TY - GEN
T1 - Parallel computing of WaveCluster algorithm for face recognition application
AU - Anggraini, Erina Letivina
AU - Suciati, Nanik
AU - Suadi, Wahyu
PY - 2013
Y1 - 2013
N2 - There have been widely applied many research related to face recognition system. The system is commonly used for video surveillance, human and computer interaction, robot navigation, and etc. Along with the utilization of the system, it leads to the need for a faster system response, such as robot navigation or application for public safety. A number of classification algorithms have been applied to face recognition system, but it still has a problem in terms of computing time. In this system, computing time of the classification or feature extraction is an important thing for further concern. Classification algorithm that is suitable for very large databases and efficient in time complexity is WaveCluster. WaveCluster based on wavelet transform able to analyze function at different resolution. To enhance system ability as a real-time system, WaveCluster will be present to be parallel process and implemented on GPU using CUDA. CUDA is a parallel computing architecture that can manage high-performance parallel computing on GPU with large memory bandwidth. The parallelization of WaveCluster algorithm on GPU using CUDA is expected to speed-up the process computing time compared to serial process on CPU. In addition, the system is intended to improve level of accuracy in recognition process of facial images
AB - There have been widely applied many research related to face recognition system. The system is commonly used for video surveillance, human and computer interaction, robot navigation, and etc. Along with the utilization of the system, it leads to the need for a faster system response, such as robot navigation or application for public safety. A number of classification algorithms have been applied to face recognition system, but it still has a problem in terms of computing time. In this system, computing time of the classification or feature extraction is an important thing for further concern. Classification algorithm that is suitable for very large databases and efficient in time complexity is WaveCluster. WaveCluster based on wavelet transform able to analyze function at different resolution. To enhance system ability as a real-time system, WaveCluster will be present to be parallel process and implemented on GPU using CUDA. CUDA is a parallel computing architecture that can manage high-performance parallel computing on GPU with large memory bandwidth. The parallelization of WaveCluster algorithm on GPU using CUDA is expected to speed-up the process computing time compared to serial process on CPU. In addition, the system is intended to improve level of accuracy in recognition process of facial images
KW - CUDA
KW - GPU
KW - face recognition
KW - parallel computing
KW - wavecluster algorithm
UR - http://www.scopus.com/inward/record.url?scp=84890261651&partnerID=8YFLogxK
U2 - 10.1109/QiR.2013.6632536
DO - 10.1109/QiR.2013.6632536
M3 - Conference contribution
AN - SCOPUS:84890261651
SN - 9781467357852
T3 - 2013 International Conference on Quality in Research, QiR 2013 - In Conjunction with ICCS 2013: The 2nd International Conference on Civic Space
SP - 56
EP - 59
BT - 2013 International Conference on Quality in Research, QiR 2013 - In Conjunction with ICCS 2013
T2 - 2013 13th International Conference on Quality in Research, QiR 2013 - In Conjunction with the 2nd International Conference on Civic Space, ICCS 2013
Y2 - 25 June 2013 through 28 June 2013
ER -