ROLI , Fabio

Recent work has shown that deep-learning algorithms for malware detection are also susceptible to adversarial examples, i.e., carefully-crafted perturbations to input malware that enable misleading classification. Although this has questioned their suitability for this task, it is not yet clear why such algorithms are easily fooled also in this...

Recent works have investigated the robustness to spoofing attacks of multi-modal biometric systems in parallel fusion mode. Contrary to a common belief, it has been shown that they can be cracked by spoofing only one biometric trait. Robustness evaluation of multi-modal systems in serial fusion mode has not yet been investigated, instead. Thus,...

No description

Recently, a kind of structured neural networks (SNNs) explicitly devoted to multisensor image recognition and aimed at allowing the interpretation of the ''network behavior'' was presented in Ref. 1. Experiments reported in Ref. 1 pointed out that SNNs provide a trade-off between recognition accuracy and interpretation of the network behavior....

No description

Multiple classifier systems have been originally proposed for supervised classification tasks. In the five editions of MCS workshop, most of the papers have dealt with design methods and applications of supervised multiple classifier systems. Recently, the use of multiple classifier systems has been extended to unsupervised classification...

An image analysis algorithm for detecting cracks on textured surfaces is presented. It is based on a new measure of texture anisotropy that is used to characterise the pixels of the image of an inspected surface. Experimental results on the detection of cracks on granite slabs are reported.

In the field of pattern recognition, fusion of multiple classifiers is currently used for solving difficult recognition tasks and designing high performance systems. This chapter is aimed at providing the reader with a gentle introduction to this fertile area of research. We open the chapter with a discussion about motivations for the use of...

The application of structured neural networks to the supervised classification of multisensor images is discussed. The purpose is to give a criterion for network architecture definition and to allow the interpretation of the network behavior. The latter result can be used to understand the importance of sensors and related channels to the...

So far few theoretical works investigated the conditions under which specific fusion rules can work well, and a unifying framework for comparing rules of different complexity is clearly beyond the state of the art. A clear theoretical comparison is lacking even if one focuses on specific classes of combiners (e.g., linear combiners). In this...

Multiple classifier systems (MCSs) based on the combination of outputs of a set of different classifiers have been proposed in the field of pattern recognition as a method for the development of high performance classification systems. Previous work clearly showed that multiple classifier systems are effective only if the classifiers forming...

Multiple classifier systems have been originally proposed for supervised classification tasks, and few works have dealt with semi-supervised multiple classifiers. However, there are important pattern recognition applications, such as multi-sensor remote sensing and multi-modal biometrics, which demand semi-supervised multiple classifier systems...

In this paper, the problem of implementing the reject option in support vector machines (SVMs) is addressed. We started by observing that methods proposed so far simply apply a reject threshold to the outputs of a trained SVM. We then showed that, under the framework of the structural risk minimisation principle, the rejection region must be...

At present, the usual operation mechanism of multiple classifier systems is the combination of classifier outputs. Recently, some researchers have pointed out the potentialities of "dynamic classifier selection" as an alternative operation mechanism. However, such potentialities have been motivated so far by experimental results and qualitative...

In this paper, a theoretical and experimental analysis of linear combiners for multiple classifier systems is presented. Although linear combiners are the most frequently used combining rules, many important issues related to their operation for pattern classification tasks lack a theoretical basis. After a critical review of the framework...

In this paper, the error-reject trade-off of linearly combined multiple classifiers is analysed in the framework of the minimum risk theory. Theoretical analysis described in [12,13] is extended for handling reject option and the optimality of the error-reject trade-off is analysed under the assumption of independence among the errors of the...

In this paper, a theoretical and experimental analysis of the error-reject trade-off achievable by linearly combining the outputs of an ensemble of classifiers is presented. To this aim, the theoretical framework previously developed by Tumer and Ghosh for the analysis of the simple average rule without the reject option has been extended....

In the last decade, the application of statistical and neural network classifiers to remote-sensing images has been deeply investigated. Therefore, performances, characteristics, and pros and cons of such classifiers are quite well known, even from remote-sensing practitioners. In this paper, we present the application ...

Despite the efforts to reduce the so-called semantic gap between the user's perception of image similarity and the feature-based representation of images, the interaction with the user remains fundamental to improve performances of content-based image retrieval systems. To this end, relevance feedback mechanisms are adopted to refine...

In the field of pattern recognition, the combination of an ensemble of neural networks has been proposed as an approach to the development of high performance image classification systems. However, previous work clearly showed that such image classification systems are effective only if the neural networks forming them make different errors....