Carlo Sansone

On the influence of denoising in PRNU based forgery detection

To detect some image forgeries one can rely on the Photo-Response Non-Uniformity (PRNU), a deterministic pattern associated with each individual camera, which can be loosely modeled as low-intensity multiplicative noise. A very promising algorithm for PRNU-based forgery detection has been recently proposed by Chen et al. Image denoising is a key step of the algorithm, since it allows to single out and remove most of the signal components and reveal the PRNU pattern. In this work we analyze the influence of denoising on the overall performance of the method and show that the use of a suitable state-of-the art denoising technique improves performance appreciably w.r.t. the original algorithm.

Fingerprint liveness detection based on Weber Local image Descriptor

In this paper, we investigate the use of a local discriminative feature space for fingerprint liveness detection. In particular, we rely on the Weber Local Descriptor (WLD), which is a powerful and robust descriptor recently proposed for texture classification. Inspired by Webers law, it consists of two components, differential excitation and orientation, evaluated for each pixel of the image. Joint histograms of these components are then processed to build the discriminative features used to train a linear kernel SVM classifier. Experimental results with different databases and different sensors show WLD to perform favorably compared to the state-of-the-art methods in fingerprint liveness detection. In addition, by combining WLD with LPQ (Local Phase Quantization) results further improve significantly.

Local contrast phase descriptor for fingerprint liveness detection

We propose a new local descriptor for fingerprint liveness detection. The input image is analyzed both in the spatial and in the frequency domain, in order to extract information on the local amplitude contrast, and on the local behavior of the image, synthesized by considering the phase of some selected transform coefficients. These two pieces of information are used to generate a bi-dimensional contrast-phase histogram, used as feature vector associated with the image. After an appropriate feature selection, a trained linear-kernel SVM classifier makes the final live/fake decision. Experiments on the publicly available LivDet 2011 database, comprising datasets collected from various sensors, prove the proposed method to outperform the state-of-the-art liveness detection techniques. HighlightsWe propose a new local descriptor for fingerprint liveness detection.It is based on the joint use of contrast and phase information.Image analysis is carried out in both the spatial and the transform domains.We generate a bi-dimensional contrast-phase histogram, used as feature vector.A properly trained linear-kernel SVM classifier makes the final live/fake decision.

A multiple classifier system for classification of breast lesions using dynamic and morphological features in DCE-MRI

In this paper we propose a Multiple Classifier System (MCS) for classifying breast lesions in Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI). The proposed MCS combines the results of two classifiers trained with dynamic and morphological features respectively. Twenty-one malignant and seventeen benign breast lesions, histologically proven, were analyzed. Volumes of Interest (VOIs) have been automatically extracted via a segmentation procedure assessed in a previous study. The performance of the MCS have been compared with histological classification. Results indicated that with automatic segmented VOIs 90% of test-set lesions were correctly classified.

A comparative analysis of forgery detection algorithms

The aim of this work is to make an objective comparison between different forgery techniques and present a tool that helps taking a more reliable decision about the integrity of a given image or part of it. The considered techniques, all recently proposed in the scientific community, follow different and complementary approaches so as to guarantee robustness with respect to tampering of different types and characteristics. Experiments have been conducted on a large set of images using an automatic copy-paste tampering generator. Early results point out significant differences about competing techniques, depending also on complexity and side information.

Influence of QT correction on temporal and amplitude features for human identification via ECG

Identification of humans via ECG is being increasingly studied because it can have several advantages over the traditional biometric identification techniques. However, difficulties arise because of the heartrate variability. In this study we analysed the influence of QT interval correction on the performance of an identification system based on temporal and amplitude features of ECG. In particular we tested MLP, Naive Bayes and 3-NN classifiers on the Fantasia database. Results indicate that QT correction can significantly improve the overall system performance.