A Self-Adaptive Architecture and Its Application to Robust Face Identification

  • Authors:
  • Paul Robertson;Robert Laddaga

  • Affiliations:
  • -;-

  • Venue:
  • PRICAI '02 Proceedings of the 7th Pacific Rim International Conference on Artificial Intelligence: Trends in Artificial Intelligence
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

Conventional approaches to most image understanding problems suffer from fragility when applied to natural environments. This is especially true of face recognition programs. The GRAVA architecture provides support for self awareness and situational awareness that allows robust recognition to occur. We describe the architecture and explain how it achieves robustness. GRAVA is a reflective architecture that supports self-adaptation that has been successfully applied to a number of visual interpretation domains. This paper describes the protocols and the main interpreter for GRAVA, as well as the application of the architecture to face recognition.