Predicting Soft Biometric Attributes from 30 Pixels: A Case Study in NIR Ocular Images

In this work, we investigate the possibility of extracting soft biometric attributes, viz., gender, race and eye color, from down-sampled near-infrared ocular images. In particular, we evaluate the possibility of deducing gender, race and eye color from ocular images as small as 56 pixels. Our preliminary analysis yields the surprising result that gender, race and eye color cues are still available in such low-resolution near-infrared images. This research bolsters the previously made assertion in the literature that certain soft biometric attributes can be deduced from poor quality biometric data.