STMicro face-recognition processor includes FPGA core
STMicro face-recognition processor includes FPGA core
By Anthony Cataldo, EE Times
May 3, 2002 (1:30 p.m. EST)
URL: http://www.eetimes.com/story/OEG20020502S0038
SAN JOSE, Calif. Looking to design a face-recognition processor that wouldn't get bogged down by heavy-duty algorithms, researchers at STMicroelectronics developed a unique chip architecture that combines a configurable processor from Tensilica Inc. and an embedded FPGA core.
The image processor uses Tensilica's Xtensa processor running at 200 MHz and special instructions to cut through the tougher face-recognition algorithms used to process 250-line images. Using C code extensions tailored for the Xtensa processor, the chip can execute four of these algorithms in 1.26 seconds, versus 10.7 seconds using only C code. Using a database of 20 faces, the face-recognition algorithm itself took 68 percent of the total processing time, STMicro said.
Linked to the Xtensa processor through a special bus is an FPGA block, which serves to generate the C code extensions. "In this way the FPGA acts as a [Tensilica instruction extension] conta iner but it's also used as a programmable master/slave and for general purpose I/O," said STMicro researcher Francesco Lertora.
Designed as a research vehicle, the 5.5 x 5.5-mm test chip was built using 0.18-micron design rules.
More Embedded Processor Forum coverage.
Related Semiconductor IP
- Multi-channel Ultra Ethernet TSS Transform Engine
- Configurable CPU tailored precisely to your needs
- Ultra high-performance low-power ADC
- HiFi iQ DSP
- CXL 4 Verification IP
Related News
- Intel FPGA Technology Supports NEC in Face Recognition Technology
- Synopsys' New ARC IoT Development Kit Accelerates Software Development for Sensor Fusion, Voice Recognition and Face Detection Designs
- PathPartner to Showcase Innovations in Face Recognition and Automotive Vision at TU-Automotive, Detroit 2018
- Creonic Introduces NCR Processor IP Core for DVB-S2X/DVB-RCS2 Satellite Communication
Latest News
- ASICLAND Partners with Daegu Metropolitan City to Advance Demonstration and Commercialization of Korean AI Semiconductors
- SEALSQ and Lattice Collaborate to Deliver Unified TPM-FPGA Architecture for Post-Quantum Security
- SEMIFIVE Partners with Niobium to Develop FHE Accelerator, Driving U.S. Market Expansion
- TASKING Delivers Advanced Worst-Case Timing Coupling Analysis and Mitigation for Multicore Designs
- Efficient Computer Raises $60 Million to Advance Energy-Efficient General-Purpose Processors for AI