Using Gabor filter in 3D convolutional neural networks for human action recognition

Jiakun Li (1) , Tian Wang (1) , Yi Zhou (2) , Ziyu Wang , Hichem Snoussi (3)

1 BUAA - Beihang University
2 Dalian Maritime University
3 LM2S - Laboratoire Modélisation et Sûreté des Systèmes

Human action recognition is an important topic in the field of computer vision. We use Gabor filter in 3D CNNs models in recognizing action. Convolutional neural networks (CNNs) are a type of deep learning models, which is an efficient recognition model and has a unique superiority in image processing. Three dimension convolutional neural networks can well analyze action from video data. Gabor filter is a special convolution kernel. Its performance in feature extraction is outstanding. We test out model by KTH dataset and achieve a well result.

Domains: Signal and Image processing

Jiakun Li, Tian Wang, Yi Zhou, Ziyu Wang, Hichem Snoussi. Using Gabor filter in 3D convolutional neural networks for human action recognition. 2017 36th Chinese Control Conference (CCC), Jul 2017, Dalian, China. pp.11139-11144, ⟨10.23919/ChiCC.2017.8029134⟩. ⟨hal-03320777⟩