Video-based person recognition using fovea intensity comparison code

Аннотация

This article proposes a feature extraction method for automatic person recognition in video. The method proposed by Viola and Jones (Viola, P. and Jones, M., 2001. Rapid object detection using a boosted cascade of simple features. In: IEEE international conference on computer vision and pattern recognition (CVPR 2001), Kauai Marriott, Hawaii, Vol. 1, 511–518) is used to detect the face region. Face region is processed in YCbCr colour space to determine the locations of the eyes. The centre of the mouth is determined relative to the locations of the eyes. Facial and mouth features are extracted using multiscale morphological erosion and dilation operations, respectively. The facial features are extracted relative to the locations of the eyes, and mouth features are extracted relative to the locations of the eyes and mouth. Fovea intensity comparison code and exclusive-OR operation for matching are used to recognise a person in video sequences. Projected fovea intensity comparison code (PFICC) and Euclidean distance for matching are also used to recognise a person in video sequences. The performance of the system using PFICC is evaluated in real time in the laboratory environment, and the system achieves a recognition rate (RR) of 99.0% and an equal error rate (EER) of about 0.84% for 50 subjects. The performance of the system is also evaluated for the eXtended Multi Modal Verification for Teleservices and Security (XM2VTS) database, and the system achieves an RR of 100% and an EER of about 0.23%.