Title :
Real-time face detection on reconfigurable device
Author :
Mooseop Kim ; Seungwan Han
Author_Institution :
Electron. & Telecommun. Res. Inst., Daejeon, South Korea
Abstract :
This paper presents an efficient hardware architecture for a real-time face detection system using a reconfigurable logic device. The proposed architecture is based on AdaBoost learning algorithm with Haar-like features and it aims to apply to a reconfigurable device. The proposed system was verified by the RTL functional simulation and tested the same input images on the OpenCV program for a fair verification of the functionality. The experimental results show that the processing time for a 320×240 pixel image is 42 frames per second with the 100MHz.
Keywords :
face recognition; feature extraction; learning (artificial intelligence); logic devices; object detection; reconfigurable architectures; AdaBoost learning algorithm; Haar-like features; OpenCV program; RTL functional simulation; fair functionality verification; frequency 100 MHz; hardware architecture; realtime face detection; reconfigurable logic device; register transfer level; AdaBoost; Face detection; Hardware implementation;
Conference_Titel :
ICT Convergence (ICTC), 2013 International Conference on
Conference_Location :
Jeju
DOI :
10.1109/ICTC.2013.6675463
