Computer recognition of facial expressions

In this diploma I try one of the more popular methods for modelling facial images and the extracted data's dimension is later on reduced. I can manipulate the shape and texture with the images reduced data. From these changed images the LGBP algorithm creates histograms, that represents the input of one of the most popular methods for machine learning. In the first part I define emotions and the process of recognizing facial expressions. I mention the factors that can effect on the result of the recognition and some tools for recognizing facial features and facial expressions. In the second part the steps for preprocessing data are mentioned and relevant algorithms for understanding the process of recognition with LGBP and AAM are described - with the steps for implementation in Matlab. The last part consists of classification results of the processed data and the meaning behind them. In the end part I explain my findings and propose some optimization techniques for this application