The synthesis of realistic facial expressions has been an unexplored area for computer graphics scientists. Over the last three decades, several different construction methods have been formulated in order to obtain natural graphic results. Despite these advancements, though, current techniques still require costly resources, heavy user intervention and specific training and outcomes are still not completely realistic. This thesis, therefore, aims to achieve an automated synthesis that will produce realistic facial expressions at a low cost. This thesis, proposes a highly automated approach for achieving a realistic facial expression synthesis, which allows for enhanced performance in speed (3 minutes processing time maximum) and quality with a minimum of user intervention. It will also demonstrate a highly technical and automated method of facial feature detection, by allowing users to obtain their desired facial expression synthesis with minimal physical input. Moreover, it will describe a novel approach to the normalization of the illumination settings values between source and target images, thereby allowing the algorithm to work accurately, even in different lighting conditions. Finally, we will present the results obtained from the proposed techniques, together with our conclusions, at the end of the paper.

Microexpression detection plays a vital role in applications such as lie detection and psychological consultations. Current research is progressing in the direction of automating microexpression recognition by aiming at classifying the microexpressions in terms of FACS Action Units. Although high detection rates are being achieved, the datasets used for evaluation of these systems are highly restricted. They are limited in size - usually still pictures or extremely short videos; motion constrained; containing only a single microexpression and do not contain negative cases where microexpressions are absent. Only a few of these systems run in real time and even fewer have been tested on real life videos. This work proposes a novel method for automated spotting of facial microexpressions as a preprocessing step to existing microexpression recognition systems. By identifying and rejecting sequences that do not contain microexpressions, longer sequences can be converted into shorter, constrained, relevant sequences which comprise of only single microexpressions, which can then be passed as input to existing systems, improving their performance and efficiency. This method utilizes the small temporal extent of microexpressions for their identification. The extent is determined by the period for which strain, due to the non-rigid motion caused during facial movement, is impacted on the facial skin. The subject's face is divided into sub-regions, and facial strain is calculated for each of these regions. The strain patterns in individual regions are used to identify subtle changes which facilitate the detection of microexpressions. The strain magnitude is calculated using the central difference method over the robust and dense optical flow field of each subject's face. The computed strain is then thresholded using a variable threshold. If the duration for which the strain is above the threshold corresponds to the duration of a microexpression, detection is reported. The datasets used for algorithm evaluation are comprised of a mix of natural and enacted microexpressions. The results were promising with up to 80% true detection rate. Increased false positive spots in the Canal 9 dataset can be attributed to talking by the subjects causing fine movements in the mouth region. Performing speech detection to identify sequences where the subject is talking and excluding the mouth region during those periods could help reduce the number of false positives.