Abstract | ||
---|---|---|
In this paper we propose PHOTO (pyramid histogram of topics), a new representation for image classification. We partition the image into hierarchical cells and learn the topic histogram using pLSA over each cell with EM algorithm. Then we concatenate the topic histograms over the cells at all levels to form a ldquolongrdquo vector, i.e. pyramid histogram of topics. Finally AdaBoost classifiers are used to select the topics most discriminative for class recognition. Experimental results on two diverse databases show that our method performs significantly better than general topic representation. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICME.2009.5202518 | ICME |
Keywords | Field | DocType |
diverse databases,class recognition,expectation-maximisation algorithm,em,photo,adaboost classifier,expectation maximisation algorithm,statistical analysis,learning (artificial intelligence),image classification,pyramid histogram-of-topic,new representation,adaboost,plsa,support vector machine,probabilistic latent semantic analysis,pyramid histogram,topic histogram learning,topic histogram,general topic representation,em algorithm,probability,data mining,learning artificial intelligence,histograms,testing,feature extraction,kernel | Computer vision,Histogram,Pattern recognition,Computer science,Pyramid (image processing),Histogram matching,Feature extraction,Artificial intelligence,Pyramid,Balanced histogram thresholding,Contextual image classification,Image histogram | Conference |
ISSN | ISBN | Citations |
1945-7871 E-ISBN : 978-1-4244-1291-1 | 978-1-4244-1291-1 | 4 |
PageRank | References | Authors |
0.42 | 8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fuxiang Lu | 1 | 12 | 1.58 |
Xiaokang Yang | 2 | 3581 | 238.09 |
Rui Zhang | 3 | 92 | 7.65 |
Yu Song | 4 | 356 | 52.74 |