Manuele Bicego

On the Use of SIFT Features for Face Authentication

Several pattern recognition and classification techniques have been applied to the biometrics domain. Among them, an interesting technique is the Scale Invariant Feature Transform (SIFT), originally devised for object recognition. Even if SIFT features have emerged as a very powerful image descriptors, their employment in face analysis context has never been systematically investigated. This paper investigates the application of the SIFT approach in the context of face authentication. In order to determine the real potential and applicability of the method, different matching schemes are proposed and tested using the BANCA database and protocol, showing promising results.

The grapevine expression atlas reveals a deep transcriptome shift driving the entire plant into a maturation program.

The authors developed a comprehensive transcriptome atlas in grapevine by comparing the genes expressed in 54 diverse samples accounting for ∼91% of all known grapevine genes. Using a panel of different statistical techniques, they found that the whole plant undergoes transcriptomic reprogramming, driving it towards maturity. We developed a genome-wide transcriptomic atlas of grapevine (Vitis vinifera) based on 54 samples representing green and woody tissues and organs at different developmental stages as well as specialized tissues such as pollen and senescent leaves. Together, these samples expressed ∼91% of the predicted grapevine genes. Pollen and senescent leaves had unique transcriptomes reflecting their specialized functions and physiological status. However, microarray and RNA-seq analysis grouped all the other samples into two major classes based on maturity rather than organ identity, namely, the vegetative/green and mature/woody categories. This division represents a fundamental transcriptomic reprogramming during the maturation process and was highlighted by three statistical approaches identifying the transcriptional relationships among samples (correlation analysis), putative biomarkers (O2PLS-DA approach), and sets of strongly and consistently expressed genes that define groups (topics) of similar samples (biclustering analysis). Gene coexpression analysis indicated that the mature/woody developmental program results from the reiterative coactivation of pathways that are largely inactive in vegetative/green tissues, often involving the coregulation of clusters of neighboring genes and global regulation based on codon preference. This global transcriptomic reprogramming during maturation has not been observed in herbaceous annual species and may be a defining characteristic of perennial woody plants.

Audio-Visual Event Recognition in Surveillance Video Sequences

In the context of the automated surveillance field, automatic scene analysis and understanding systems typically consider only visual information, whereas other modalities, such as audio, are typically disregarded. This paper presents a new method able to integrate audio and visual information for scene analysis in a typical surveillance scenario, using only one camera and one monaural microphone. Visual information is analyzed by a standard visual background/foreground (BG/FG) modelling module, enhanced with a novelty detection stage and coupled with an audio BG/FG modelling scheme. These processes permit one to detect separate audio and visual patterns representing unusual unimodal events in a scene. The integration of audio and visual data is subsequently performed by exploiting the concept of synchrony between such events. The audio-visual (AV) association is carried out online and without need for training sequences, and is actually based on the computation of a characteristic feature called audio-video concurrence matrix, allowing one to detect and segment AV events, as well as to discriminate between them. Experimental tests involving classification and clustering of events show all the potentialities of the proposed approach, also in comparison with the results obtained by employing the single modalities and without considering the synchrony issue

Similarity-based classification of sequences using hidden Markov models

Hidden Markov models (HMM) are a widely used tool for sequence modelling. In the sequence classification case, the standard approach consists of training one HMM for each class and then using a standard Bayesian classification rule. In this paper, we introduce a novel classification scheme for sequences based on HMMs, which is obtained by extending the recently proposed similarity-based classification paradigm to HMM-based classification. In this approach, each object is described by the vector of its similarities with respect to a predetermined set of other objects, where these similarities are supported by HMMs. A central problem is the high dimensionality of resulting space, and, to deal with it, three alternatives are investigated. Synthetic and real experiments show that the similarity-based approach outperforms standard HMM classification schemes.

