In this paper the problem of eye detection across three different bands, i.e., the visible, multispectral, and short wave infrared (SWIR), is studied in order to illustrate the advantages and limitations of multi-band eye localization. The contributions of this work are two-fold. First, a multi-band database of 30 subjects is assembled and used to illustrate the challenges associated with the problem. Second, a set of experiments is performed in order to demonstrate the possibility for multi-band eye detection. Experiments show that the eyes on face images captured under different bands can be detected with promising results. Finally, we illustrate that recognition performance in all studied bands is favorably affected by the geometric normalization of raw face images that is based on our proposed detection methodology. To the best of our knowledge this is the first time that this problem is being investigated in the open literature in the context of human eye localization across different bands.
We propose a novel and efficient methodology for the detection of human pupils using face images acquired under controlled and difficult (large pose and illumination changes) conditions in variable spectra (i.e., visible, multi-spectral, and short wave infrared (SWIR)). The methodology is based on template matching, and is composed of an offline and an online mode. During the offline mode, band-dependent eye templates are generated for each eye from the face images of a pre-selected number of subjects. Using the eye templates that are generated in the offline mode, the online pupil detection mode determines the locations of the human eyes and the pupils. A combination of texture-and template-based matching algorithms is used for this purpose. Our method achieved a significantly high detection rate, yielding an average of 96.38% pupil detection accuracy across all datasets used. Based on a comparative analysis on different databases, we concluded that: (i) a single methodological approach can be used to efficiently detect human eyes and pupils of face images (with strong pose and illumination variations) acquired in the visible and hyper-spectral bands, and (ii) the use of texture-based matching and normalized band-specific templates significantly increases detection accuracy. To the best of our knowledge, this is the first time in the open literature that the problem of multi-band pupil detection on face images in the presence of lighting and pose variations, is being investigated using a unified algorithm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.