Papers by Claudio De Stefano
Lecture Notes in Computer Science, 2008
We present a GA-based feature selection algorithm in which feature subsets are evaluated by means... more We present a GA-based feature selection algorithm in which feature subsets are evaluated by means of a separability index. This index is based on a filter method, which allows to estimate statistical properties of the data, independently of the classifier used. More specifically, the defined index uses covariance matrices for evaluating how spread out the probability distributions of data are in a given n−dimensional space. The effectiveness of the approach has been tested on two satellite images and the results have been compared with those obtained without feature selection and with those obtained by using a previously developed GAbased feature selection algorithm.
Engineering Applications of Artificial Intelligence, 2018
In the field of manuscript studies (palaeography and codicology), a particularly interesting case... more In the field of manuscript studies (palaeography and codicology), a particularly interesting case is the study of highly standardized handwriting and book typologies. In such cases, the analysis of some basic layout features, mainly related to the organization of the page and to the exploitation of the available space, may be very helpful for distinguishing similar scribal hands. In this framework, we have defined a set of layout features to develop a pattern recognition system for identifying the scribes who collaborated to the transcription of a single medieval Latin book. We have also experimentally characterized the discriminative power of each considered feature and we have verified whether the selection of an appropriate subset of features for each scribe, specifically devised for distinguishing him from all the others, could allow us to achieve better results. This approach allowed us to introduce in a very simple way a reject option for rejecting unreliably classified samples, namely those not assigned to any scribe or assigned to more scribes. The experiments, performed on a large database of digital images from the so called ''Avila Bible''-a giant Latin copy of the whole Bible produced during the XII century between Italy and Spain-confirmed the effectiveness of the proposed method. Finally, we made publicly available the data set extracted from the Avila Bible images.
International Journal of Pattern Recognition and Artificial Intelligence, 2007
A new prototyping method based on the evolutionary computation paradigm and on the concept of Vec... more A new prototyping method based on the evolutionary computation paradigm and on the concept of Vector Quantization is proposed. It uses a specifically devised evolutionary algorithm for evolving a set of prototype feature vectors and does not require any a priori knowledge about either the actual number of prototypes or the statistical properties of the input data. Experiments performed by using both synthetic data and handwritten digits randomly extracted from the NIST database have confirmed the effectiveness of the approach.
Using entropy for drawing reliable templates
Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93)
ABSTRACT
Multiple Classifier Systems, 2011
Recently, ensemble techniques have also attracted the attention of Genetic Programing (GP) resear... more Recently, ensemble techniques have also attracted the attention of Genetic Programing (GP) researchers. The goal is to further improve GP classification performances. Among the ensemble techniques, also bagging and boosting have been taken into account. These techniques improve classification accuracy by combining the responses of different classifiers by using a majority vote rule. However, it is really hard to ensure that classifiers in the ensemble be appropriately diverse, so as to avoid correlated errors. Our approach tries to cope with this problem, designing a framework for effectively combine GP-based ensemble by means of a Bayesian Network. The proposed system uses two different approaches. The first one applies a boosting technique to a GP-based classification algorithm in order to generate an effective decision trees ensemble. The second module uses a Bayesian network for combining the responses provided by such ensemble and select the most appropriate decision trees. The Bayesian network is learned by means of a specifically devised Evolutionary algorithm. Preliminary experimental results confirmed the effectiveness of the proposed approach.
Lecture Notes in Computer Science, 2012
Classifier ensemble techniques are effectively used to combine the responses provided by a set of... more Classifier ensemble techniques are effectively used to combine the responses provided by a set of classifiers. Classifier ensembles improve the performance of single classifier systems, even if a large number of classifiers is often required. This implies large memory requirements and slow speeds of classification, making their use critical in some applications. This problem can be reduced by selecting a fraction of the classifiers from the original ensemble. In this work, it is presented an ensemble-based framework that copes with large datasets, however selecting a small number of classifiers composing the ensemble. The framework is based on two modules: an ensemble-based Genetic Programming (GP) system, which produces a high performing ensemble of decision tree classifiers, and a Bayesian Network (BN) approach to perform classifier selection. The proposed system exploits the advantages provided by both techniques and allows to strongly reduce the number of classifiers in the ensemble. Experimental results compare the system with well-known techniques both in the field of GP and BN and show the effectiveness of the devised approach. In addition, a comparison with a pareto optimal strategy of pruning has been performed.
