Face identification implementation in a standalone embedded system

In this paper is described an embedded system for face identification. The system, running on FPGA, is built around LEON3 processor and consists of several IP (Intellectual Property) modules designed as AMBA bus peripherals. The face detection is accelerated with the help of a hardware module while the face recognition is entirely executed in software. The face detection hardware accelerator module is reconfigurable and can share its internal resources (memory, multiplier, integer square root unit) with the LEON3 processor. The system has been designed on the criteria of resources optimization, low power consumption and improved operation speed.