Image Quality Evaluation for Video Iris Recognition in the Visible Spectrum

Abstract

Video-based eye image acquisition in the visible spectrum for iris recognition has taken great importance in the current context of the extensive use of video surveillance cameras and mobile devices. This modality can provide more information from the video capture of the eye region, but it is essential that the images captured have a quality that allows an effective recognition process. In this work, an approach for video iris recognition in the visible spectrum is presented. It is based on a scheme whose novelty is in the possibility of evaluating the quality of the eye image simultaneously with the process of video capturing. A measure of image quality that takes into account the elements defined in the ISO / IEC 19794-6 2005 standard and its combination with automatic detection methods is proposed. The experiments developed on three international databases and own video database demonstrate the relevance of the proposal. DOI: 10.29011/ 2577-2260. 00044