Investigating hidden Markov models' capabilities in 2D shape classification

In this paper, Hidden Markov Models (HMMs) are investigated for the purpose of classifying planar shapes represented by their curvature coefficients. In the training phase, special attention is devoted to the initialization and model selection issues, which make the learning phase particularly effective. The results of tests on different data sets show that the proposed system is able to accurately classify objects that were translated, rotated, occluded, or deformed by shearing, also in the presence of noise.

A Hidden Markov Model-Based Approach to Sequential Data Clustering

Clustering of sequential or temporal data is more challenging than traditional clustering as dynamic observations should be processed rather than static measures. This paper proposes a HiddenMarkov Model (HMM)-based technique suitable for clustering of data sequences. The main aspect of the work is the use of a probabilistic model-based approach using HMM to derive new proximity distances, in the likelihood sense, between sequences. Moreover, a novel partitional clustering algorithm is designed which alleviates computational burden characterizing traditional hierarchical agglomerative approaches. Experimental results show that this approach provides an accurate clustering partition and the devised distance measures achieve good performance rates. The method is demonstrated on real world data sequences, i.e. the EEG signals due to their temporal complexity and the growing interest in the emerging field of Brain Computer Interfaces.

Soft clustering using weighted one-class support vector machines

This paper describes a new soft clustering algorithm in which each cluster is modelled by a one-class support vector machine (OC-SVM). The proposed algorithm extends a previously proposed hard clustering algorithm, also based on OC-SVM representation of clusters. The key building block of our method is the weighted OC-SVM (WOC-SVM), a novel tool introduced in this paper, based on which an expectation-maximization-type soft clustering algorithm is defined. A deterministic annealing version of the algorithm is also introduced, and shown to improve the robustness with respect to initialization. Experimental results show that the proposed soft clustering algorithm outperforms its hard clustering counterpart, namely in terms of robustness with respect to initialization, as well as several other state-of-the-art methods.

Similarity-based clustering of sequences using hidden Markov models

Hidden Markov models constitute a widely employed tool for sequential data modelling; nevertheless, their use in the clustering context has been poorly investigated. In this paper a novel scheme for HMM-based sequential data clustering is proposed, inspired on the similarity-based paradigm recently introduced in the supervised learning context. With this approach, a new representation space is built, in which each object is described by the vector of its similarities with respect to a predeterminate set of other objects. These similarities are determined using hidden Markov models. Clustering is then performed in such a space. By way of this, the difficult problem of clustering of sequences is thus transposed to a more manageable format, the clustering of points (vectors of features). Experimental evaluation on synthetic and real data shows that the proposed approach largely outperforms standard HMM clustering schemes.

Using hidden Markov models and wavelets for face recognition

In this paper, a new system for face recognition is proposed, based on hidden Markov models (HMM) and wavelet coding. A sequence of overlapping sub-images is extracted from each face image, computing the wavelet coefficients for each of them. The whole sequence is then modelled by using hidden Markov models. The proposed method is compared with a DCT coefficient-based approach (Kohir et al. (1998)), showing comparable results. By using an accurate model selection procedure, we show that results proposed in Kohir can be improved even more. The obtained results outperform all results presented in the literature on the Olivetti Research Laboratory (ORL) face database, reaching a 100% recognition rate. This performance proves the suitability of HMM to deal with the new JPEG2000 image compression standard.

Integrated region- and pixel-based approach to background modelling

In this paper a new probabilistic method for background modelling is proposed, aimed at the application in video surveillance tasks using a monitoring static camera. Recently, methods employing time-adaptive, per pixel, mixture of Gaussians (TAPPMOG) modelling have become popular due to their intrinsic appealing properties. Nevertheless, they are not able per se to monitor global changes in the scene, because they model the background as a set of independent pixel processes. In this paper, we propose to integrate this kind of pixel-based information with higher level region-based information, that permits one to manage also sudden changes of the background. These pixel- and region-based modules are naturally and effectively embedded in a probabilistic Bayesian framework called particle filtering, that allows a multi-object tracking. Experimental comparison with a classic pixel-based approach reveals that the proposed method is really effective in recovering from situations of sudden global illumination changes of the background, as well as limited non-uniform changes of the scene illumination.