A Novel Distribution of Local Invariant Features for Classification of Scene and Object Categories - Intelligent Information Processing V Access content directly
Conference Papers Year : 2010

A Novel Distribution of Local Invariant Features for Classification of Scene and Object Categories

Abstract

A new image representation based on distribution of local invariant features to be used in a discriminative approach to image categorization is presented. The representation which is called Probability Signature (PS) is combined with character of two distribution models Probability Density Function and standard signatures. The PS representation retains high discriminative power of PDF model, and is suited for measuring dissimilarity of images with Earth Mover's Distance (EMD), which allows for partial matches of compared distributions. It is evaluated on whole-image classification tasks from the scene and category image datasets. The comparative experiments show that the proposed algorithm has inspiring performance.
Fichier principal
Vignette du fichier
3400318.pdf (219.33 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01060367 , version 1 (04-09-2014)

Licence

Attribution

Identifiers

Cite

Lijun Guo, Jieyu Zhao, Rong Zhang. A Novel Distribution of Local Invariant Features for Classification of Scene and Object Categories. 6th IFIP TC 12 International Conference on Intelligent Information Processing (IIP), Oct 2010, Manchester, United Kingdom. pp.308-315, ⟨10.1007/978-3-642-16327-2_37⟩. ⟨hal-01060367⟩
107 View
73 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More