L’articolo intende presentare una ricerca multidisciplinare in corso presso l’Università di Cassi... more L’articolo intende presentare una ricerca multidisciplinare in corso presso l’Università di Cassino. Il progetto si incentra sull’uso di robot per effettuare una visita ad un museo durante l’orario di chiusura, permettendo al visitatore, connesso al robot attraverso il proprio computer di casa o il proprio tablet o smartphone, di controllare e “guidare” il dispositivo attraverso le sale del museo, inquadrando e guardando le varie opere, ottenendone o una semplice visione oppure una esplorazione ampliata dell’opera che si sta osservando, attraverso un database multimediale appositamente predisposto
Lecture Notes in Computer Science, 2005
A new genetic programming based approach to classification problems is proposed. Differently from... more A new genetic programming based approach to classification problems is proposed. Differently from other approaches, the number of prototypes in the classifier is not a priori fixed, but automatically found by the system. In fact, in many problems a single class may contain a variable number of subclasses. Hence, a single prototype, may be inadequate to represent all the members of the class. The devised approach has been tested on several problems and the results compared with those obtained by a different genetic programming based approach recently proposed in the literature.
A multiresolution approach to on-line handwriting segmentation and feature extraction
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., 2004
We present an approach to on-line handwriting segmentation into elementary strokes. The segmentat... more We present an approach to on-line handwriting segmentation into elementary strokes. The segmentation is achieved by exploiting curvature information extracted from the electronic ink at different level of resolution. Such information is then combined into a saliency map, through which the ...
Ninth International Workshop on Frontiers in Handwriting Recognition
We propose a method derived from an analogy with the primate visual system for selecting the best... more We propose a method derived from an analogy with the primate visual system for selecting the best scale at which the electronic ink of the handwriting should be described. According to this analogy, the method computes a multiscale features maps by evaluating the curvature along the ink at different levels of resolution and arranges them into a pyramidal structure. Then, feature values extracted at different scales are combined in such a way that values that locally stand out from their surrounds are enhanced, while those comparable with their neighbours are suppressed. A saliency map is eventually obtained by combining those features value across all possible scales. Such a map is then used to select a representation that is largely invariant with respect to the shape variations encountered in handwriting. Experiments on two data sets have shown that simple algorithms adopting the proposed representation lead to very stable stroke segmentation and feature matching.
<title>Modeling the trade-off between completeness and consistency in genetic-based handwritten character prototyping</title>
Document Recognition and Retrieval VI, 1999
ABSTRACT
Image Analysis and Processing – ICIAP 2011, 2011
In the framework of Palaeography, the use of digital image processing techniques has received inc... more In the framework of Palaeography, the use of digital image processing techniques has received increasing attention in recent years, resulting in a new research field commonly denoted as "digital palaeography". In such a field, a key role is played by both pattern recognition and feature extraction methods, which provide quantitative arguments for supporting expert deductions. In this paper, we present a pattern recognition system which tries to solve a typical palaeographic problem: to distinguish the different scribes who have worked together to the transcription of a single medieval book. In the specific case of a high standardized book typology (the so called Latin "Giant Bible"), we wished to verify if the extraction of certain specifically devised features, concerning the layout of the page, allowed to obtain satisfactory results. To this aim, we have also performed a statistical analysis of the considered features in order to characterize their discriminant power. The experiments, performed on a large dataset of digital images from the so called "Avila Bible"-a giant Latin copy of the whole Bible produced during the XII century between Italy and Spain-confirmed the effectiveness of the proposed method.
2007 IEEE International Geoscience and Remote Sensing Symposium, 2007
We propose a new feature selection algorithm for remote sensing image classification. Our approac... more We propose a new feature selection algorithm for remote sensing image classification. Our approach has been especially devised for applications in which there is a large number of different features that can be potentially selected, implying that the search space is complex and high-dimensional. In this framework, our proposal is that of reformulating the feature selection problem as the search for the optimal subspace in which the different classes are more effectively discriminated. The search has been performed by using a genetic algorithm in which each individual encode the choice of a subspace, and its fitness is a measure of the class seperability in that subspace. The experimental results, performed on two databases, confirmed the effectiveness of the approach.
A feature selection algorithm for handwritten character recognition
2008 19th International Conference on Pattern Recognition, 2008
... F. Fontanella and C. Marrocco DAEIMI Universit`a di Cassino Via G. Di Biasio, 43 02043 Cass... more ... F. Fontanella and C. Marrocco DAEIMI Universit`a di Cassino Via G. Di Biasio, 43 02043 Cassino (FR) Italy {destefano, fontanella, cristina.marrocco ... Table 1. Number of features Nbest of the best selected individual for different val-ues of C. Mean number of selected fea ...
