Loris Nanni

An on-line signature verification system based on fusion of local and global information

An on-line signature verification system exploiting both local and global information through decision-level fusion is presented. Global information is extracted with a feature-based representation and recognized by using Parzen Windows Classifiers. Local information is extracted as time functions of various dynamic properties and recognized by using Hidden Markov Models. Experimental results are given on the large MCYT signature database (330 signers, 16500 signatures) for random and skilled forgeries. Feature selection experiments based on feature ranking are carried out. It is shown experimentally that the machine expert based on local information outperforms the system based on global analysis when enough training data is available. Conversely, it is found that global analysis is more appropriate in the case of small training set size. The two proposed systems are also shown to give complementary recognition information which is successfully exploited using decision-level score fusion.

Local binary patterns variants as texture descriptors for medical image analysis

OBJECTIVE This paper focuses on the use of image-based machine learning techniques in medical image analysis. In particular, we present some variants of local binary patterns (LBP), which are widely considered the state of the art among texture descriptors. After we provide a detailed review of the literature about existing LBP variants and discuss the most salient approaches, along with their pros and cons, we report new experiments using several LBP-based descriptors and propose a set of novel texture descriptors for the representation of biomedical images. The standard LBP operator is defined as a gray-scale invariant texture measure, derived from a general definition of texture in a local neighborhood. Our variants are obtained by considering different shapes for the neighborhood calculation and different encodings for the evaluation of the local gray-scale difference. These sets of features are then used for training a machine-learning classifier (a stand-alone support vector machine). METHODS AND MATERIALS Extensive experiments are conducted using the following three datasets: RESULTS AND CONCLUSION Our results show that the novel variant named elongated quinary patterns (EQP) is a very performing method among those proposed in this work for extracting information from a texture in all the tested datasets. EQP is based on an elliptic neighborhood and a 5 levels scale for encoding the local gray-scale difference. Particularly interesting are the results on the widely studied 2D-HeLa dataset, where, to the best of our knowledge, the proposed descriptor obtains the highest performance among all the several texture descriptors tested in the literature.

Genetic programming for creating Chou’s pseudo amino acid based features for submitochondria localization

Given a protein that is localized in the mitochondria it is very important to know the submitochondria localization of that protein to understand its function. In this work, we propose a submitochondria localizer whose feature extraction method is based on the Chou’s pseudo-amino acid composition. The pseudo-amino acid based features are obtained by combining pseudo-amino acid compositions with hundreds of amino-acid indices and amino-acid substitution matrices, then from this huge set of features a small set of 15 “artificial” features is created. The feature creation is performed by genetic programming combining one or more “original” features by means of some mathematical operators. Finally, the set of combined features are used to train a radial basis function support vector machine. This method is named GP-Loc. Moreover, we also propose a very few parameterized method, named ALL-Loc, where all the “original” features are used to train a linear support vector machine. The overall prediction accuracy obtained by GP-Loc is 89% when the jackknife cross-validation is used, this result outperforms the performance obtained in the literature (85.2%) using the same dataset. While the overall prediction accuracy obtained by ALL-Loc is 83.9%.

Local binary patterns for a hybrid fingerprint matcher

In this work, we present a novel hybrid fingerprint matcher system based on local binary patterns. The two fingerprints to be matched are first aligned using their minutiae, then the images are decomposed in several overlapping sub-windows, each sub-window is convolved with a bank of Gabor filters and, finally, the invariant local binary patterns histograms are extracted from the convolved images. Extensive experiments conducted over the four FVC2002 fingerprint databases show the effectiveness of the proposed hybrid approach with respect to the well-known Ticos minutiae matcher and other image-based approaches. Moreover, a BioHashing approach have been designed using the proposed fixed-length feature vector and very interesting performance has been obtained by combining it with the Ticos minutiae matcher.

Local Ternary Patterns from Three Orthogonal Planes for human action classification

Research highlights? LBP features extracted from the human silhouette. ? Random subspace for human action classification. ? To combine LBP-TOP with LTP. Human action classification is a new field of study with applications ranging from automatically labeling video segments to recognition of suspicious behavior in video surveillance cameras. In this paper we present some variants of Local Binary Patterns from Three Orthogonal Planes (LBP-TOP), which is considered one of the state of the art texture descriptors for human action classification. The standard LBP-TOP operator is defined as a gray-scale invariant texture measure, derived from the standard Local Binary Patterns (LBP). It is obtained by calculating the LBP features from the xt and yt planes of a space-time volume. Our LBP-TOP variants combine the idea of LBP-TOP with Local Ternary Patterns (LTP). The encoding of LTP is used for the evaluation of the local gray-scale difference in the different planes of the space-time volume. Different histograms are concatenated to form the feature vector and a random subspace of linear support vector machines is used for classifying action using the Weizmann database of video images. To the best of our knowledge, our method offers the first set of classification experiments to obtain 100% accuracy using the 10-class Weizmann dataset.

