Publications (selected):
  1. Pattern Recognition: A Quality of Data Perspective, a monograph by Wladyslaw Homenda and Witold Pedrycz
  2. Unsupervised Mode of Rejection of Foreign Patterns, by: Wladyslaw Homenda, Agnieszka Jastrzebska, Witold Pedrycz
  3. Classification with a Limited Space of Features: Improving Quality by Rejecting Misclassifications, by: Wladyslaw Homenda, Agnieszka Jastrzebska, Witold Pedrycz, Radoslaw Piliszek
  4. Classification with rejection based on various SVM techniques, by: Wladyslaw Homenda, Marcin Luckner, Witold Pedrycz
  5. Classification with rejection: concepts and evaluations, by: Wladyslaw Homenda, Marcin Luckner, Witold Pedrycz
  6. Clustering as a Tool of Reinforced Rejecting in Pattern Recognition Problem, by: Jakub Ciecierski, Bartlomiej Dybisz, Wladyslaw Homenda, Agnieszka Jastrzebska
  7. Dealing with Contaminated Datasets: an Approach to Classifier Training, by: Wladyslaw Homenda, Agnieszka Jastrzebska, Mariusz Rybnik
  8. Decision Making beyond Pattern Recognition: Classification or Rejection, by: Wladyslaw Homenda, Agnieszka Jastrzebska, Piotr Waszkiewicz
  9. Decision Trees and Their Families in Imbalanced Pattern Recognition: Recognition with and without Rejection, by: Wladyslaw Homenda, Wojciech Lesinski
  10. Global and Local Rejection Option in Multi–classification Task, by: Marcin Luckner
  11. Global, Local and Embedded Architectures for Multiclass Classification with Foreign Elements Rejection: an Overview, by: Wladyslaw Homenda, Agnieszka Jastrzebska
  12. Imbalanced Pattern Recognition: Concepts and Evaluations, by: Wladyslaw Homenda, Wojciech Lesinski
  13. Pattern Classification with Rejection Using Cellular Automata-Based Filtering, by: Agnieszka Jastrzebska, Rafael Toro Sluzhenko
  14. Pattern Recognition with Rejection: Application to Handwritten Digits, by: Wladyslaw Homenda, Marcin Luckner
  15. Pattern Recognition with Rejection. Combining Standard Classification Methods with Geometrical Rejecting, by: Wladyslaw Homenda, Agnieszka Jastrzebska, Piotr Waszkiewicz, Anna Zawadzka
  16. Rejecting Foreign Elements in Pattern Recognition Problem. Reinforced Training of Rejection Level, by: Wladyslaw Homenda, Agnieszka Jastrzebska, Witold Pedrycz




Details:
  1. Book Title: Pattern Recognition: A Quality of Data Perspective

    Authors: Wladyslaw Homenda and Witold Pedrycz

    To be published in: John Wiley & Sons

  2. Title: Unsupervised Mode of Rejection of Foreign Patterns

    Authors: Wladyslaw Homenda, Agnieszka Jastrzebska, Witold Pedrycz

    Published in: Applied Soft Computing 57 (2017) 615–626.

    Abstract: The study deals with an issue of recognition of native (proper) patterns and rejection of foreign (erroneous) patterns. We present a novel unsupervised approach to rejecting foreign patterns. We construct a geometrical model, which identifies regions in the feature space that are predominantly occupied by native patterns and determines regions where foreign patterns are localized. The model is constructed in an unsupervised mode: we engage clustering to discover structures in the data and use the revealed geometry to form regions with high likelihood of being occupied by native patterns and regions in which foreign patterns are likely to be localized. The geometry of the region of rejected patterns is adjusted by two parameters, which are tuned to achieve a sound balance between rejection of foreign patterns and acceptance of native patterns. It is shown that the proposed method is applicable not only to multiclass data processing problems, but it could also be beneficial in situations when the only available informa- tion concerns a single phenomenon (a so-called a one-class data). We demonstrate the usefulness of the proposed approach by studying several publicly available medical datasets.

