Michele Nappi

A range/domain approximation error-based approach for fractal image compression

Fractals can be an effective approach for several applications other than image coding and transmission: database indexing, texture mapping, and even pattern recognition problems such as writer authentication. However, fractal-based algorithms are strongly asymmetric because, in spite of the linearity of the decoding phase, the coding process is much more time consuming. Many different solutions have been proposed for this problem, but there is not yet a standard for fractal coding. This paper proposes a method to reduce the complexity of the image coding phase by classifying the blocks according to an approximation error measure. It is formally shown that postponing range/spl bsol/slash domain comparisons with respect to a preset block, it is possible to reduce drastically the amount of operations needed to encode each range. The proposed method has been compared with three other fractal coding methods, showing under which circumstances it performs better in terms of both bit rate and/or computing time.

FIRME: Face and Iris Recognition for Mobile Engagement☆

Abstract Mobile devices, namely phones and tablets, have long gone “smart”. Their growing use is both a cause and an effect of their technological advancement. Among the others, their increasing ability to store and exchange sensitive information, has caused interest in exploiting their vulnerabilities, and the opposite need to protect users and their data through secure protocols for access and identification on mobile platforms. Face and iris recognition are especially attractive, since they are sufficiently reliable, and just require the webcam normally equipping the involved devices. On the contrary, the alternative use of fingerprints requires a dedicated sensor. Moreover, some kinds of biometrics lend themselves to uses that go beyond security. Ambient intelligence services bound to the recognition of a user, as well as social applications, such as automatic photo tagging on social networks, can especially exploit face recognition. This paper describes FIRME (Face and Iris Recognition for Mobile Engagement) as a biometric application based on a multimodal recognition of face and iris, which is designed to be embedded in mobile devices. Both design and implementation of FIRME rely on a modular architecture, whose workflow includes separate and replaceable packages. The starting one handles image acquisition. From this point, different branches perform detection, segmentation, feature extraction, and matching for face and iris separately. As for face, an antispoofing step is also performed after segmentation. Finally, results from the two branches are fused. In order to address also security-critical applications, FIRME can perform continuous reidentification and best sample selection. To further address the possible limited resources of mobile devices, all algorithms are optimized to be low-demanding and computation-light.

Mobile Iris Challenge Evaluation (MICHE)-I, biometric iris dataset and protocols

A new dataset of iris images acquired by mobile devices can support researchers.MICHE-I will assist with developing continuous authentication to counter spoofing.The dataset includes images from different mobile devices, sessions and conditions. We introduce and describe here MICHE-I, a new iris biometric dataset captured under uncontrolled settings using mobile devices. The key features of the MICHE-I dataset are a wide and diverse population of subjects, the use of different mobile devices for iris acquisition, realistic simulation of the acquisition process (including noise), several data capture sessions separated in time, and image annotation using metadata. The aim of MICHE-I dataset is to make up the starting core of a wider dataset that we plan to collect, with the further aim to address interoperability, both in the sense of matching samples acquired with different devices and of assessing the robustness of algorithms to the use of devices with different characteristics. We discuss throughout the merits of MICHE-I with regard to biometric dimensions of interest including uncontrolled settings, demographics, interoperability, and real-world applications. We also consider the potential for MICHE-I to assist with developing continuous authentication aimed to counter adversarial spoofing and impersonation, when the bar for uncontrolled settings raises even higher for proper and effective defensive measures.

Moving face spoofing detection via 3D projective invariants

Face recognition provides many advantages compared with other available biometrics, but it is particularly subject to spoofing. The most accurate methods in literature addressing this problem, rely on the estimation of the three-dimensionality of faces, which heavily increase the whole cost of the system. This paper proposes an effective and efficient solution to problem of face spoofing. Starting from a set of automatically located facial points, we exploit geometric invariants for detecting replay attacks. The presented results demonstrate the effectiveness and efficiency of the proposed indices.

Robust Face Recognition for Uncontrolled Pose and Illumination Changes

Face recognition has made significant advances in the last decade, but robust commercial applications are still lacking. Current authentication/identification applications are limited to controlled settings, e.g., limited pose and illumination changes, with the user usually aware of being screened and collaborating in the process. Among others, pose and illumination changes are limited. To address challenges from looser restrictions, this paper proposes a novel framework for real-world face recognition in uncontrolled settings named Face Analysis for Commercial Entities (FACE). Its robustness comes from normalization (“correction”) strategies to address pose and illumination variations. In addition, two separate image quality indices quantitatively assess pose and illumination changes for each biometric query, before submitting it to the classifier. Samples with poor quality are possibly discarded or undergo a manual classification or, when possible, trigger a new capture. After such filter, template similarity for matching purposes is measured using a localized version of the image correlation index. Finally, FACE adopts reliability indices, which estimate the “acceptability” of the final identification decision made by the classifier. Experimental results show that the accuracy of FACE (in terms of recognition rate) compares favorably, and in some cases by significant margins, against popular face recognition methods. In particular, FACE is compared against SVM, incremental SVM, principal component analysis, incremental LDA, ICA, and hierarchical multiscale local binary pattern. Testing exploits data from different data sets: CelebrityDB, Labeled Faces in the Wild, SCface, and FERET. The face images used present variations in pose, expression, illumination, image quality, and resolution. Our experiments show the benefits of using image quality and reliability indices to enhance overall accuracy, on one side, and to provide for individualized processing of biometric probes for better decision-making purposes, on the other side. Both kinds of indices, owing to the way they are defined, can be easily integrated within different frameworks and off-the-shelf biometric applications for the following: 1) data fusion; 2) online identity management; and 3) interoperability. The results obtained by FACE witness a significant increase in accuracy when compared with the results produced by the other algorithms considered.

