Introduction to the Special Issue on the Segmentation of Visible Wavelength Iris Images Captured At-a-distance and On-the-move
Image and Vision Computing Vol. 28, Nº 2, pp. 213 - 214, February, 2010.
ISSN (print): 0262-8856
Journal Impact Factor: 1,496 (in 2008)
Digital Object Identifier: 10.1016/j.imavis.2009.09.004
Deployed iris recognition systems are mainly based on Daugman’s pioneering approach, and have proven their effectiveness in relatively constrained scenarios: operating in the near infra-red spectrum (NIR, 700-900 nm), at close acquisition distances and with stop-and-stare interfaces. However, the human iris supports contactless data acquisition, and it can — at least theoretically — be imaged covertly. The feasibility of covert iris recognition receives increasing attention and is of particular interest for forensic and security purposes. In this scope, one possibility is the use of visible wavelength light (VW) to perform image acquisition, although the use of this type of light can severely degrade the quality of the captured data. This is mainly due to the optical properties of the two molecules that constitute the pigment of the human iris: brown-black Eumelanin (over 90%) and yellow-reddish Pheomelanin. Eumelanin has most of its radiative fluorescence under VW, which enables the capturing of a much higher level of detail, but also of many more noisy artifacts, including specular and diffuse reflections and shadows. Also, the spectral reflectance of the sclera is significantly higher in the VW than in the NIR and the spectral radiance of the iris in respect to the levels of its pigmentation varies much more significantly in the VW than in the NIR. Furthermore, traditional template- and boundary-based iris segmentation approaches will probably fail, due to difficulties in detecting edges or in fitting rigid shapes. All these reasons justify the need of specialized segmentation strategies and were the major motivations behind the NICE.I contest (http://nice1.di.ubi.pt) that gave birth to this issue of the Image and Vision Computing Journal.