The development of face recognition based on lip using neural network / Halizawati Mohd Nor

Nowadays a lot of applications have been developed especially in face recognition
system. Face recognition became an interesting application in surveillance,
identification system and security system. This project is focusing on the
development of face recognition based on lip using Neural Network Technique. The
objective is to identify the persons' ID based on individual lip from different
expression of facial image. This project is divided into two phases. The first phase is
image pre-processing using MATLAB. The pre-processing is conducted by applying
all fimctions in MATLAB image processing Toolbox. Tthis project used 'imadjust'
and 'histeq' functions for Grayscale Enhancement, 'imfilter' for Linear Filtering and
'im2bw' for Image Segmentation. The second phase is NN application design and
development. Training and testing has been conducted to measuring the performance
of learning by manipulating the parameters to achieve a better performance. It
demonstrates that 60 percent of accuracy which person's lip can be recognized in the
form of normal and smile expressions.