Reliable interest point detection under large illumination variations

Gevrekci M., GÜNTÜRK B. K.

2008 IEEE International Conference on Image Processing, ICIP 2008, San Diego, CA, United States Of America, 12 - 15 October 2008, pp.869-872, (Full Text) identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/icip.2008.4711893
  • City: San Diego, CA
  • Country: United States Of America
  • Page Numbers: pp.869-872
  • Keywords: Feature extraction, image registration
  • Istanbul Medipol University Affiliated: Yes

Abstract

Most interest point detection algorithms are highly sensitive to illumination variations. This paper presents a method to detect interest points robustly under large photometric changes. The method, which we call contrast invariant feature transform (CIFT), determines salient interest points in an image by calculating and processing contrast signatures. A contrast signature shows the response of an interest point detector with respect to a set of contrast stretching functions. The method is generic and can be used with most interest point detectors. In this paper, we demonstrate how CIFT improves the repeatability rate of the Harris corner detector. © 2008 IEEE.