Loading...

Facial Expression Recognition using Kinect Sensor and Alice Humanoid Robot Real-time Facial Expression Imitation

Siamy, Alireza | 2016

485 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 50585 (58)
  4. University: Sharif University of Technology, International Campus, Kish Island
  5. Department: Science and Engineering
  6. Advisor(s): Meghdari, Ali; Bagheri Shouraki, Saeed
  7. Abstract:
  8. In the recent years, development of new technologies in the field of cognitive science has made a huge effect on the people social life style. Facial expression imitation with applications in the design of human robot interaction (HRI) systems is an active area of research. In this study, we propose an approach using a humanoid social robot, The Alice, for real-time imitation of human facial expression. The facial keypoints of the user are extracted by using the Kinect sensor together with manipulated SDK 2.0 codes. Kinect output array are collected for each expression, then the training dataset is created with these output arrays. An accurate Artificial neural network (ANN), which has a balance between number of layers and accuracy, is found for classifying the facial expressions like happiness, sadness, fear, anger, disgusted and surprised. Then, C# and Java Netbeans are connected for transferring data between Kinect sensor and Alice to complete the imitation process. Alice, the humanoid receives the classification outputs and imitate the recognized gesture through the decision-making algorithm. Simulations and experimental results showed a satisfying reaction time and appropriate accuracy in gesture recognition and imitation by humanoid, the Alice
  9. Keywords:
  10. Artificial Neural Network ; Social Robotics ; Humanoid Robot ; Facial Expression Recognition ; Kinect Sensor

 Digital Object List

 Bookmark

No TOC