    Link at ScienceDirect: http://www.sciencedirect.com/science/article/pii/S1568494617302181

  3. Title: Classification with a Limited Space of Features: Improving Quality by Rejecting Misclassifications

    Authors: Wladyslaw Homenda, Agnieszka Jastrzebska, Witold Pedrycz, Radoslaw Piliszek

    Published in: Proceedings of the 2014 World Congress on Information and Communication Technologies (WICT 2014), Malacca, Malaysia, 08-11.12.2014, IEEE Catalog Number: CFP1468R-ART ISBN: 978-1-4799-8115-1, pp. 164 - 169

    Abstract: Standard assumption of pattern recognition problem is that processed elements belong to recognized classes. However, in practice, we are often faced with elements presented to recognizers, which do not belong to such classes. For instance, paper-to-computer recognition technologies (e.g. character or music recognition technologies, both printed and handwritten) must cope with garbage elements produced at segmentation level. In this paper we distinguish between elements of desired classes and other ones. We call them native and foreign elements, respectively. The assumption that we have only native elements results in incorrect inclusion of foreign ones into desired classes. Since foreign elements are usually not known at the stage of recognizer construction, standard classification methods fail to eliminate them. In this paper we study construction of recognizers based on support vector machines and aimed on coping with foreign elements. Several tests are performed on real-world data.

    Link to the paper on publisher's site: http://ieeexplore.ieee.org/document/7077322/

  4. Title: Classification with rejection based on various SVM techniques

    Authors: Wladyslaw Homenda, Marcin Luckner, Witold Pedrycz

    Published in: Proceedings of 2014 International Joint Conference on Neural Networks (IJCNN), pp. 3480 - 3487.

    Abstract: The task of identifying native and foreign elements and rejecting foreign ones in the pattern recognition problem is discussed in this paper. Such the task is a nonstandard aspect of pattern recognition, which is rarely present in research. In this paper, ensembles of support vector machines solving two–classes and one–class problems are employed as classification tools and as basic tools for rejecting of foreign elements. Evaluation of quality of classification and rejection methods are proposed in the paper and finally some experiments are performed in order to illustrate acquainted terms and methods.

    Link at the publisher's site: http://ieeexplore.ieee.org/document/6889655/

  5. Title: Classification with rejection: concepts and evaluations

    Authors: Wladyslaw Homenda, Marcin Luckner, Witold Pedrycz

    Published in: Skulimowski A., Kacprzyk J. (eds) Knowledge, Information and Creativity Support Systems: Recent Trends, Advances and Solutions. Advances in Intelligent Systems and Computing, vol 364. Springer, pp. 413 - 425.

    Abstract: Standard classification process allocates all processed elements to given classes. Such type of classification assumes that there is are only native and no foreign elements, i.e. all processed elements are included in given classes. The quality of standard classification can be measured by two factors: numbers of correctly and incorrectly classified elements, called True Positives and False Positives. Admitting foreign elements in standard classification process increases False Positives and, in this way, deteriorates quality of classification. In this context, it is desired to reject foreign elements, i.e. to not assign them to any of given classes. Rejecting foreign elements will reduce the number of False Positives, but can also reject native elements reducing True Positives as side effect. Therefore, it is important to build well designed rejection, which will reject significant part of foreigners and only few natives. In this paper, evaluations of classification with rejection concepts are presented. Three main models: a classification without rejection, a classification with rejection, and a classification with reclassification are presented. The concepts are illustrated by flexible ensembles of binary classifiers with evaluations of each model. The proposed models can be used, in particular, as classifiers working with noised data, where recognized input is not limited to elements of known classes.

    Link at the publisher's site: https://link.springer.com/chapter/10.1007/978-3-319-19090-7_31

  6. Title: Clustering as a Tool of Reinforced Rejecting in Pattern Recognition Problem

    Authors: Jakub Ciecierski, Bartlomiej Dybisz, Wladyslaw Homenda, Agnieszka Jastrzebska

    Published in: Proceedings of the International Conference on Numerical Analysis and Applied Mathematics 2015 (ICNAAM 2015), AIP Conference Proceedings 1738, 180004, 2016, pp. 180004-1 - 180004-4.

    Abstract: In this paper pattern recognition problem with rejecting option is discussed. The problem is aimed at classification patterns from given classes (native patterns) and rejecting ones not belonging to these classes (foreign patterns). In practice the characteristics of the native patters are given, while no information about foreign ones is known. A rejecting tool is aimed at enclosing native patterns in compact geometrical figures and excluding foreign ones from them.

    Link to the paper on publisher's site: http://aip.scitation.org/doi/abs/10.1063/1.4951951

  7. Title: Dealing with Contaminated Datasets: an Approach to Classifier Training

    Authors: Wladyslaw Homenda, Agnieszka Jastrzebska, Mariusz Rybnik

    Published in: Proceedings of the International Conference on Numerical Analysis and Applied Mathematics 2015 (ICNAAM 2015), AIP Conference Proceedings 1738, 180005, 2016, pp. 180005-1 - 180005-4.

