Title :
Face-recognition hardware implementation based on SOPC
Author :
He, Cheng ; Sui, Chunchun ; Chen, Ling ; Xixin, Cao
Author_Institution :
Sch. of Software & Microelectron., Peking Univ., Beijing, China
Abstract :
As the rapid development of computer science and pattern recognition, visual technology is widely applied in industry and daily life. This paper provides a face-recognition hardware implementation based on SOPC, in which custom peripherals, manufacture-provided IP and NiosII processor are connected by Avalon Memory-Mapped Interface. Real time data is transported through Avalon Streaming Interface between custom peripherals without the intervening of CPU. Two kinds of hardware acceleration are used to improve performance, C2H and Custom instructions, which can accelerate the speed of face-recognition up to about 50 and 90 times, respectively.
Keywords :
computer interfaces; face recognition; programmable circuits; system-on-chip; Avalon memory mapped interface; Avalon streaming interface; C2H; NiosII processor; SOPC; computer science; custom instructions; custom peripherals; face recognition hardware; hardware acceleration; manufacture provided IP processor; pattern recognition; Acceleration; Application software; Application specific integrated circuits; Embedded system; Face detection; Face recognition; Hardware; Image recognition; Intelligent transportation systems; Pattern recognition; Face-recognition; Hardware acceleration; NiosII; SOPC;
Conference_Titel :
Advanced Communication Technology (ICACT), 2010 The 12th International Conference on
Conference_Location :
Phoenix Park
Print_ISBN :
978-1-4244-5427-3