Multivariate log-Gaussian Cox models of elementary shapes for recognizing natural scene categories

Author

Nguyen, Huu-Giao ; Fablet, Ronan ; Boucher, Jean-Marc

Author_Institution

LabSTICC, Inst. Telecom, Brest, France

fYear

2011

fDate

11-14 Sept. 2011

Firstpage

665

Lastpage

668

Abstract

In this paper, we address invariant scene classification from images. We propose a novel descriptor based on the statistical characterization of the spatial patterns formed by elementary objects in images. Elementary objects are defined from a tree of shapes of the topology map of the image and each object is characterized by shape context feature vector. Viewing the set of elementary objects as a realization of a random spatial process, we investigate a statistical analysis using log- Gaussian Cox model to define an invariant image descriptor. An application to natural scene recognition is described. Re- ported results validate the proposed descriptor with respect to previous work.

Keywords

Gaussian processes; image classification; image recognition; natural scenes; random processes; solid modelling; statistical analysis; trees (mathematics); elementary objects; elementary shapes; invariant image descriptor; invariant scene classification; multivariate log-Gaussian Cox model; natural scene category recognition; random spatial process realization; shape context feature vector; spatial pattern characterization; statistical analysis; statistical characterization; topology map; Conferences; Context; Correlation; Probabilistic logic; Shape; Training; Visualization; inner-distance shape context; log-Gaussian Cox process; scene recognition; topographic map;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2011 18th IEEE International Conference on

Conference_Location

Brussels

ISSN

1522-4880

Print_ISBN

978-1-4577-1304-0

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2011.6116640

Filename

6116640