|本期目录/Table of Contents|

[1]郭乐新,金泰松,李玲玲.基于融合SIFT特征和二次聚类视觉词典生成的场景分类方法[J].厦门大学学报(自然科学版),2013,52(2):196.[doi:10.6043/j.issn.0438-0479.2013.02.011]
 GUO Le-xin,JIN Tai-song*,LI Ling-ling.Scene Classification Based on Integrated Scale-invariant Feature Transform (SIFT) Feature and Visual Dictionary Using Twice-clustering Method[J].Journal of Xiamen University(Natural Science),2013,52(2):196.[doi:10.6043/j.issn.0438-0479.2013.02.011]
点击复制

基于融合SIFT特征和二次聚类视觉词典生成的场景分类方法(PDF)
分享到:

《厦门大学学报(自然科学版)》[ISSN:0438-0479/CN:35-1070/N]

卷:
52卷
期数:
2013年第2期
页码:
196
栏目:
研究论文
出版日期:
2013-05-01

文章信息/Info

Title:
Scene Classification Based on Integrated Scale-invariant Feature Transform (SIFT) Feature and Visual Dictionary Using Twice-clustering Method
作者:
郭乐新金泰松李玲玲
1.厦门大学信息科学与技术学院,福建厦门361005;2.郑州航空工业管理学院计算机科学与应用系,河南郑州450015
Author(s):
GUO Le-xin1JIN Tai-song1*LI Ling-ling2
1.School of Information Science and Engineering,Xiamen University,Xiamen 361005,China;2.Department of Computer Science and Application,Zhengzhou Institute of Aeronautical Industry Management,Zhengzhou 450015,China
关键词:
场景分类SIFT特征视觉词典二次聚类
Keywords:
scene classificationscale-invariant feature transform featurevisual dictionarytwice-clustering
分类号:
TP 391
DOI:
10.6043/j.issn.0438-0479.2013.02.011
文献标志码:
-
摘要:
在传统SIFT(scale-invariant feature transform)特征检测算子基础上,增加部分伪极值点和非极值点作为特征点,提出融合SIFT特征检测算子.该算子能够提取图像中更多特征点,并使特征点在图像上分布均匀;然后在生成视觉词典前,对每幅图像的特征单独进行聚类,使视觉单词包含更多的场景信息,并缩短视觉词典的生成时间;最后使用PLSA(probabilistic latent semantic analysis)主题生成模型实现场景分类.在标准图像集上进行的对比实验表明:该方法的分类性能有一定提高,并且对多个不同场景的表现较为均稳.
Abstract:
A new approach to scene classification is proposed based on integrated scale-invariant feature transform (SIFT) feature and visual dictionary using twice-clustering method.Firstly,the proposed integrated SIFT feature operator adds some pseudo-extreme points and non-extreme points to points of interest based on traditional SIFT method,and it can use the more feature points and make the feature points distribution more uniform in the image;Secondly,the features in every image are clustered before the visual dictionary is constructed,and it can make the visual word represents the more scene information and greatly reduce the time of constructing visual dictionary.Finally,the probabilistic latent semantic analysis (PLSA) model is used for training and testing.The test on the standard image dataset shows that the proposed approach has the better classification results,and deal with the different scene categories very well.

参考文献/References:


[1]Gokalp D,Aksoy S.Scene classification using bag-of-regions representations[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Minneapolis,USA:IEEE,2007:1-8.
[2]Gu G H,Zhao Y,Zhu Z F.Integrated image representation based natural scene classification[J].Expert Systems With Applications,2011,38(9):11273-11279.
[3]Bosch A,Zisserman A,Muoz X.Scene classification using a hybrid generative/discriminative approach[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(4):712-727.
[4]Rasiwasia N,Vasconcelos N.Scene classification with low-dimensional semantic spaces and weak supervision[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Alaska,USA:IEEE,2008:1-6.
[5]Qin J Z,Yung N C.Scene categorization via contextual visual words[J].Pattern Recognition,2010,43(5):1874-1888.
[6]Liu Y,Rong J,Sukthankar R,et al.Unifying discriminative visual codebook generation with classifier training for object category recognition[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Alaska,USA:IEEE,2008:7-8.
[7]Jiang Y G,Ngo C W,Yang J.Towards optimal bag-of-features for object categorization and semantic video retrieval[C]∥ACM International Conference on Image and Video Retrieval.New York,USA:ACM,2007:494-501.
[8]Jurie F,Triggs B.Creating efficient codebooks for visual recognition[C]∥Tenth IEEE International Conference on Computer Vision.[s.l.]:IEEE,2005:604-610.
[9]Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[10]Li F F,Perona P.A bayesian hierarchical model for learning natural scene categories[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Diego,USA:IEEE,2005:524-531.
[11]Bosch A,Zisserman A,Munoz A.Scene classification via PLSA[C]∥European Conference on Computer Vision.Graz,Austria:ECCV,2006:517-530.

备注/Memo

备注/Memo:
收稿日期:2012-08-24
基金项目:国家自然科学基金项目(41171341); 教育部新世纪优秀人才支持计划项目(NCET-09-0126);教育部博士点基金项目(20110121110020); 国防基础科研项目;航空科学基金项目(20125168001);福建省自然科学基金项目(2011J01365);河南省科技创新人才杰出青年项目(114100510006);郑州市科技局科技计划项目(10PTGG342-1) *通信作者:jintaisong@xmu.edu.cn
更新日期/Last Update: 2013-03-20