A local approach based on a Local Binary Patterns variant texture descriptor for classifying pain states

This paper focuses on the use of image-based techniques for classifying pain states, in particular we compare several texture descriptors based on Local Binary Patterns (LBP), and we proposed some novel solutions based on the combination of new texture descriptors: the Elongated Ternary Pattern (ELTP) and the Elongated Binary Pattern (ELBP). ELTP is the best performing descriptor in our experiments. The ELBP descriptor combines characteristics of the Local Ternary Pattern (LTP) and ELTP. These two variants of the standard LBP are obtained by considering different shapes for the neighborhood calculation and different encodings for the evaluation of the local gray-scale difference. The resulting extracted features are used to train a support vector machine classifier. Extensive experiments are conducted using the Infant COPE database of neonatal facial images. Our results show that a local approach based on the ELTP feature extractor produces a reliable system for classifying pain states.

Fusion of color spaces for ear authentication

In this work, we propose a local approach for 2D ear authentication based on an ensemble of matchers trained on different color spaces. This is the first work that proposes to exploit the powerful properties of color analysis for improving the performance of an ear matcher. The method described is based on the selection of color spaces from which a set of Gabor features are extracted. The selection is performed using the sequential forward floating selection where the fitness function is related to the optimization of the ear recognition performance. Finally, the matching step is performed by means of the combination by the sum rule of several 1-nearest neighbor classifiers constructed on different color components. The effectiveness of the proposed method is demonstrated using the Notre-Dame EAR data set. Particularly interesting are the results obtained by the new approach in terms of rank-1 (~84%), rank-5 (~93%) and area under the ROC curve (~98.5%), which are better than those obtained by other state-of-the-art 2D ear matchers.

A multi-matcher for ear authentication

In this work we propose a local approach of 2D ear authentication. A multi-matcher system is proposed where each matcher is trained using features extracted from a single sub-window of the whole 2D image. The features are extracted by the convolution of each sub-window with a bank of Gabor Filters, then their dimensionality is reduced by Laplacian EigenMaps. The best matchers, corresponding to the most discriminative sub-windows, are selected by running the Sequential Forward Floating Selection (SFFS). Our experiments, carried out on a database of 114 people, show that combining only few (~ten) sub-windows in the fusion step it is possible to achieve a very low Equal Error Rate.

Weighted Sub-Gabor for face recognition

In this paper, we introduce a new face recognition approach based on the representation of each individual by a feature vector extracted through a bank of Gabor filters and Karhunen-Loeve transform. This method operates directly on sub-patterns of the whole image, extracting features from them. The features obtained by each sub-pattern are used to train a Parzen Window Classifier. Moreover, our method computes the contributions of each part in order to enhance the robustness to facial expression and illumination condition. Extensive experiments carried out on the FERET database of faces prove the advantages of the proposed approach when compared with other well-known techniques.

Prediction of protein structure classes by incorporating different protein descriptors into general Chou's pseudo amino acid composition.

Successful protein structure identification enables researchers to estimate the biological functions of proteins, yet it remains a challenging problem. The most common method for determining an unknown proteins structural class is to perform expensive and time-consuming manual experiments. Because of the availability of amino acid sequences generated in the post-genomic age, it is possible to predict an unknown proteins structural class using machine learning methods given a proteins amino-acid sequence and/or its secondary structural elements. Following recent research in this area, we propose a new machine learning system that is based on combining several protein descriptors extracted from different protein representations, such as position specific scoring matrix (PSSM), the amino-acid sequence, and secondary structural sequences. The prediction engine of our system is operated by an ensemble of support vector machines (SVMs), where each SVM is trained on a different descriptor. The results of each SVM are combined by sum rule. Our final ensemble produces a success rate that is substantially better than previously reported results on three well-established datasets. The MATLAB code and datasets used in our experiments are freely available for future comparison at http://www.dei.unipd.it/node/2357.