Embedded implementation of real-time skin detection system

Skin detection is an important step in the field of hand gesture and face recognition. With the aim of overcoming the weak points that existing software solutions show in real-time applications, an FPGA-based embedded system is proposed. Firstly, we propose the skin segmentation algorithm using color pixel classification and discuss the thresholds of the skin classifier. Then, the hardware architecture of the FPGA platform is described. Finally, Experiment results are presented in terms of classification performance, processing rate and hardware resources. In addition, the proposed system can also perform other tasks and FPGA implementation renders it more useful for real-time applications.