Design of rotation, illumination, and texture-invariant composite filters from range images using simulated annealing for face recognition

Shizhuo Yin, David Duarte, Purwadi Purwosumarto

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, the design of composite filters from range images using the simulated annealing technique for robust face recognition is discussed. Due to the use of range images as the training set for the synthesis of composite filters, besides the out-of-plane rotation invariance, the designed composite filters are also inherently insensitive to the variation in the illumination and texture of the object. In addition, since the correlation operation can be done in the 2-D domain, the required processing time for 3-D range data is also substantially reduced. The experimental results show that the maximum responses of the antitarget are always less than the minimum response of the target, even in the case where multiple faces are involved, which demonstrates the feasibility of the proposed technique.

Original languageEnglish (US)
Pages (from-to)151-155
Number of pages5
JournalMicrowave and Optical Technology Letters
Volume23
Issue number3
DOIs
StatePublished - Nov 5 1999

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Condensed Matter Physics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Design of rotation, illumination, and texture-invariant composite filters from range images using simulated annealing for face recognition'. Together they form a unique fingerprint.

Cite this