sign classification is based on the normalized cross correlation similarity to class prototypes followed by the nearest neighbor classifier. Because of the global nature of the cross correlation similarity, this method suffers from presence of uninformative pixels (caused, e.g., by occlusions) and is computationally demanding. In this paper, a novel concept of a trainable similarity measure is introduced, which alleviates these shortcomings. The similarity is based on individual matches in a set of local image regions. The set of regions that are relevant for a particular similarity assessment is refined by the training process. It is illustrated on a set of experiments with road-sign-classification problems that the trainable similarity yields high-performance data representations and classifiers. Apart from a multiclass classification accuracy, nonsign rejection capability and computational demands in execution are also discussed. It appears that the trainable similarity representation alleviates some difficulties of other algorithms that are currently used in road-sign classification.@en

Edgedetectioniswelldevelopedareaofimageanalysis.Manyvariouskindsoftechniquesweredesignedforone-channelimages.Also,aconsiderableattentionwaspaidtoedgedetectionincolor,multispectral,andhyperspectralimages.However,therearestillmanyopenissuesinedgedetectioninmultichannelimages.Forexample,eventhede¿nitionofmultichanneledgeisratherempiricalandisnotwellestablished.Inthispaperstatisticalpatternrecognitionmethodologyisusedtoapproachtheproblemofedgedetectionbyconsideringimagepixelsaspointsinamultidimensionalfeaturespace.Appropriatemultivariatetechniquesareusedtoretrieveinformationwhichcanbeusefulforedgedetection.Theproposedapproachesweretestedonthereal-worlddata.@en

This paper presents paper retrieval using the speci¿c paper features chain and laid lines. Paper features are detected in digitized paper images and they are represented such that they could be used for retrieval. Optimal retrieval performance is achieved by means of a trainable similarity measure for a given set of paper features. By means of these methods a retrieval system is developed that art experts could use real-time in order to speed up their paper research.@en

Consider the class of problems in which a target class is well-defined, and an outlier class is ill-defined. In these cases new outlier classes can appear, or the class-conditional distribution of the outlier class itself may be poorly sampled. A strategy to deal with this problem involves a two-stage classifier, in which one stage is designed to perform discrimination between known classes, and the other stage encloses known data to protect against changing conditions. The two stages are, however, interrelated, implying that optimising one may compromise the other. In this paper the relation between the two stages is studied within an ROC analysis framework. We show how the operating characteristics can be used for both model selection, and in aiding in the choice of the reject threshold. An analytic study on a controlled experiment is performed, followed by some experiments on real-world datasets with the distance-based reject-option classifier. Keywords: Ill-defined classification problems; Unseen classes; Reject-option; Model selection; ROC analysis@en

In the past few years a variety of successful algorithms to select/extract discriminative spectral bands was introduced. By exploiting the connectivity of neighbouring spectral bins, these techniques may be more beneficial than the standard feature selection/extraction methods applied for spectral classification. The goal of this paper is to study the effect of the training sample size on the performance of different strategies to select/extract informative spectral regions. We also consider the success of these methods compared to Principal Component Analysis (PCA) for different numbers of extracted components/groups of spectral bands.@en

Abstract A conventional way to discriminate between objects represented by dissimilarities is the nearest neighbor method. A more efficient and sometimes a more accurate solution is offered by other dissimilarity-based classifiers. They construct a decision rule based on the entire training set, but they need just a small set of prototypes, the so-called representation set, as a reference for classifying new objects. Such alternative approaches may be especially advantageous for non-Euclidean or even non-metric dissimilarities. The choice of a proper representation set for dissimilarity-based classifiers is not yet fully investigated. It appears that a random selection may work well. In this paper, a number of experiments has been conducted on various metric and non-metric dissimilarity representations and prototype selection methods. Several procedures, like traditional feature selection methods (here effectively searching for prototypes), mode seeking and linear programming are compared to the random selection. In general, we find out that systematic approaches lead to better results than the random selection, especially for a small number of prototypes. Although there is no single winner as it depends on data characteristics, the k-centres works well, in general. For two-class problems, an important observation is that our dissimilarity-based discrimination functions relying on significantly reduced prototype sets (3¿10% of the training objects) offer a similar or much better classification accuracy than the best k-NN rule on the entire training set. This may be reached for multi-class data as well, however such problems are more difficult. Keywords: Dissimilarity; Representation; Prototype selection; Normal density based classifiers; Nearest neighbor rule@en