Paper Info
Title
The distinctiveness, detectability, and robustness of local image features
Abstract
We introduce a new method that characterizes typical local image features (e.g., SIFT [9], phase feature [3]) in terms of their distinctiveness, detectability, and robustness to image deformations. This is useful for the task of classifying local image features in terms of those three properties. The importance of this classification process for a recognition system using local features is as follows: a) reduce the recognition time due to a smaller number of features present in the test image and in the database of model features; b) improve the recognition accuracy since only the most useful features for the recognition task are kept in the model database; and c) increase the scalability of the recognition system given the smaller number of features per model. A discriminant classifier is trained to select well behaved feature points. A regression network is then trained to provide quantitative models of the detection distributions for each selected feature point. It is important to note that both the classifier and the regression network use image data alone as their input. Experimental results show that the use of these trained networks not only improves the performance of our recognition system, but it also significantly reduces the computation time for the recognition process.
Year
DOI
Venue
2005
10.1109/CVPR.2005.340
Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference
Keywords
Field
DocType
feature extraction,image classification,learning (artificial intelligence),regression analysis,visual databases,discriminant classifier,image deformation,local image feature classification,model database,recognition system,regression network
Computer vision,Scale-invariant feature transform,Feature detection (computer vision),Pattern recognition,Feature (computer vision),Computer science,Feature extraction,Haar-like features,Feature (machine learning),Artificial intelligence,Contextual image classification,Standard test image
Conference
Volume
ISSN
ISBN
2
1063-6919
0-7695-2372-2
Citations 
PageRank 
References 
16
0.92
14
Authors
2
Name
Order
Citations
PageRank
Gustavo Carneiro1115369.37
Jepson, A.D.240281.91