Lecture Notes in Computer Science, 2005
Edit Distance has been widely studied and successfully applied in a large variety of application ... more Edit Distance has been widely studied and successfully applied in a large variety of application domains and many techniques based on this concept have been proposed in the literature. These techniques share the property that, in case of patterns having different lengths, a number of symbols are introduced in the shortest one, or deleted from the longest one, until both patterns have the same length. In case of applications in which strings are used for shape description, however, this property may introduce distortions in the shape, resulting in a distance measure not reflecting the perceived similarity between the shapes to compare. Moving from this consideration, we propose a new edit distance, called Weighted Edit Distance that does not require the introduction or the deletion of any symbol. Preliminary experiments performed by comparing our technique with the Normalized Edit Distance and the Markov Edit Distance have shown very encouraging results.
Incorporating a Wavelet Transform Into a Saliency-Based Method for Online Handwriting Segmentation
International Journal of Pattern Recognition and Artificial Intelligence, 2007
In the framework of a saliency-based approach for segmenting cursive handwriting into elementary ... more In the framework of a saliency-based approach for segmenting cursive handwriting into elementary strokes, we propose a smoothing technique based on the use of a Wavelet Transform to describe the electronic ink at different resolutions. According to such an approach, derived in analogy with those proposed in the literature for early visual tasks in primates, curvature maxima corresponding to actual segmentation points are separated from those produced by the different source of noise affecting the handwriting generation process. This is obtained by evaluating the curvature maxima at different levels of resolution, and by arranging them into a pyramidal structure, from which a saliency map is eventually achieved by combining the values across all possible scales. Such maps enjoy the property of exhibiting higher values in correspondence of regions of the original ink where curvature maxima survive along difference scales, thus indicating that those regions should correspond to the par...
2009 10th International Conference on Document Analysis and Recognition, 2009
Combining classifier methods have shown their effectiveness in a number of applications. Nonethel... more Combining classifier methods have shown their effectiveness in a number of applications. Nonetheless, using simultaneously multiple classifiers may result in some cases in a reduction of the overall performance, since the responses provided by some of the experts may generate consensus on a wrong decision even if other experts provided the correct one. To reduce these undesired effects, in a previous study, we proposed a combining method based on the use of a Bayesian Network. In this paper, we present an improvement of that method which allows to solve some of the drawbacks exhibited by standard learning algorithms for Bayesian Networks. The proposed method is based on an Evolutionary Algorithm which uses a specifically devised data structure to encode direct acyclic graphs. This data structure allows to effectively implement crossover and mutation operators. The experimental results, obtained by using three standard databases, confirmed the effectiveness of the method.
Handwritten numeral recognition by means of evolutionary algorithms
C. De Stefano Facolt`a di Ingegneria Universit`a del Sannio I82100 Benevento, ITALY cladeste@uni... more C. De Stefano Facolt`a di Ingegneria Universit`a del Sannio I82100 Benevento, ITALY [email protected] ... A. Della Cioppa Dipartimento di Informatica e Sistemistica Universit`a di Napoli Federico II I80125 Napoli, ITALY [email protected] ... A. Marcelli Dipartimento di ...
Pattern Recognition Letters, 2002
This paper presents a learning system that uses genetic programming as a tool for automatically i... more This paper presents a learning system that uses genetic programming as a tool for automatically inferring the set of classification rules to be used during a preclassification stage by a hierarchical handwritten character recognition system. Starting from a structural description of the character shape, the aim of the learning system is that of producing a set of classification rules able to capture the similarities among those shapes, independently of whether they represent characters belonging to the same class or to different ones. In particular, the paper illustrates the structure of the classification rules, the grammar used to generate them and the genetic operators devised to manipulate the set of rules, as well as the fitness function used to drive the inference process. The experimental results obtained by using a set of 10,000 digits extracted from the NIST database show that the proposed preclassification is efficient and accurate, because it provides at most 6 classes for more than 87% of the samples, and the error rate almost equals the intrinsic confusion found in the data set.
Learning handwriting by evolution: a conceptual framework for performance evaluation and tuning
Pattern Recognition, 2002
... They have been typically applied to function-optimization problems with noisy, real-valued fu... more ... They have been typically applied to function-optimization problems with noisy, real-valued functions. ... of a fitness function φ, as follows: given a objective function , the fitness value of an ... discovers as many niches as the number of peaks in a multimodal fitness landscape [18]. ...
Uploads
Papers by Claudio De Stefano