Andrea Casanova

Ubiquitous iris recognition by means of mobile devices

Iris authentication/recognition on mobile devices is feasible.Spatial histograms can be exploited for iris features extraction and matching.Performance of iris segmentation/recognition algorithms is strongly affected by capture conditions.Imaging sensors resolution alone does not necessarily result in higher recognition accuracy. The worldwide diffusion of latest generations mobile devices, namely smartphones and tablets, represents the technological premise to a new wave of applications for which reliable owner identification is becoming a key requirement. This crucial task can be approached by means of biometrics (face, iris or fingerprint) by exploiting high resolution imaging sensors typically built-in on this class of devices, possibly resulting in a ubiquitous platform to verify owner identity during any kind of transaction involving the exchange of sensible data. Among the aforementioned biometrics, iris is known for its inherent invariance and accuracy, though only a few works have explored this topic on mobile devices. In this paper a comprehensive method for iris authentication on mobiles by means of spatial histograms is described. The proposed approach has been tested on the MICHE-I iris dataset, featuring subjects captured indoor and outdoor under controlled and uncontrolled conditions by means of built-in cameras aboard three among the most diffused smartphones/tablets on the market. The experimental results collected, provide an interesting insight about the readiness of mobile technology with regard to iris recognition.

The urinary metabolomics profile of an Italian autistic children population and their unaffected siblings

Abstract Objective: A supervised multivariate model to classify the metabolome alterations between autistic spectrum disorders (ASD) patients and controls, siblings of autistic patients, has been realized and used to realize a network model of the ASD patients’ metabolome. Methods: In our experiment we propose a quantification of urinary metabolites with the Mass Spectroscopy technique couple to Gas Chromatography. A multivariate model has been used to extrapolate the variables of importance for a network model of interaction between metabolites. In this way we are able to propose a network-based approach to ASD description. Results: Children with autistic disease composing our studied population showed elevated concentration of several organic acids and sugars. Interactions among diet, intestinal flora and genes may explain such findings. Among them, the 3-(3-hydroxyphenyl)-3-hydroxypropanoic acid has been previously described as altered in autistic subjects. Other metabolites increased are 3,4-dihydroxybutyric acid, glycolic acid and glycine, cis-aconitic acid; phenylalanine, tyrosine, p-hydroxyphenylacetic acid, and homovanillic acid are all involved in the tyrosine pathway leading to neurotransmitter cathecolamine. Conclusion: GC-MS-based metabolomic analysis of the urinary metabolome suggests to have the required sensitivity and specificity to gain insight into ASD phenotypes and aid a personalized network-based medicine approach.

Urinary metabolomics (GC-MS) reveals that low and high birth weight infants share elevated inositol concentrations at birth.

Abstract Objective: Metabolomics is a new “omics” platform aimed at high-throughput identification, quantification and characterization of small-molecule metabolites. The metabolomics approach has been successfully applied to the classification different physiological states and identification of perturbed biochemical pathways. The purpose of the current investigation is the application of metabolomics to explore biological mechanisms which may lead to the onset of metabolic syndrome in adulthood. Methods: We evaluated differences in metabolites in the urine collected within 12 h from 23 infants with IUGR (IntraUterine Growth Restriction), or LGA (Large for Gestational Age), compared to control infants (10 patients defined AGA: Appropriate for Gestational Age). Urinary metabolites were quantified by GC-MS and used to highlight similarities between the two metabolic diseases and identify metabolic markers for their predisposition. Quantified metabolites were analyzed using a multivariate statistics coupled with receiver operator characteristic curve (ROC) analysis of identified biomarkers. Results: Urinary myo-inositol was the most important discriminant between LGA + IUGR and control infants, and displayed an area under the ROC curve = 1. Conclusion: We postulate that the increase in plasma and consequently urinary inositol may constitute a marker of altered glucose metabolism during fetal development in both IUGR and LGA newborns.

White Paper on Industrial Applications of Computer Vision and Pattern Recognition

The paper provides a summary of the contributions to the industrial session at ICIAP2013, describing a few practical applications of Video Analy- sis, in the Surveillance and Security field. The session has been organized to stimulate an open discussion within the scientific community of CVPR on new emerging research areas which deserve particular attention, and may contribute to the improvement of industrial applications in the near future.

Fusion of physiological measures for multimodal biometric systems

Physiological measures are widely studied from a medical point of view. Most applications lie in the field of diagnosis of heart attacks, as regards the ECG, or the detection of epileptic events, in the case of the EEG. In the last ten years, these signals are being investigated also from a biometric point of view, in order to exploit the discriminative capability provided by these measures in recognizing individuals. The present work proposes a multimodal biometric recognition system based on the fusion of the first lead (i) of the electrocardiogram (ECG) with six different bands of the electroencephalogram (EEG). The proposed approach is based on the extraction of fiducial features (peaks) from the ECG combined with spectrum features of the EEG. A dataset has been created, by composing the signals of two well-known databases. The results, reported by means of EER values, AUC values and ROC curves, show good recognition performances.

The Role of Entropy: Mammogram Analysis

This paper introduces entropy as a feature for 1D signals. It proposes the ratio between signal perturbation (i.e. its part within minimum and maximum grey level) and the total signal energy as a measurement of entropy. Linear transformation of 2D signals into 1D signals is also illustrated together with the results. This paper also presents the experimentation carried out on different mammograms containing different pathologies (microcalcification and masses).A comparison between different entropy measures and ours is also illustrated in this study.

EEG/ECG Signal Fusion Aimed at Biometric Recognition

The recognition of individuals based on behavioral and biological characteristics has made important strides over the past few years. Growing interest has been recently devoted to the study of physiological measures, which include the electrical activity of brain (EEG) and heart (ECG). Even if the use of multimodal approaches overcome several limitations of traditional uni-modal biometric systems, the simultaneous use of EEG and ECG characteristics has been scarcely investigated. In this paper, we present a set of preliminary results derived by the investigation of a biometric system based on the fusion of simple features simultaneously extracted from EEG and ECG signals. The reported results show high performance both from uni-modal approach (higher performance being EER = 11.17 and EER = 3.83 for EEG and ECG respectively) and fusion (EER = 2.94). However, caution should be considered in the interpretation of the reported results mainly beacuse the analysis was performed on a limited set of subjects.

Babies: Biometric authentication of newborn identities by means of ear signatures

Many research studies demonstrated that recognition based on ear biometrics offers an accuracy which is comparable to face trait, especially in controlled settings. Our proposal is to exploit it to avoid the problem of newborn swap, which is possible and actually happens, most of all in crowded maternity wards of big hospitals. We tested the viability of this solution using a dataset of ear images of newborns, and the obtained results testify that it is possible to decrease the probability of an error using this technique.

CONTEXT: a technique for image retrieval integrating CONtour and TEXTure information

Many intrinsically 2-dimensional visual signals can be effectively encoded in a 1-D form. This simpler representation is well-suited to both pattern recognition and image retrieval tasks. This paper deals with contour and texture, combined together in order to obtain an effective technique for content based image indexing. The data used for experimentally assessing CONTEXT were contours and textures from various application domains. The experiments reveal a high discriminating power which in turn yields a high perceived quality of the retrieval results.

Equilibrium and dissipative structures role on images

This paper introduces entropy as a feature for 1D signals. We propose as entropy measure the ratio between the signals perturbation (i.e. its part within minimum and maximum grey level) and the total energy of the signal. A linear transformation of 2D signals into 1D signals is also illustrated together with the results concerning natural scene, texture and medical images from a large mammograms database. The aim of this paper is to verify if the entropy variations for a closed system can be a discriminant feature to select homogenous regions.