Please use this identifier to cite or link to this item:
Title: Human face recognition using line edge information
Authors: Gao, Yong Sheng.
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
Issue Date: 2000
Abstract: The automatic recognition of human faces presents a significant challenge to the pattern recognition research community. Typically, human faces are very similar in structure with minor differences from person to person. They are actually within one class of "human face". Furthermore, pose variations, lighting condition changes and facial expressions further complicate the face recognition task as one of the difficult problems in pattern analysis. This thesis has proved the proposed novel concept, "Faces can be recognized using Line Edge Map". A compact face feature, Line Edge Map (LEM), is generated for face coding and recognition. A complete investigation on the proposed concept is conducted according to two organization schemes. The first scheme covers all three levels (low, intermediate and high) pattern recognition methodologies that make use of information from spatial domain to structural and syntactic representations. The second scheme covers all aspects on human face recognition. The investigation covers face recognition under (a) controlled/ideal condition, (b) pose variation, (c) varying lighting condition, and (d) varying facial expression. The system performances are also compared with Eigenface method, one of the best face recognition techniques, and reported experiment results of other methods. It is a very encouraging finding that the proposed face recognition technique has performed consistently superior to (or equally well as) the Eigenface method in all the comparison experiments. The results demonstrate that LEM of human faces efficiently provide sufficient information for face recognition. LEM and the proposed generic Line Segment Hausdorff Distance measure provide a new way for face coding and recognition.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Theses

Files in This Item:
File Description SizeFormat 
  Restricted Access
Main report21.88 MBAdobe PDFView/Open

Page view(s)

checked on Sep 25, 2020


checked on Sep 25, 2020

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.