A multi-core architecture for face detection—Based on application specific instruction-set processor

A detection system, which could extract the face information from image or video frame, is becoming more and more important in lots of field, such as Computer vision, image processing, artificial intelligence and so on. In this paper, a multi-core architecture, based on ASIP, is proposed for Viola and Jones's algorithm. A novel scan strategy is adopted to make the data accessing more regular. Meanwhile, through multiple levels optimization of detection processing and the application-oriented ASIPs, the design is able to meet the overall demand. The architecture is prototyped on Altera Cyclone II FPGA, and the result shows that with lower resource consumption it performs real-time processing and high detection rate.

[1]  Yu Wei,et al.  FPGA implementation of AdaBoost algorithm for detection of face biometrics , 2004, IEEE International Workshop on Biomedical Circuits and Systems, 2004..

[2]  Ming Yang,et al.  AdaBoost-based face detection for embedded systems , 2010, Comput. Vis. Image Underst..

[3]  Narendra Ahuja,et al.  Detecting Faces in Images: A Survey , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[5]  Shih-Lien L. Lu,et al.  Field programmable gate array-ased haar classifier for accelerating face detection algorithm , 2010 .

[6]  Ryan Kastner,et al.  Parallelized Architecture of Multiple Classifiers for Face Detection , 2009, 2009 20th IEEE International Conference on Application-specific Systems, Architectures and Processors.

[7]  Pavel Zemcík,et al.  Real-time object detection on CUDA , 2010, Journal of Real-Time Image Processing.

[8]  Ryusuke Miyamoto,et al.  Partially Parallel Architecture for AdaBoost-Based Detection With Haar-Like Features , 2009, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  Theocharis Theocharides,et al.  A Flexible Parallel Hardware Architecture for AdaBoost-Based Real-Time Object Detection , 2011, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[10]  Henk Corporaal.  Design of transport triggered architectures , 1994, Proceedings of 4th Great Lakes Symposium on VLSI.

[11]  Grant Martin,et al.  Multi-Processor SoC-Based Design Methodologies Using Configurable and Extensible Processors , 2008, J. Signal Process. Syst..