Image compression by B-tree triangular coding

This paper describes an algorithm for still image compression called B-tree triangular coding (BTTC). The coding scheme is based on the recursive decomposition of the image domain into right-angled triangles arranged in a binary tree. The method is attractive because of its fast encoding, O(n log n), and decoding, /spl Theta/(n), where n is the number of pixels, and because it is easy to implement and to parallelize. Experimental studies indicate that BTTC produces images of satisfactory quality from a subjective and objective point of view, One advantage of BTTC over JPEG is its shorter execution time.

Ear Recognition by means of a Rotation Invariant Descriptor

Iannarellis studies showed that ear shape can be considered a biometric identifier able to authenticate people as well as more established biometrics like face or voice, for instance. However, very few researches can be found in literature about ear recognition. In most cases techniques already working in other biometric fields, such as PCA (principal component analysis), are applied to ear. Eigen-ears provide high recognition rate only in closely controlled conditions. Indeed, even a slight amount of rotation can cause a significant drop in system performance and in unattended systems rotations occur very frequently. In this paper, we propose the use of a rotation invariant descriptor, namely GFD (generic Fourier descriptor), to extract meaningful features from ear images. This descriptor results to be quite robust to both ear rotations and illumination changes. Experimental results confirm the superiority of this approach even compared to Eigen-ears

FIRST: Fractal Indexing and Retrieval SysTem for Image Databases

We present an image indexing method and a system to perform content-based retrieval in heterogeneous image databases (IDB). The method is based upon the fractal framework of the iterated function systems (IFS) widely used for image compression. The image index is represented through a vector of numeric features, corresponding to contractive functions (CF) of the IFS framework. The construction of the index vector requires a preliminary processing of the images to select an appropriate set of indexing features (i.e. contractive functions). The latter will be successively used to fill in the vector components, computed as frequencies by which the selected contractive functions appear inside the images. In order to manipulate the index vectors efficiently we use discrete Fourier transform (DFT) to reduce their cardinalities and use a spatial access method (SAM), like R*-tree, to improve search performances. The sound theoretical framework underlying the method enabled us to formally prove some properties of the index. However, for a complete validation of the indexing method, also in terms of effectiveness and efficacy, we performed several experiments on a large collection of images from different domains, which revealed good system performances with a low percentage of false alarms and false dismissals. q 1998 Elsevier Science B.V. All rights reserved.

GANT: Gaze analysis technique for human identification

Abstract Anatomical biometric recognition is widely used in a large number of civilian and government applications, within well-tested biometric parameters. New sensors and matching algorithms have led to the deployment of soft biometrics, which may provide a fast and reliable identity finding procedure. These traits are physical or behavioral human characteristics like skin color, eye color, and gait, used by humans to recognize their peers, presenting distinctiveness and permanence to identify an individual uniquely and reliably. This paper regards a novel Gaze ANalysis Technique, namely GANT, exploiting a graph-based representation of fixation points obtained by an eye tracker during human computer interaction. The main goal is to demonstrate the conjecture that the way an individual looks at an image might be a personal distinctive feature, i.e. a soft biometric application. A novel dataset acquired through the Tobii 1750 remote eye tracker has been used to demonstrate GANT accuracy in soft biometry, in terms of Receiver Operating Characteristic Curve (ROC), Equal Error Rate (EER) and Cumulative Match Curve (CMC).

A haptic-based approach to virtual training for aerospace industry

In the last years, the industrial world has been increasingly adopting computer-aided solutions for design for maintainability and maintenance training tasks with the goal to reduce development costs and to shorten time, and to improve product and service quality. Computer-based training systems created to simulate machine assembly maintenance are normally operated by means of ordinary human-computer interfaces (keyboard, mouse, etc.), but this usually results in systems that are far from the real procedures, and therefore not effective in terms of training. In this study, we show that a better solution may come from the combination of virtual reality techniques and haptic interaction. To this regard, we present the results of a research aimed at testing and evaluating the effectiveness of the haptic feedback for first-person maintenance tasks targeted to the aerospace industry. The proposed system implements an interaction environment in which each of the main maintenance activities can be simulated by the trainee exploiting a hand-based commercial haptic device, operated by means of specific haptic-rendering techniques to provide realistic feedbacks during manipulation. A usability study is included to help assessing the potential of this approach.