DocumentCode
1538195
Title
Graph-based method for face identification from a single 2D line drawing
Author
Liu, Jianzhuang ; Lee, Yong Tsui
Author_Institution
Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, China
Volume
23
Issue
10
fYear
2001
fDate
10/1/2001 12:00:00 AM
Firstpage
1106
Lastpage
1119
Abstract
The faces in a 2D fine drawing of an object provide important information for the reconstruction of its 3D geometry. In this paper, a graph-based optimization method is proposed for identifying the faces is a line drawing. The face identification is formulated as a maximum weight clique problem. This formulation is proven to be equivalent to the formulation proposed by Shpitalni and Upson (1996). The advantage of our formulation is that it enables one to develop a much faster algorithm to find the faces in a drawing. The significant improvement in speed is derived from two algorithms provided: the depth-first graph search for quickly generating possible faces from a drawing; and the maximum weight clique finding for obtaining the optimal face configurations of the drawing. The experimental results shown that our algorithm generates the same results of face identification as Shpitalni and Lipson´s method, but is much faster when dealing with objects of more than 20 faces
Keywords
graph theory; image reconstruction; object recognition; optimisation; search problems; stereo image processing; 2D line drawing; 3D object reconstruction; depth-first search; graph algorithms; line drawing interpretation; maximum weight clique; Application software; Computational geometry; Computer Society; Computer vision; Design automation; Face detection; Humans; Information geometry; Object recognition; Optimization methods;
fLanguage
English
Journal_Title
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher
ieee
ISSN
0162-8828
Type
jour
DOI
10.1109/34.954601
Filename
954601
Link To Document