Khawaja Ubaid Ur RehmanMuhammad Maaz AslamMuhammad Hassan RazaAyesha Farooq2016-03-292016-03-292015https://escholar.umt.edu.pk/handle/123456789/1637Supervisor: Syed Farooq AliMost accidents occur due to drowsiness while driving, avoiding road signs and due to driver's distraction. Driver's distraction depends on various factors which includes talking with passengers while driving, avoiding road signs, mood disorder, nervousness, anger, over-excitement, anxiety, loud music, illness and fatigue that may result in the distraction of a driver. This paper introduces novel approaches that compute various features using the facial points especially features computed using motion vectors and interpolation. These facial points are detected by Active Shape Model (ASM) and Boosted Regression with Markov Networks (BoRMaN). The features of different frames are trained and tested on Neural Networks (NN) to decide about driver's distraction. These approaches are also scale invariant. The result shows that the approach 4 using novel idea of motion vectors and interpolation techniques outperforms all other approaches.BS ThesisDriver's DistractionDetection TechniquesNeural NetworkThesis