Search

In this paper we propose a nonlinear correlation filter using the kernel trick, which can be used for redundant class-dependence feature analysis (CFA) to perform robust face recognition. This approach is evaluated using the Face Recognition Grand Challenge (FRGC) data set. The FRGC contains a large corpus of data and a set of challenging problems. The dataset is divided into training and validation partitions, with the standard still-image training partition consisting of 12,800 images, and the validation partition consisting of 16,028 controlled still images, 8,014 uncontrolled stills, and 4,007 3D scans. We have tested the proposed linear correlation filter and nonlinear correlation filter based CFA method on this FRGC2.0 data. The results show that the CFA method outperforms the baseline algorithm and the newly proposed kernel-based non-linear correlation filters perform even better than linear CFA filters. [ABSTRACT FROM AUTHOR]

In this paper we explore performing robust face verification using Advanced Correlation Filters on Bijective-Mapping preprocessed face images. We show that using the proposed Bijective-Mapping preprocessing method we can increase verification performance (at 0.1% FAR) significantly in our experiments using the Face Recognition Grand Challenge (FRGC) database collected by the University of Notre Dame consisting of 152 subjects. This recognition experiment is challenging as the results reported on these experiments utilize only a single gallery image from each subject during the training phase and the probe images are captured in different time-lapsed sessions which vary mostly in pose and facial expression. [ABSTRACT FROM AUTHOR]