    Abstract: The paper presents a novel approach to classification reinforced with rejection mechanism. The method is based on a two-tier set of classifiers. First layer classifies elements, second layer separates native elements from foreign ones in each distinguished class. The key novelty presented here is rejection mechanism training scheme according to the philosophy "one-against-all-other-classes". Proposed method was tested in an empirical study of handwritten digits recognition.

    Link at the publisher's site: http://aip.scitation.org/doi/abs/10.1063/1.4951952

  8. Title: Decision Making beyond Pattern Recognition: Classification or Rejection

    Authors: Wladyslaw Homenda, Agnieszka Jastrzebska, Piotr Waszkiewicz

    To be published in: Proceedings of KES 2017

  9. Title: Decision Trees and Their Families in Imbalanced Pattern Recognition: Recognition with and without Rejection

    Authors: Wladyslaw Homenda, Wojciech Lesinski

    Published in: Proceedings of CISIM 2014, LNCS 8838, pp. 219–230, 2014.

    Abstract: Decision trees are considered to be among the best classifiers. In this work we use decision trees and its families to the problem of imbalanced data recognition. Considered are aspects of recognition without rejection and with rejection: it is assumed that all recognized elements belong to desired classes in the first case and that some of them are outside of such classes and are not known at classifiers training stage. The facets of imbalanced data and recognition with rejection affect different real world problems. In this paper we discuss results of experiment of imbalanced data recognition on the case study of music notation symbols. Decision trees and three methods of joining decision trees (simple voting, bagging and random forest) are studied. These methods are used for recognition without and with rejection.

    Link at the publisher's site: https://link.springer.com/chapter/10.1007/978-3-662-45237-0_22

  10. Title: Global and Local Rejection Option in Multi–classification Task

    Authors: Marcin Luckner

    Published in: Proceedings of ICANN 2014, LNCS 8681, pp. 483–490, 2014.

    Abstract: This work presents two rejection options. The global rejection option separates the foreign observations – not defined in the classification task – from the normal observations. The local rejection option works after the classification process and separates observations individually for each class. We present implementation of both methods for binary classifiers grouped in a graph structure (tree or directed acyclic graph). Next, we prove that the quality of rejection is identical for both options and depends only on the quality of binary classifiers. The methods are compared on the handwritten digits recognition task. The local rejection option works better for the most part.

    Link at the publisher's site: https://link.springer.com/chapter/10.1007/978-3-319-11179-7_61

  11. Title: Global, Local and Embedded Architectures for Multiclass Classification with Foreign Elements Rejection: an Overview

    Authors: Wladyslaw Homenda, Agnieszka Jastrzebska

    Published in: Proceedings of the 7th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2015), Fukuoka, 13-15.11.2015, IEEE Computer Society Press, 978-1-4673-9360-7, pp. 89-94.

    Abstract: In the paper we look closely at the issue of contaminated data sets, where apart from proper elements we may have garbage. In a typical scenario, further classification of such data sets is always negatively influenced by garbage elements. Ideally, we would like to remove them from the data set entirely. Garbage elements are called here foreign elements and the task of removing them from the data set is called rejection of foreign elements. The paper is devoted to comparison and analysis of three different models capable to perform classification with rejection of foreign elements. It shall be emphasized that all studied methods are based only on proper patterns and no knowledge about foreign elements is needed to construct them. Hence, the methods we study are truly general and could be applied in many ways and in many problems. The following classification/rejection architectures are considered: global, local, and embedded. We analyze their performance in two aspects: influence of rejection mechanisms on classification and the quality of rejection. Issues are addressed theoretically and empirically in a study of handwritten digits recognition. Results show that the local architecture and the embedded architecture are advantageous, in comparison to the global architecture.

    Link at the publisher's site: http://ieeexplore.ieee.org/document/7492789/

  12. Title: Imbalanced Pattern Recognition: Concepts and Evaluations

    Authors: Wladyslaw Homenda, Wojciech Lesinski

    Published in: Proceedings of 2014 International Joint Conference on Neural Networks (IJCNN), pp. 3488 - 3495.

    Abstract: In this paper we propose and investigate a concept of imbalanced pattern recognition problems and evaluation methods of solutions applied to solve such problems. The attention is focused on so called paper-to-computer technologies, but it is not limited to them due to possible direct generalization to other domains. Besides bringing a concept of imbalanced pattern recognition problem, classification quality from the perspective of single classes is considered. Parameters of binary classification and parameters and measures used in signal detection theory are adopted. Quality of classification in terms of one class contra all others is taken into account. Then, classifiers performance in frames of one class at the background of other classes and in frames of impact of other classes on the given on are evaluated. Finally, parameters characterizing global properties of classification are introduced and illustrated.

