Detection of facial changes for hospital ICU patients using neural network

This paper presents an integrated system for detecting facial changes of patient in a hospital in Intensive Care Unit (ICU). The facial changes are most widely represented by eyes movements. The proposed system uses color images and it consists of three modules. The first module implements skin detection to detect the face. The second module constructs eye maps that are responsible for changes in eye regions. The third module extracts the features of eyes by processing the image and measuring certain demensions of eyes regions. Finally a neural network classifier used to classify the motion of eyes either it open, half open or close. From 300 samples of face images, it is found that the maximum classification accuracy of 93.33% was obtained for the proposed features and classification technique.