Face Emotion recognition system

2.0 Literature Review

Face detection is a computer technology that will identify human faces in arbitrary images and human faces basically have the same basic configure appearance such as two eyes above a nose and mouth. After the computers have successfully on detecting the faces, there are more researches have done in face processing include emotion recognition.

2.1 Face Acquisition

In this process, user’s faces are acquired in order to extract out the facial features from cluttered background. In Robust Real-time Object Detection (P.Viola ,2002), the authors used AdaBoost algorithm to detect the frontal view of faces rapidly. The system able to detect the face from background quickly and compute the face features in a short time. However, the frontal view of faces cannot always guarantee appear in the environment, so some of the researchers have considered used side view plus frontal view to detect the faces. Besides that, this algorithm will fail to detect those faces with more than 10 degree rotation.

In Expert System for Automatic Analysis of Facial Expressions (M.Pantic , 2000), the author used dual-view faces which are front face and a 90 degree right faces in his system by using two cameras mounted on user’s head. Besides that, in article Decoding of Profile Versus Full-Face Expressions of Affect (Kleck, R. & Mendolia, 1990), the authors used three side views such as full-face, right and left in his system. They found out that full view and right were accurate in detecting positive expressions while left view was accurate in detecting negative expressions compared to right view.

From these articles, it has proved that the system can recognize the face not only from front view but also left and right view. In order to im...

... middle of paper ...

... will combine both techniques which are AdaBoost algorithm and colour detection to detect the human face.

At feature extraction part, authors proposed geometric and appearance method to extract the facial feature points out and some authors also stated that by using both combination approaches, it will increase the accuracy compared to the system which only used one approach. From here, it already gave the idea to the project system that it has no harm in applying two approaches together.

At last, in face emotion recognition part, the articles shows the strength and weakness between HMM and neural network. This part shows that by applying those approaches which can support various combinations of AUs can generate better result. So, it already gave a big hint to this project which is to avoid using those techniques which are unable to support multiple combinations.