The basic aim of a biometric identification system is\ud to discriminate automatically between subjects in a reliable and\ud dependable way, according to a specific-target application. Multimodal\ud biometric identification systems aim to fuse two or more\ud physical or behavioral traits to provide optimal False Acceptance\ud Rate (FAR) and False Rejection Rate (FRR), thus improving system\ud accuracy and dependability. In this paper, an innovative multimodal\ud biometric identification system based on iris and fingerprint\ud traits is proposed. The paper is a state-of-the-art advancement\ud of multibiometrics, offering an innovative perspective on features\ud fusion. In greater detail, a frequency-based approach results in\ud a homogeneous biometric vector, integrating iris and fingerprint\ud data. Successively, a hamming-distance-based matching algorithm\ud deals with the unified homogenous biometric vector. The proposed\ud multimodal system achieves interesting results with several commonly\ud used databases. For example, we have obtained an interesting\ud working point with FAR = 0% and FRR = 5.71% using\ud the entire fingerprint verification competition (FVC) 2002 DB2B\ud database and a randomly extracted same-size subset of the BATH\ud database. At the same time, considering the BATH database and\ud the FVC2002 DB2A database, we have obtained a further interesting\ud working point with FAR = 0% and FRR = 7.28% ÷ 9.7%

No abstract

No abstract

Automatic Road Sign Recognition Systems are aimed at detection and recognition of one or more road signs from real-world color images. In this research, road signs are detected and extracted from real world scenes on the basis of their color and shape features. A dynamic region growing technique is adopted to enhance color segmentation results obtained in the HSV color space. The technique is based on a dynamic threshold that reduces the effect of hue instability in real scenes due to external brightness variation. Classification is then performed on extracted candidate regions using Multi-Layer Perceptron neural networks. The obtained results show good detection and recognition rates of the entire system with real outdoor scenes, using several light conditions. Finally, the implementation of the neural layer on the Georgia Institute of Technology SIMD Pixel Processor is outlined.

No abstract