Annalisa Franco

Fingerprint verification competition 2006

The interest in fingerprint-based biometric systems has constantly grown in recent years and considerable efforts have been focused by both academia and industry on the development of new algorithms for fingerprint recognition. Raffaele Cappelli, Matteo Ferrara, Annalisa Franco and Davide Maltoni of the Biometric System Laboratory at the University of Bologna explain the findings of the Fingerprint Verification Competition 2006.

Indoor localization in a hospital environment using Random Forest classifiers

A system able to localize patients in a hospital environment is proposed.The system relies on RFID technology and a combination of Random Forest classifiers.The system has been deployed in the emergency unit of a large Italian hospital.Accuracy, precision, complexity, robustness and scalability have been evaluated.Patients localization is correctly performed in 98% of cases. This paper proposes a new indoor localization system, based on RFID technology and a hierarchical structure of classifiers. This system has been specifically designed to work in unfriendly scenarios, where transmissions could be disturbed by other electronic devices or shielded walls. The infrastructure has been deployed and evaluated in the emergency unit of a large Italian hospital (48 rooms covering about 4000 m 2 ) to detect the room where lost or forgotten patients lie. Extensive experiments show the potential of such technology for indoor localization applications in terms of accuracy, precision, complexity, robustness and scalability. In 98% of cases the system localizes the correct room (83%) or one of its adjacency (15%).

The magic passport

Once upon a time there was a criminal; he was reading his e-mail when a banner caught his attention: low cost flights for the destination of his dreams! He had already started to book the trip when suddenly realized that, being wanted by the police, he could not use his passport without being arrested. What to do? He could not miss that opportunity, so he called a good friend and they started to think for a possible solution. Do you want to know if they succeeded? Read the rest of the paper and find it out.

Incremental template updating for face recognition in home environments

The extreme variability of faces in smart environment applications, due to continuous changes in terms of pose, illumination and subject appearance (hairstyle, make-up, etc.), requires the relevant mode of variations of the subjects faces to be encoded in the templates and to be continuously updated based on new inputs. This work proposes a new video-based template updating approach suitable for home environments where the image acquisition process is totally unconstrained but a large amount of face data is available for continuous learning. A small set of labeled images is initially used to create the templates and the updating is then totally unsupervised. Although the method is here presented in conjunction with a subspace-based face recognition approach, it can be easily adapted to deal with different kinds of face representations. A thorough performance evaluation is carried out to show the efficacy and reliability of the proposed technique.

An enhanced subspace method for face recognition

In this paper we introduce a new face recognition approach based on the representation of each individual by several lower dimensional subspaces obtained by an unsupervised clustering of different poses: this provides a higher robustness to face variations than traditional subspace approaches. A set of subspaces is created for each individual, starting from a feature vector extracted through a bank of Gabor filters and non-linear Fisher transform. Extensive experiments carried out on the FERET database of faces, which is the most common benchmark in this area, prove the advantages of the proposed approach when compared with other well-known techniques. These results confirm the robustness of our approach against appearance variations due to expression, illumination and pose changes or to aging effects.

2D face recognition based on supervised subspace learning from 3D models

One of the main challenges in face recognition is represented by pose and illumination variations that drastically affect the recognition performance, as confirmed by the results of recent face recognition large-scale evaluations. This paper presents a new technique for face recognition, based on the joint use of 3D models and 2D images, specifically conceived to be robust with respect to pose and illumination changes. A 3D model of each user is exploited in the training stage (i.e. enrollment) to generate a large number of 2D images representing virtual views of the face with varying pose and illumination. Such images are then used to learn in a supervised manner a set of subspaces constituting the users template. Recognition occurs by matching 2D images with the templates and no 3D information (neither images nor face models) is required. The experiments carried out confirm the efficacy of the proposed technique.

Eigenspace merging for model updating

The Karhunen-Loeve transform (KLT) is an optimal method for dimensionality reduction, widely applied in image compression, reconstruction and retrieval, pattern recognition and classification. The basic idea consists in evaluating, starting from a set of representative examples, a reduced space, which takes into account the structure of the data distribution as much as possible, and representing each element in such an uncorrelated space. Unfortunately, KLT has the drawback of requiring a periodical recomputation in presence of a dynamic dataset. This work presents a novel efficient approach to merge multiple eigenspaces, which provides an incremental method to compute an eigenspace model by successively adding new sets of elements. Experimental results show that the merged model grants performances as good as a one obtained by a batch procedure.

Fusion of classifiers for illumination robust face recognition

In this paper the problem of face recognition under variable illumination conditions is considered. Most of the works in the literature exhibit good performance under strictly controlled acquisition conditions, but the performance drastically drop when changes in pose and illumination occur, so that recently a number of approaches have been proposed to deal with such variability. The aim of this work is twofold: first a survey on the existing techniques proposed to obtain an illumination robust recognition is given, and then a new method, based on the fusion of different classifiers, is proposed. The experiments carried out on different face databases confirm the effectiveness of the approach.

On the Effects of Image Alterations on Face Recognition Accuracy

Face recognition in controlled environments is nowadays considered rather reliable, and if face is acquired in proper conditions, a good accuracy level can be achieved by state-of-the-art systems. However, we show that, even under these desirable conditions, some intentional or unintentional face image alterations can significantly affect the recognition performance. In particular, in scenarios where the user template is created from printed photographs rather than from images acquired live during enrollment (e.g., identity documents ), digital image alterations can severely affect the recognition results. In this chapter, we analyze both the effects of such alterations on face recognition algorithms and the human capabilities to deal with altered images.

A new approach for relevance feedback through positive and negative samples

Relevance feedback has recently emerged as a solution to the problem of providing an effective response to a similarity query in an images retrieval system based on low-level information such as color, texture and shape features. This work describes an approach for learning an optimal similarity metric based on the analysis of relevant and non-relevant information given by the user during the feedback process. A positive and a negative space are determined as an approximation of the examples given by the user. The relevant region is represented by a KL subspace of positive examples and is iteratively updated at each feedback iteration. The nonrelevant region is modeled by a MKL space, which better characterizes the variety of negative examples, which very likely could belong to more than one class. The search process is, then, formulated as a classification problem, based on the calculation of the minimal distance to the relevant or non-relevant region.