Loading...

Pain Level Estimation Using Facial Expression

Mohebbi Kalkhoran, Hamed | 2015

724 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 47365 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Fatemizadeh, Emad
  7. Abstract:
  8. In this study pain level estimation using facial expression is investigated. To do this, there are two approaches, one approach is sequence level pain estimation and the other one is frame level pain estimation. In sequence level, after feature extraction from all frames of sequence, each sequence is represented by a fixed length feature vector, this feature vector is constructed by concatenating min, max and mean of frame features of that specific sequence, then KLPP is applied in order to reduce feature vector dimension and in the end a linear regression is implemented to predict the pain labels of the sequence. In the frame level, two approaches are introduced, the first one is based on the facial landmark distances and displacements, and the other one is based on estimation theory by tracking approach. Linear kalman filter and non-linear particle filter is used to predict the intensity of facial action units. In order to compensate head movements in the database a new method is introduced to model observation noise in kalman filter and particle filter. The results in sequence-level pain estimation shows an ICC of 0.699 and AUC of 88.43 percent which has about 8 percent improvement in comparison with the primary base work and about 0.5 percent improvement in comparison with the state of the art. In frame level pain estimation the acquired ICC is 0.725 wich has noticble improvement with respect to the latest work with ICC of 0.64
  9. Keywords:
  10. Particle Filter ; Kalman Filters ; Linear Regression ; Facial Action Units ; Pain Level Estimation ; Kernel Locality Preserving Projection (KLPP) ; Facial Landmarks

 Digital Object List

 Bookmark

No TOC