How the Number of Interest Points Affect Scene Classification

Wenjie XIE  De XU  Shuoyan LIU  Yingjun TANG  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E93-D   No.4   pp.930-933
Publication Date: 2010/04/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E93.D.930
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
Keyword: 
bag-of-words,  feature selection,  SIFT,  

Full Text: PDF(116.1KB)>>
Buy this Article




Summary: 
This paper focuses on the relationship between the number of interest points and the accuracy rate in scene classification. Here, we accept the common belief that more interest points can generate higher accuracy. But, few effort have been done in this field. In order to validate this viewpoint, in our paper, extensive experiments based on bag of words method are implemented. In particular, three different SIFT descriptors and five feature selection methods are adopted to change the number of interest points. As innovation point, we propose a novel dense SIFT descriptor named Octave Dense SIFT, which can generate more interest points and higher accuracy, and a new feature selection method called number mutual information (NMI), which has better robustness than other feature selection methods. Experimental results show that the number of interest points can aggressively affect classification accuracy.