Verma, Monu
(Vision Intelligence Lab at Malaviya National Institute of Technlogy, Jaipur, Rajasthan, India)
,
Vipparthi, Santosh Kumar
(Vision Intelligence Lab at Malaviya National Institute of Technlogy, Jaipur, Rajasthan, India)
,
Singh, Girdhari
(Vision Intelligence Lab at Malaviya National Institute of Technlogy, Jaipur, Rajasthan, India)
In this letter, we propose a novel lightweight network HiNet: hybrid inherited feature learning network and its variants: HiNet -ReLU, HiNet -Concat, Large Scale HiNet, 2 stack HiNet and 4 stack HiNet for facial expression recognition. In HiNet, we introduce the hybrid feature (HyFeat) block that fo...
In this letter, we propose a novel lightweight network HiNet: hybrid inherited feature learning network and its variants: HiNet -ReLU, HiNet -Concat, Large Scale HiNet, 2 stack HiNet and 4 stack HiNet for facial expression recognition. In HiNet, we introduce the hybrid feature (HyFeat) block that follows a two - level hybrid structure to capture the local contextual information of expressive regions. In level -1, HyFeat block uses two different scaled conv filters to preserve the domain knowledge features for expressive regions. Similarly, level -2 captures the enriched features through refine edge variation of the receptive fields by employing another two filters. Thus, HyFeat block allows network to perpetuate prominent features of facial expressions and enhances the discriminability of the HiNet. Moreover, performance of the proposed HiNet is evaluated by conducting person dependent (PD) and person independent (PI) experiments on four datasets: CK+, MUG, AFEW and OULU respectively. Experimental results on CK+ dataset prove the adequacy of the proposed HiNet over its variants in terms of accuracy and computational complexity. Furthermore, the proposed HiNet uses approximately 5 /16, 1/138, 1/144 and 1/31 times less parameters as compared to the MobileNet, VGG -16, VGG - 19 and ResNet, respectively. The experimental and computational complexity analysis demonstrate the significant performance improvement of the proposed method over the state-of-the-art techniques in terms of recognition rate.
In this letter, we propose a novel lightweight network HiNet: hybrid inherited feature learning network and its variants: HiNet -ReLU, HiNet -Concat, Large Scale HiNet, 2 stack HiNet and 4 stack HiNet for facial expression recognition. In HiNet, we introduce the hybrid feature (HyFeat) block that follows a two - level hybrid structure to capture the local contextual information of expressive regions. In level -1, HyFeat block uses two different scaled conv filters to preserve the domain knowledge features for expressive regions. Similarly, level -2 captures the enriched features through refine edge variation of the receptive fields by employing another two filters. Thus, HyFeat block allows network to perpetuate prominent features of facial expressions and enhances the discriminability of the HiNet. Moreover, performance of the proposed HiNet is evaluated by conducting person dependent (PD) and person independent (PI) experiments on four datasets: CK+, MUG, AFEW and OULU respectively. Experimental results on CK+ dataset prove the adequacy of the proposed HiNet over its variants in terms of accuracy and computational complexity. Furthermore, the proposed HiNet uses approximately 5 /16, 1/138, 1/144 and 1/31 times less parameters as compared to the MobileNet, VGG -16, VGG - 19 and ResNet, respectively. The experimental and computational complexity analysis demonstrate the significant performance improvement of the proposed method over the state-of-the-art techniques in terms of recognition rate.
참고문헌 (17)
arXiv preprint arXiv 1904 01870 EXPERTNet exigent features preservative network for facial expression recognition verma 2019
Proc 9th Forum Media Technol Comparing shallow versus deep neural network architectures for automatic music genre classification schindler 2016 1734 17
arXiv preprint arXiv 1412 6806 Striving for simplicity: The all convolutional net springenberg 2014
10.1109/CVPRW.2010.5543262
Proc 11th IEEE Int Conf Image Anal Multimed Interactive Workshop The MUG facial expression database aifanti 2010 1
10.1145/3136755.3143004
Zhao, G., Huang, X., Taini, M., Li, S.Z., Pietikainen, M..
Facial expression recognition from near-infrared videos.
Image and vision computing,
vol.29,
no.9,
607-619.
Byungyong Ryu, Ramirez Rivera, Adin, Jaemyun Kim, Oksam Chae.
Local Directional Ternary Pattern for Facial Expression Recognition.
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society,
vol.26,
no.12,
6006-6018.
Proc Int Conf Learn Representations Very deep convolutional networks for large-scale image recognition simonyan 2015
Shan, C., Gong, S., McOwan, P.W..
Facial expression recognition based on Local Binary Patterns: A comprehensive study.
Image and vision computing,
vol.27,
no.6,
803-816.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.