A compact discriminative representation for efficient image-set classification with application to biometric recognition

We present a simple yet compact and discriminative representation for image sets which can efficiently be used for image-set based object classification. For each image-set we compute a global covariance matrix which captures correlated variations in all image-set dimensions. Without loss of information, we compact the covariance matrix into a lower triangular matrix by using Cholesky decomposition. While preserving discrimination capability of the representation, we obtain further compression by applying Multiple Discriminant Analysis. As a result, we are able to represent image sets containing N samples each of dimensionality d by a single vector whose dimensionality is ≪ N d. We apply the proposed representation to various biometric applications such as image-set based face recognition and person identification using image-sets of periocular regions. To show that our representation is generic, we also report results for image-set based object categorization. We observe improved accuracy and significant speedup over the current state-of-the-art techniques on standard datasets.