Paper Info
Title
A Robust Keypoints Matching Strategy for SIFT: An Application to Face Recognition
Abstract
Recently, the Scale Invariant Feature Transform (SIFT) proposed by Lowe has emerged as a cut edge methodology in general object recognition as well as for other machine vision applications. However, SIFT method has not shown successful results in face recognition problem because of its original matching strategy which does not consider the location of local keypoints. This paper proposes a novel keypoints matching strategy for face recognition. The proposed matching strategy can avoid mis-matching of local keypoints by using regular grid of face image and can give robustness to various transformations by using keypoint voting strategy. By performing computational experiment on the AR face data set, we confirmed the proposed matching strategy gives better performance than the conventional methods. Especially, the proposed method can give robust and best performance for facial images with occlusions.
Year
DOI
Venue
2009
10.1007/978-3-642-10677-4_82
ICONIP (1)
Keywords
Field
DocType
matching strategy.,face image,scale invariant feature transform sift,face recognition,general object recognition,proposed matching strategy,original matching strategy,keypoint voting strategy,face recognition problem,ar face data,local keypoints,object recognition,computer experiment,scale invariant feature transform,machine vision
Scale-invariant feature transform,Machine vision,Regular grid,Computer science,Robustness (computer science),Artificial intelligence,Computer vision,Facial recognition system,3D single-object recognition,Pattern recognition,Three-dimensional face recognition,Machine learning,Cognitive neuroscience of visual object recognition
Conference
Volume
ISSN
Citations 
5863
0302-9743
3
PageRank 
References 
Authors
0.42
6
2
Name
Order
Citations
PageRank
Minkook Cho162.55
Hyeyoung Park219432.70