Paper Info
Title
Distinguishing Falsification Of Human Faces From True Faces Based On Optical Flow Information
Abstract
Falsification of Human Faces using face photos has been an arising problem for face recognition and verification systems. In this paper, we propose a system to distinguish face photos from true faces by their motion models. In order to enhance the difference between the two classes, we design an enhanced optical flow method which generates a larger difference between the motion model of true faces and that of face photos. The feature vector we adopted is the dense optical flow field across a short period of time. An LDA-based training method is adopted to separate the projection of the training data into two classes, and a Bayes classifier is used to classify the testing samples. Under the specified motion of true faces and face photos, our proposed method can effectively distinguish the two classes with high verification rate. Even if the motion is arbitrary for both classes, the proposed system can also report satisfying results.
Year
DOI
Venue
2009
10.1109/ISCAS.2009.5118336
ISCAS: 2009 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-5
Keywords
Field
DocType
image classification,biometrics,bayes classifier,face detection,optical imaging,face recognition,computer science,satisfiability,vectors,optical flow,estimation,feature vector,computer vision,training data,adaptive optics,learning artificial intelligence
Training set,Computer vision,Facial recognition system,Feature vector,Pattern recognition,Computer science,Artificial intelligence,Contextual image classification,Optical imaging,Optical flow,Bayes classifier,Adaptive optics
Conference
Citations 
PageRank 
References 
0
0.34
1
Authors
5
Name
Order
Citations
PageRank
Chia-Ming Wang117812.15
Hsu-Yung Cheng224323.56
Kuo-chin Fan31369117.82
Chih-Chang Yu4328.93
Feng-Yang Hsieh561.55