Ivan Fratric

A biometric identification system based on eigenpalm and eigenfinger features

This paper presents a multimodal biometric identification system based on the features of the human hand. We describe a new biometric approach to personal identification using eigenfinger and eigenpalm features, with fusion applied at the matching-score level. The identification process can be divided into the following phases: capturing the image; preprocessing; extracting and normalizing the palm and strip-like finger subimages; extracting the eigenpalm and eigenfinger features based on the K-L transform; matching and fusion; and, finally, a decision based on the (k, l)-NN classifier and thresholding. The system was tested on a database of 237 people (1,820 hand images). The experimental results showed the effectiveness of the system in terms of the recognition rate (100 percent), the equal error rate (EER = 0.58 percent), and the total error rate (TER = 0.72 percent).

A biometric verification system based on the fusion of palmprint and face features

This paper presents a bimodal biometric verification system for physical access control based on the features of the palmprint and the face. The system tries to improve the verification results of unimodal biometric systems based on palmprint or facial features by integrating them using fusion at the matching-score level. The verification process consists of image acquisition using a scanner and a camera, palmprint recognition based on the principal lines, face recognition with eigenfaces, fusion of the unimodal results at the matching-score level, and finally, a decision based on thresholding. The experimental results show that fusion improves the equal error rate by 0.74% and the minimum total error rate by 1.72%.

Experimental Evaluation of Matching-Score Normalization Techniques on Different Multimodal Biometric Systems

The goal of this work is the experimental evaluation of matching-score normalization techniques for the following three multimodal biometric systems: a verification system based on the fusion of face and palmprint principal line features, an identification system based on eigenfingers and finger-geometry, and an identification system based on eigenpalm and eigenfinger features. The following normalization techniques are tested: Bayes-based normalization and several heuristic techniques (min-max, z-score, median-MAD, double-sigmoid, tanh, and piecewise-linear). The results of evaluation are represented by means of system performance (expressed by ROC, EER and minTER) and F-statistics

Local binary LDA for face recognition

Extracting discriminatory features from images is a crucial task for biometric recognition. For this reason, we have developed a new method for the extraction of features from images that we have called local binary linear discriminant analysis (LBLDA), which combines the good characteristics of both LDA and local feature extraction methods. We demonstrated that binarizing the feature vector obtained by LBLDA significantly improves the recognition accuracy. The experimental results demonstrate the feasibility of the method for face recognition as follows: on XM2VTS face image database, a recognition accuracy of 96.44% is obtained using LBLDA, which is an improvement over LDA (94.41%). LBLDA can also outperform LDA in terms of computation speed.

Colour-based palmprint verification - An experiment

This paper presents biometric verification experiments based on palm colour information. Feasibility of colour components from several different colour models (RGB, normalized rgb, HSL, YUV, CIE XYZ, CIE LAB and Hunter LAB) for the purpose of biometric recognition was determined. According to the recognition rate, feature vectors based on normalized r and normalized b colour components are selected. Fusion at the matching score level is used to improve verification accuracy. Experimental results suggest colour can be used as a highly discriminatory characteristic, which in combination with other palm characteristics (principal lines, palm geometry, appearance-based features) enables the design of a biometric system for medium/high security applications.

Real-Time Model-Based Hand Localization for Unsupervised Palmar Image Acquisition

Unsupervised and touchless image acquisition are two problems that have recently emerged in biometric systems based on hand features. We have developed a real-time model-based hand localization system for palmar image acquisition and ROI extraction. The system operates on video sequences and produces a set of palmprint regions of interest (ROIs) for each sequence. Hand candidates are first located using Viola-Jones approach and then the best candidate is selected using model-fitting approach. Experimental results demonstrate the feasibility of the system for unsupervised palmar image acquisition in terms of speed and localization accuracy.

A multimodal hand-based verification system with an aliveness-detection module

This paper presents a multimodal biometrie verification system based on the following hand features: palmprint, four digitprints and four fingerprints. The features are obtained using the Karhunen-Loève transform based approach, and information fusion at the matching-score level was applied. We experimented with different resolutions of the regions of interest, different numbers of features and several normalization and fusion techniques at the matching-score level. To increase the reliability of the system to spoof attacks we included an aliveness-detection module based on thermal images of the hand dor sa. The verification performance when using a system configuration with optimum parameters, i.e., resolution, number of features, normalization and fusion technique, showed an equal error rate (EER) of 0.0020%, which makes the system appropriate for the implementation of high-security biometric systems.RésuméDans ce papier est présenté un système de vérification biométrique multimodal qui repose sur les éléments de la main suivants: empreinte palmaire, empreintes de quatre doigts et quatre empreintes digitales. Les caractéristiques sont obtenues grâce à une approche reposant sur la transformée de Karhunen-Loève et une fusion d’information au niveau des degrés de pertinence (ORES) est effectuée. Les expériences reflètent différentes résolutions des régions d’intérêt, un nombre différent de caractéristiques et plusieurs techniques de normalisation et de fusion au niveau des scores. Pour augmenter la résistance du système aux imitations nous avons inclus un module qui permet de détecter si la main est vivante en utilisant des images thermiques du dos de la main. Les performances en vérification lorsqu On utilise un système optimal en terme de résolution, nombre de caractéristiques extraites, techniques de normalisation et fusion présentent un taux d’égale erreur (EER) de 0.0020%, ce qui en fait un système approprié à l’implementation de systèmes biométriques de haute sécurité.