Paper Info
Title
CSIFT: A SIFT Descriptor with Color Invariant Characteristics
Abstract
SIFT has been proven to be the most robust local invariant feature descriptor. SIFT is designed mainly for gray images. However, color provides valuable information in object description and matching tasks. Many objects can be misclassified if their color contents are ignored. This paper addresses this problem and proposes a novel colored local invariant feature descriptor. Instead of using the gray space to represent the input image, the proposed approach builds the SIFT descriptors in a color invariant space. The built Colored SIFT (CSIFT) is more robust than the conventional SIFT with respect to color and photometrical variations. The evaluation results support the potential of the proposed approach.
Year
DOI
Venue
2006
10.1109/CVPR.2006.95
Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference
Keywords
Field
DocType
color invariant space,gray space,gray image,robust local invariant feature,sift descriptors,color invariant characteristics,conventional sift,colored sift,sift descriptor,color content,local invariant feature descriptor,feature extraction,colored noise,photometry,histograms,robustness,image processing,image retrieval,computer vision,lighting
Histogram,Computer vision,Scale-invariant feature transform,GLOH,Pattern recognition,Computer science,Image processing,Image retrieval,Feature extraction,Artificial intelligence,Principal curvature-based region detector,Invariant (mathematics)
Conference
Volume
ISSN
ISBN
2
1063-6919
0-7695-2597-0
Citations 
PageRank 
References 
94
3.77
13
Authors
2
Name
Order
Citations
PageRank
Alaa E. Abdel-hakim11229.75
Aly A. Farag22147172.03