A Massively Parallel Face Recognition System. (21st December 2006)

• Record Type: Journal Article
• Authors: Lahdenoja, Olli; Laiho, Mika; Maunu, Janne; Paasio, Ari
• Other Names: Garn Heinrich Academic Editor.
• Is Part Of: EURASIP journal on embedded systems. Volume 2007(2007)
• Publication Date: 2006-12-21
• Subjects: Embedded computer systems -- Periodicals; Systèmes enfouis (Informatique); Embedded computer systems; Periodicals; Electronic journals; 006.22
• DOI: 10.1155/2007/72316
• Languages: English
• ISSNs: 1687-3955

Abstract

Abstract : We present methods for processing the LBPs (local binary patterns) with a massively parallel hardware, especially with CNN-UM (cellular nonlinear network-universal machine). In particular, we present a framework for implementing a massively parallel face recognition system, including a dedicated highly accurate algorithm suitable for various types of platforms (e.g., CNN-UM and digital FPGA). We study in detail a dedicated mixed-mode implementation of the algorithm and estimate its implementation cost in the view of its performance and accuracy restrictions.