    Link at the publisher's site: http://ieeexplore.ieee.org/document/6889783/?reload=true

  13. Title: Pattern Classification with Rejection Using Cellular Automata-Based Filtering

    Authors: Agnieszka Jastrzebska, Rafael Toro Sluzhenko

    Published in: Proceedings of CISIM 2017, LNCS 10244, pp. 3–14.

    Abstract: In this article we address the problem of contaminated data in pattern recognition tasks, where apart from native patterns we may have foreign ones that do not belong to any native class. We present a novel approach to image classification with foreign pattern rejection based on cellular automata. The method is based only on native patterns, so no knowledge about characteristics of foreign patterns is required at the stage of model construction. The proposed approach is evaluated in a study of handwritten digits recognition. As foreign patterns we use distorted digits. Experiments show that the proposed model classifies native patterns with a high success rate and rejects foreign patterns as well.

    Link at the publisher's site: https://link.springer.com/chapter/10.1007/978-3-319-59105-6_1

  14. Title: Pattern Recognition with Rejection: Application to Handwritten Digits

    Authors: Wladyslaw Homenda, Marcin Luckner

    Published in: Proceedings of 2014 Fourth World Congress on Information and Communication Technologies (WICT), pp. 326 - 331.

    Abstract: The paper considers rejecting option in pattern recognition problem. Studied are native and foreign elements in a multi-class pattern recognition. Native elements are those included in recognized classes, they are known at the stage of classifier design. Foreign elements do not belong to recognized classes. Usually foreign elements are not known when classifier is designed. If foreign elements are classified to recognized classes, recognition quality is deteriorated. So then, they are classified to native classes, if they are not rejected. In such the case, recognition quality is deteriorated. Therefore, they should be rejected by a classifier, i.e. not classified to any class. Several attempts to rejection of foreign elements are investigated in this study.

    Link at the publisher's site: http://ieeexplore.ieee.org/document/7077288/

  15. Title: Pattern Recognition with Rejection. Combining Standard Classification Methods with Geometrical Rejecting

    Authors: Wladyslaw Homenda, Agnieszka Jastrzebska, Piotr Waszkiewicz, Anna Zawadzka

    Published in: Proceedings of CISIM 2016, Springer: Lecture Notes in Computer Science 9842, pp. 589 – 602.

    Abstract: The motivation of our study is to provide algorithmic approaches to distinguish proper patterns, from garbage and erroneous patterns in a pattern recognition problem. The design assumption is to provide methods based on proper patterns only. In this way the approach that we propose is truly versatile and it can be adapted to any pattern recognition problem in an uncertain environment, where garbage patterns may appear. The proposed attempt to recognition with rejection combines known classifiers with geometric methods used for separating native patterns from foreign ones. Empirical verification has been conducted on datasets of handwritten digits classification (native patterns) and handwritten letters of Latin alphabet (foreign patterns).

    Link at the publisher's site: https://link.springer.com/chapter/10.1007/978-3-319-45378-1_52

  16. Title: Rejecting Foreign Elements in Pattern Recognition Problem. Reinforced Training of Rejection Level

    Authors: Wladyslaw Homenda, Agnieszka Jastrzebska, Witold Pedrycz

    Published in: Proceedings of the 7th International Conference on Agents and Artificial Intelligence (ICAART 2015), Lisbon 10-12.01.2015, pp. 90 – 99.

    Abstract: Standard assumption of pattern recognition problem is that processed elements belong to recognized classes. However, in practice, we are often faced with elements presented to recognizers, which do not belong to such classes. For instance, paper-to-computer recognition technologies (e.g. character or music recognition technologies, both printed and handwritten) must cope with garbage elements produced at segmentation level. In this paper we distinguish between elements of desired classes and other ones. We call them native and foreign elements, respectively. The assumption that we have only native elements results in incorrect inclusion of foreign ones into desired classes. Since foreign elements are usually not known at the stage of recognizer construction, standard classification methods fail to eliminate them. In this paper we study construction of recognizers based on support vector machines and aimed on coping with foreign elements. Several tests are performed on real-world data.

    Link to the paper on publisher's site: http://www.scitepress.org/DigitalLibrary/PublicationsDetail.aspx?ID=wnMra1PrgaI=&t=1