Jorge Orts
ECE533 – Image Processing
Course Project: Face recognition techniques
Problem: Face recognition using computer image processing has always been
one of the most challenging problems over the past few years. Face recognition
techniques have a huge variety of applications such as personal identification or
comparison from faces in a database. The difficulty of successful face recognition
comes from the differences of a face picture taken from the same person. We can
find differences of light; eyes, mouth or nose motion; and size. Therefore, the
quality of a face recognition algorithm depends on how accurate it is; this can be
measured as a percentage of correct recognitions.
Approach: Many face recognition techniques have been proposed to solve this
problem; however, not all of them have the same level of success. This project will
try to show some of the best of these techniques explaining how they fulfill this
task. The purpose is to apply course knowledge in order to understand these highlevel techniques that might vary in the image processing that they use. Some
results of the analyzed techniques will be provided in order to make a good
comparison between them. The main techniques described will be: Face
recognition using line edge map, A shape- and texture-based enhanced Fisher
classifier for face recognition, Face recognition for smart environments, Line-based
face recognition under varying pose. All of them are deeply described in the
articles included at the references below. Although some of them take into
consideration more variation than the rest a good comparison can be made in
order to determinate the most suitable technique for each situation.
References:
L.C. Jain, “Intelligent biometric techniques in fingerprint and face recognition”. Boca Raton: CRC
Press, 1999.
Aurélio Campilho, Mohamed Kamel, “Image analysis and recognition : international conference,
ICIAR 2004, Porto, Portugal, September 29-October 1, 2004”. Berlin ; New York : Springer, c2004.
Yongsheng Gao; Leung, M.K.H., “Face recognition using line edge map”. Pattern Analysis and
Machine Intelligence, IEEE Transactions on , Volume: 24 Issue: 6 , June 2002, Page(s): 764 -779.
Chengjun Liu; Wechsler, H. , “A shape- and texture-based enhanced Fisher classifier for face
recognition”. Image Processing, IEEE Transactions on , Volume: 10 Issue: 4 , April 2001, Page(s):
598 -608.
Pentland, A.; Choudhury, T. , “Face recognition for smart environments “. Computer, Volume: 33
Issue: 2 , Feb. 2000, Page(s): 50 -55.
De Vel, O.; Aeberhard, S., “Line-based face recognition under varying pose”. Pattern Analysis and
Machine Intelligence, IEEE Transactions on , Volume: 21 Issue: 10 , Oct. 1999, Page(s): 1081 1088.