Visible-wavelength iris/periocular imaging and recognition surveillance environments*,**

https://doi.org/10.1016/j.imavis.2016.03.015Get rights and content

Abstract

Visual surveillance cameras have been massively deployed in public urban environments over the recent years, as a crime prevention and law enforcement solution. This fact raised the interest in developing automata to infer useful information from such crowded scenes (from abnormal behavior detection to human identification). In order to cover wide outdoor areas, one interesting possibility is to combine wide-angle and pan–tilt–zoom (PTZ) cameras in a master–slave configuration. The use of fish-eye lenses allows the master camera to maximize the coverage area while the PTZ acts as a foveal sensor, providing high-resolution images of the interest regions. This paper addresses the feasibility of using this type of data acquisition paradigm for imaging iris/periocular data with enough discriminating power to be used for biometric recognition purposes.

Section snippets

Biometrics in surveillance environments

Recent attacks in crowded urban environments reduced the perception of safety in modern societies, while the citizens' tolerance to reasonable risks has been also decreasing. There are now growing needs of assuring the safety of people, particularly in places/events that concentrate large crowds, which are naturally perceived as those with the highest risk (due to e.g., 2001 New York 9/11, 2004 Madrid train bombing, 2013 Boston marathon and 2015 Paris events). To counterbalance this fear,

Related work

In order to consider an image with acceptable quality, the iris recognition standards recommend a resolution of at least 100  pixels across the iris diameter (ISO/IEC 2004) and an in-focus image. Also, sufficient near infrared (NIR) illumination should be ensured (more than 2 mW/cm2) without harming human health (less than 10 mW/cm2 according to the international safety standard IEC-60852-1). The space volume in front of the image acquisition system where these constraints met is usually referred

Challenges

Most of the current iris recognition systems require that the iris is illuminated in the NIR wavelength band. Although this wavelength has the major advantage (with respect to the visible band) of avoiding corneal reflections from the surrounding light, the use of NIR illuminators highly restricts the workability of iris recognition in less constrained scenarios: the irradiance of the illuminators decreases quadratically as the stand-off distance increases, implying the use of extremely

Conclusions

Developing automata able to perform biometric recognition in crowded scenes and without explicitly requiring any active human effort in the data acquisition process is an ambition that dates back—at least—to 1949, as a result of the widely famous George Orwell's Big Brother character. Even though such type of machine raises evident concerns from the ethical/privacy protection perspectives, it is also obvious that it will constitute a valuable law enforcement/security tool. Among several

References (13)

  • S. Yoon et al.

    Non-intrusive iris image capturing system using light stripe projection and pan–tilt–zoom camera

  • D. Barret

    One surveillance camera for every 11 people in Britain, says CCTV survey

    (2014)
  • J.C. Neves et al.

    Acquiring High-resolution face images in outdoor environments: a master–slave calibration algorithm

  • N. Kariotoglou et al.

    A stochastic reachability framework for autonomous surveillance with pan–tilt–zoom cameras

  • J.C. Neves et al.

    Dynamic camera scheduling for visual surveillance in crowded scenes using Markov random fields

  • J.R. Matey et al.

    Iris on the move: acquisition of images for iris recognition in less constrained environments

    Proc. IEEE

    (2006)
There are more references available in the full text version of this article.

Cited by (0)

*

This paper has been recommended for acceptance by Sinisa Todorovic, PhD.

**

This work was supported by FCT: Fundação Ciência e Tecnologia project UID/EEA/50008/2013.

View full text