15 May 2014 Automatic face recognition in HDR imaging
Author Affiliations +
Abstract
The gaining popularity of the new High Dynamic Range (HDR) imaging systems is raising new privacy issues caused by the methods used for visualization. HDR images require tone mapping methods for an appropriate visualization on conventional and non-expensive LDR displays. These visualization methods might result in completely different visualization raising several issues on privacy intrusion. In fact, some visualization methods result in a perceptual recognition of the individuals, while others do not even show any identity. Although perceptual recognition might be possible, a natural question that can rise is how computer based recognition will perform using tone mapping generated images? In this paper, a study where automatic face recognition using sparse representation is tested with images that result from common tone mapping operators applied to HDR images. Its ability for the face identity recognition is described. Furthermore, typical LDR images are used for the face recognition training.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Manuela Pereira, Juan-Carlos Moreno, Hugo Proença, António M. G. Pinheiro, "Automatic face recognition in HDR imaging", Proc. SPIE 9138, Optics, Photonics, and Digital Technologies for Multimedia Applications III, 913804 (15 May 2014); doi: 10.1117/12.2054539; https://doi.org/10.1117/12.2054539
PROCEEDINGS
10 PAGES


SHARE
Back to Top