Classification of Facial Part Movement Acquired from Kinect V1 and Kinect V2 Sheng Guang Heng, Rosdiyana Samad, Mahfuzah Mustafa, Zainah Md Zain, Nor Rul Hasma Abdullah, and Dwi Pebrianti Abstract The aim of this study is to determine the motion sensor with better performance in facial part movements recognition among Kinect v1 and Kinect v2. This study has applied some classification methods such as neural network, com- plex decision tree, cubic SVM, fine Gaussian SVM, fine kNN and QDA in the dataset obtained from Kinect v1 and Kinect v2. The facial part movement is detected and extracted in 11 features and 15 classes. The chosen classifications are then applied to train and test the dataset. Kinect sensor that has the dataset with highest testing accuracy will be selected to develop an assistive facial exercise application in terms of tracking performance and detection accuracy. Keywords Kinect V1 Á Kinect V2 Á Face tracking Á Classification Á Confusion matrix Á Facial part movement 1 Introduction Recently, assistive technologies have been widely used in human life in various aspects such as vision and hearing care. Hence, devices that featuring assistive technologies must have satisfying performance in terms of detection accuracy and time response. Furthermore, assistive technologies can help in rehabilitation by restoring the ability to its original state. For example, patients with Bell’s Palsy syndrome are dif ficult to make facial expressions correctly or precisely like before. They are required to do a series of rehabilitation to get back to normal. Normally, the rehabilitation process will take a long time because of the dif ficulty of physical exercises and lacking motivation repeating the same exercises. The assistive tech- nologies help to improve the motivation for ef ficient rehabilitation. S. G. Heng (&) Á R. Samad Á M. Mustafa Á Z. M. Zain Á N. R. H. Abdullah Á D. Pebrianti Faculty of Electrical and Electronics Engineering, Universiti Malaysia Pahang, 26600 Pekan, Pahang, Malaysia e-mail: meg17001@stdmail.ump.edu.my © Springer Nature Singapore Pte Ltd. 2021 Z. Md Zain et al. (eds.), Proceedings of the 11th National Technical Seminar on Unmanned System Technology 2019, Lecture Notes in Electrical Engineering 666, https://doi.org/10.1007/978-981-15-5281-6_65 911