A robust eyelash detection based on iris focus assessment

  • Authors:

  • Byung Jun Kang;Kang Ryoung Park

  • Affiliations:

  • Department of Computer Science, Sangmyung University, Biometrics Engineering Research Center, 7 Hongji-Dong, Chongro-Gu, Seoul 110-743, Republic of Korea;Division of Digital Media Technology, Sangmyung University, Biometrics Engineering Research Center, 7 Hongji-Dong, Chongro-Gu, Seoul 110-743, Republic of Korea

  • Venue:
  • Pattern Recognition Letters
  • Year:
  • 2007

Quantified Score

Hi-index 0.10

Visualization

Abstract

For accurate iris recognition, it is essential to detect eyelash regions and remove them for iris code generation, since eyelashes act as noise factors in the iris recognition. In addition, eyelash positions can be changed for enrollment and recognition and this may cause FR (false rejection). To overcome these problems, we propose a new method for detecting eyelashes in this paper. This work shows three advantages over previous works. First, because eyelash detection was performed based on focus assessment, its performance was not affected by image blurring. Second, the new focus assessment method is appropriate for iris images. Third, the detected eyelash regions were not used for iris code generation and therefore iris recognition accuracy was greatly enhanced. Experimental results showed that the eyelash detection error was about 0.96% when using the CASIA DB and iris recognition accuracy with eyelash detection was enhanced more than 0.86% of EER when compared to the EER obtained without eyelash detection.