TY - GEN
T1 - Hyper-parameter determination of CNN classifier for head pose estimation of three dimensional degraded face images
AU - Kuswana, Randy Pangestu
AU - Faqih, Akhmad
AU - Kusumoputro, Benyamin
PY - 2019/9
Y1 - 2019/9
N2 - This paper presents the evaluation of parameters for head pose estimation using Convolutional Neural Network (CNN) towards the degraded images. Head pose estimation is one of the important factor for three dimensional face recognition system. Due to its superiority, Convolutional Neural Network (CNN) has been used as a head pose estimator, however, its performance is significantly dropped when the input face images is exposed to noises. As the CNN comes with different choices of pooling layer, two different experimental setups are created with similar architecture and training condition but using a different type of pooling layer. After learning, the CNN are tested with another five different testing datasets to monitor the effects of various particular noises, such as: Gaussian noise, Salt-Pepper, and Speckle. Result of the experiments shows that the usage of max pooling significantly lowering the performance of the CNN, compared to the system with average pooling layer.
AB - This paper presents the evaluation of parameters for head pose estimation using Convolutional Neural Network (CNN) towards the degraded images. Head pose estimation is one of the important factor for three dimensional face recognition system. Due to its superiority, Convolutional Neural Network (CNN) has been used as a head pose estimator, however, its performance is significantly dropped when the input face images is exposed to noises. As the CNN comes with different choices of pooling layer, two different experimental setups are created with similar architecture and training condition but using a different type of pooling layer. After learning, the CNN are tested with another five different testing datasets to monitor the effects of various particular noises, such as: Gaussian noise, Salt-Pepper, and Speckle. Result of the experiments shows that the usage of max pooling significantly lowering the performance of the CNN, compared to the system with average pooling layer.
KW - Convolutional neural network
KW - Face recognition head pose estimation
KW - Hyperparameter evaluation
KW - Image noises
UR - http://www.scopus.com/inward/record.url?scp=85081052134&partnerID=8YFLogxK
U2 - 10.1109/ICAITI48442.2019.8982142
DO - 10.1109/ICAITI48442.2019.8982142
M3 - Conference contribution
T3 - Proceedings of ICAITI 2019 - 2nd International Conference on Applied Information Technology and Innovation: Exploring the Future Technology of Applied Information Technology and Innovation
SP - 99
EP - 104
BT - Proceedings of ICAITI 2019 - 2nd International Conference on Applied Information Technology and Innovation
A2 - Humaira, Humaira
A2 - Hidayat, Rahmat
A2 - Alanda, Alde
A2 - Sonatha, Yance
A2 - Rahmayuni, Indri
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2nd International Conference on Applied Information Technology and Innovation, ICAITI 2019
Y2 - 21 September 2019 through 22 September 2019
ER -