On Emerging Biometric Technologies

Many body parts, personal characteristics and imaging methods have been suggested and used for biometrics systems: fingers, hands, feet, faces, eyes, ears, teeth, veins, voices, signatures, typing styles and gaits. Literature contains a wide range of techniques occupying a large number of implemented algorithms regarding biometrics. In this paper we will introduce the latest improvements on biometric systems. A distinct dissociation separates them to intrusive and non-intrusive according to the level of nuisance that each system sets off. 1. NON INTRUSIVE SYSTEMS The amount of non-intrusive systems so far is not so large. Most of the developed techniques require the imminent participation of the person that is to be recognized. Although that voluntary presence seems to agree more with the idea of protection of the personal data, intrusive methods are not always the requisite ones. The latest achievements on non-intrusive biometrics present knew technologies that promise to change the way of thinking in this direction. Thermogram, smile identification, lip recognition and hyperspectral analysis seem to be the most important and promising techniques. 1.1 Thermogram Scientists have found that a unique heat distribution pattern can be obtained in human face. This pattern can be seen by taking pictures using infrared cameras. The different densities of bone, skin, fat and blood vessels all contribute to an individual’s personal “heat signature”. Conventional video cameras sense reflect light so that image values are a product of both intrinsic skin reflectivity and external incident illumination, thus obfuscating the intrinsic reflectivity of skin. Thermal emission from skin, on the other hand, is an intrinsic measurement that can be isolated from external illumination. Nine different comparative parameters are used excluding the nose and ears, which are prone to wide variations in temperature. Once a picture of a face is taken, its thermal image can be matched with accuracy against a database of pre-recorded thermographs. This work is funded by the integrated project BioSec IST-2002001766 (Biometric Security, http://www.biosec.org), under Information Society Technologies (IST) priority of the 6 Framework Programme of the European Community. A study in [1] examines the invariance of Long-Wave Infrared (LWIR) imagery with respect to different illumination conditions from the viewpoint of performance comparisons of two well known face recognition algorithms applied to LWIR and visible imagery. A rigorous data collection protocol is developed that formalize face recognition analysis for computer vision in the thermal IR. One of the obvious advantages of thermal imagery is the ability to operate in complete darkness which makes it ideal for covert surveillance. However, it has other limitations including that it is opaque to glass [2]. 1.2 Smile Recognition Another promising method for person recognition is suggested in [3]. A high speed camera with a strong zoom lens allows smile maps to be produced. This map is claimed to be unique for each person. This new method compares images of a person, taken fractions of a second apart, while they are in the smiling process. The system probes the characteristic pattern of muscles beneath the skin of the face. The way the skin around the mouth is moved between shots is analysed by tracking the change position and direction of tiny wrinkles in the skin. The data is used to produce an image of the face overlaid with tiny arrows that indicate how different areas of skin move during a smile. This movement is controlled by the pattern of muscles under the skin and is not affected by the size of the smile or the presence of make-up. The system has been successfully tested so far on a very small database consisted of 4 lab members smiling samples. The system is currently tested on a larger group of 30 smiling faces but it is obviously too early to evaluate its robustness. 1.3 Lip Recognition Another study concerning human recognition is described in [4]. A lip recognition method that uses shape similarity when vowels are uttered is proposed. In this method, a mathematical morphology analysis is applied using three different structuring elements. The proposed structuring elements are the square and vertical and horizontal line and they are used for deriving a pattern spectrum. The shape vector is compared with the reference vector to recognize an individual from its lip shape. Experimental results show that the shape vector contains information capable to perform recognition by lip shape. In particular eight Japanese lips could be classified with 100.0% accuracy. Of course the result is fictitious and authors make that clear. They note that the system is not sophisticated yet and