FPGA implementation of decision functions
Generalized Fourier Descriptors
Curvilinear detector
Viola Jones hardware implementation
Cancer Prostate

This project is performed by Khalil Khattab, PhD student  in the Le2i, and was initiated in collaboration with Jiri Matas,  from CMP (Prague, Czech Rep.). Julien Dubois (Le2i) is now also supervising K. Khattab.


The face detection is a fundamental prerequisite step in the process of face recognition. The focus of this work is the implementation of a real time embedded face detection system while relying on high level description language such as SystemC. Recently, the boosting based object detection algorithms proposed by Viola and Jones have gained a lot of attention and are considered as the fastest accurate object detection algorithms today. However, the embedded implementation of such algorithms into hardware is still a challenge, since these algorithms are heavily based on memory access. We built a parallel implementation that exploits the parallelism and the pipelining in these algorithms. We show that, using a SystemC description model paired with a mainstream automatic synthesis tool, can lead to an efficient hardware implementation. We also display some of the tradeoffs and considerations, for this implementation to be effective. This implementation proves capable of increasing the speed of the detector as well as bringing regularity in time consuming. The design implementation is reasonably low on FPGA resource utilization.


Publications about Viola-Jones Implementation:

  • "Embedded System Study For Real Time Boosting Based Face Detection", Khalil KHATTAB, Johel MITERAN, Julien DUBOIS, Jiri MATAS, IECON 06, Paris, France, pp. 3461-3465, 2006.

Viola Jones hardware implementation