A Multi-Classifier Approach to Fingerprint Classification

Fingerprint classification is a challenging pattern recognition problem which plays a fundamental role in most of the large fingerprint-based identification systems. Due to the intrinsic class ambiguity and the difficulty of processing very low quality images (which constitute a significant proportion), automatic fingerprint classification performance is currently below operating requirements, and most of the classification work is still carried out manually or semi-automatically. This paper explores the advantages of combining the MASKS and MKL-based classifiers, which we have specifically designed for the fingerprint classification task. In particular, a combination at the ‘abstract level’ is proposed for exclusive classification, whereas a fusion at the ‘measurement level’ is introduced for continuous classification. The advantages of coupling these distinct techniques are well evident; in particular, in the case of exclusive classification, the FBI challenge, requiring a classification error ≤ 1% at 20% rejection, was met on NIST-DB14. Received: 06 November 2000, Received in revised form: 25 October 2001, Accepted: 03 January 2002     

A Markov chain model to describe fluidization of particles with time-varying properties

A one-dimensional mathematical model of particulate solids thermal treatment in a fluidized bed based on the theory of Markov chains is proposed. A feature of the model takes into account the variation of particle properties that takes place during the fluidization. This variation occurs due to thermo-physical and chemical processes that take place during particulate solids treatment in the fluidized bed. These variations affect the particle settling velocity which is the main parameter that forms the bed expansion and local velocity of flow around the particles that strongly influences the thermo-physical and chemical processes in the bed. A generalized correlation for the drag force coefficient is proposed and tested for various materials. It was necessary to have more precise calculation of the particle settling velocity in the model. The model was developed to describe the drying process in the bed. A good correlation between computed and experimental data was achieved.     

Adding security and trust to multiagent systems

Multiagent systems (MASs) are societies whose individuals are software delegatees (agents) acting on behalf of their owners or delegators (people or organizations). When deployed in an open network such as the Internet, MASs face some trust and security issues. Agents comeand go, and interact with strangers. Assumptions about security and general trustworthiness of agents and their deployers are inadequate in this context. In this paper, the design of a security infrastructure is presented applicable to MASs in general. This design addresses both security threats and trust issues. In this design, there are mechanisms for ensuring secure communication among agents and secure naming and resource location services. And two types of trusts are addressed: trust that agents will not misbehave and trust that agents are really delegatees of whom they claim to be. To establish the first type of trust, deployers of agents are made liable for the actions of their agents; to establish the second type of trust, it is proposed that agents prove that they know secrets that only their delegators know.     

Performance evaluation of fingerprint verification systems

This paper is concerned with the performance evaluation of fingerprint verification systems. After an initial classification of biometric testing initiatives, we explore both the theoretical and practical issues related to performance evaluation by presenting the outcome of the recent fingerprint verification competition (FVC2004). FVC2004 was organized by the authors of this work for the purpose of assessing the state-of-the-art in this challenging pattern recognition application and making available a new common benchmark for an unambiguous comparison of fingerprint-based biometric systems. FVC2004 is an independent, strongly supervised evaluation performed at the evaluators' site on evaluators' hardware. This allowed the test to be completely controlled and the computation times of different algorithms to be fairly compared. The experience and feedback received from previous, similar competitions (FVC2000 and FVC2002) allowed us to improve the organization and methodology of FVC2004 and to capture the attention of a significantly higher number of academic and commercial organizations (67 algorithms were submitted for FVC2004). A new, "light" competition category was included to estimate the loss of matching performance caused by imposing computational constraints. This paper discusses data collection and testing protocols, and includes a detailed analysis of the results. We introduce a simple but effective method for comparing algorithms at the score level, allowing us to isolate difficult cases (images) and to study error correlations and algorithm "fusion." The huge amount of information obtained, including a structured classification of the submitted algorithms on the basis of their features, makes it possible to better understand how current fingerprint recognition systems work and to delineate useful research directions for the future.     

Multispace KL for pattern representation and classification

This work introduces the multispace Karhunen-Loeve (MKL) as a new approach to unsupervised dimensionality reduction for pattern representation and classification. The training set is automatically partitioned into disjoint subsets, according to an optimality criterion; each subset then determines a different KL subspace which is specialized in representing a particular group of patterns. The extension of the classical KL operators and the definition of ad hoc distances allow MKL to be effectively used where KL is commonly employed. The limits of the standard KL transform are pointed out, in particular, MKL is shown to outperform KL when the data distribution is far from a multidimensional Gaussian and to better cope with large sets of patterns, which could cause a severe performance drop in KL     

A fast and accurate palmprint recognition system based on minutiae

Palmprint recognition is a challenging problem, mainly due to low quality of the pattern, large nonlinear distortion between different impressions of the same palm and large image size, which makes feature extraction and matching computationally demanding. This paper introduces a high-resolution palmprint recognition system based on minutiae. The proposed system follows the typical sequence of steps used in fingerprint recognition, but each step has been specifically designed and optimized to process large palmprint images with a good tradeoff between accuracy and speed. A sequence of robust feature extraction steps allows to reliably detect minutiae; moreover, the matching algorithm is very efficient and robust to skin distortion, being based on a local matching strategy and an efficient and compact representation of the minutiae. Experimental results show that the proposed system compares very favorably with the state of the art.     

Optimization of a Fabric Softener Formulation with an Electrochemical Sensor and Streaming Potential Measurements

An electrochemical, cationic, surfactant-selective sensor based on multiwalled carbon nanotubes (MWCNT) functionalized with a sulfate group and the cetylpyridinium ion (MWCNT–OSO₃⁻CP⁺) as a sensing material was used for optimization of the formulation of a fabric softener. Potentiometric titrations were performed and response measurements were obtained using four cationic surfactants (CS) of technical grade and four CS of analytical grade. The slope closest to Nernstian was obtained for di-(tallow carboxyethyl) hydroxyethyl methylammonium methosulfate (MAS) (59.5 ± 1.1 mV/decade of activity in water and 57.5 ± 1.3 mV/decade of activity in CaCl₂). When using CS as analytes in potentiometric titrations, the best accuracy (99.8%) was obtained when using MAS; therefore, it was chosen as the CS for the fabric softener formulation. Due to the better properties of fabric softeners with silicone in their formulations, four silicones at several concentration levels were used as potential additives. Based on the stability and viscosity of the system, the diquaternary polydimethylsiloxane (DPS) (w = 0.19%) was chosen for the fabric softener formulation. The pH did not significantly influence the potential when in the range of 3–8 or the recovery of potentiometric titrations when in the range of 3–7. The application profile of the CS was assessed through streaming potential measurements of reference fabrics in an electrokinetic analyzer. The obtained electrokinetic parameters indicated on lag in adsorption of model fabric softener (MFS) based on MAS (w = 9%), with the addition of silicone DPS (MFS 3), on cotton and polyester fabrics, but advantage in stability when compared with other MFS investigated.     

Effect of the mold temperature on the electrical properties of carbon-black-loaded polystyrene/SB block copolymer blends

The electrical resistivities of a carbon-black-filled styrene–butadiene block copolymer (SB) and their blends with polystyrene were measured as a function of carbon content for specimens compression-molded at 200 and 250°C. The insulator–conductor point transition was greatly influenced by the mold temperature. This behavior associated to the scanning electronic microscopy investigations suggests the presence of some amount of the filler at the interface. A strong interaction between the filler and the polymer was also observed. The formation of bound rubber and a coherent rubber–filler gel depend on the molding conditions and the carbon black content in the composites. © 1998 John Wiley & Sons, Inc. J Appl Polym Sci 69: 825–833, 1998