The Editors
It was three years ago that we had our first special issue in Computer Vision Beyond the Visibel Spectrum (CVBVS) in the Machine Vision and Applications journal [1]. At that time, we expected that computer vision research would grow significantly in the nonvisible spectrum, particularly in the biometrics area. This second special issue in the Image and Vision Computing journal comes to verify our expectations. New CVBVS methods and systems in face detection, tracking, and recognition enable identification at a distance under any lighting conditions. As a result, this new technology heralds the migration of human identification screening from access control to surveillance applications. These adavances promise to revolutionize the security industry. Also, methods and systems for defense applications, which is the traditional CVBVS domain, grew more sophisticated and effective. Target detection and recognition in Synthetic Aperture Radar (SAR) imagery is at the very core of these advancements.
All the papers included in this special issue were presented in preliminary form at the IEEE Workshop in Computer Vision Beyond the Visible Spectrum, held in Kauai, Hawaii, on December 14, 2001. The selected papers were a small subset of the total number of papers presented at the Workshop and underwent two rounds of further rigorous review and updates to ensure a high quality outcome.
In the first paper Face Detection in the Near-IR Spectrum, J. Dowdall et al. introduce a new face detection method based on the fusion of two near-infrared bands. The resulting phenomenology is such that it allows reliable face detection with simple algorithmic means like integral projection. The authors realized a prototype system based