DocumentCode :
2300333
Title :
Real-Time Face-Detection Engine for Robustness to Variable Illumination and Rotated Faces
Author :
Choi, Jongho ; Han, Dongil ; Yoo, Seong Joon
Author_Institution :
Dept. of Comput. Eng., Sejong Univ., Seoul, South Korea
fYear :
2011
fDate :
23-25 May 2011
Firstpage :
53
Lastpage :
58
Abstract :
In this paper, we proposes a novel hardware architecture and FPGA implementation method of high performance real-time face-detection engine for robustness to variable illumination and rotation. The proposed face detection algorithm improved its performance by using MCT (Modified Census Transform), rotation transformation and AdaBoost learning algorithm. For implementation, we used a QVGA class camera, LCD display, and Virtex5 LX330 FPGA made by Xilinx Corporation. The verification results showed that it is possible to detect at least 32 faces in a wide variety of sizes at a maximum speed of 43 frames per second in real time. This finding can be applied to artificial intelligence robots for human recognition, conventional security systems for identity certification, and cutting-edge digital cameras using image processing techniques.
Keywords :
face recognition; field programmable gate arrays; learning (artificial intelligence); real-time systems; AdaBoost learning algorithm; LCD display; QVGA class camera; Virtex5 LX330 FPGA; artificial intelligence robots; conventional security system; cutting-edge digital cameras; face detection algorithm; hardware architecture; human recognition; image processing technique; modified census transform; real-time face detection engine; robustness; rotated faces; variable illumination; Face detection; Field programmable gate arrays; Hardware; Lighting; Pixel; Real time systems; Reliability; AdaBoost; FPGA Hardware implementation; Face-detection; MCT; Real-Time; Rotation trans-formation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computers, Networks, Systems and Industrial Engineering (CNSI), 2011 First ACIS/JNU International Conference on
Conference_Location :
Jeju Island
Print_ISBN :
978-1-4577-0180-1
Type :
conf
DOI :
10.1109/CNSI.2011.67
Filename :
5954277
Link To Document :
بازگشت