Local Higher-Order Statistics (LHS) for Texture Categorization and Facial Analysis

Gaurav Sharma^{1, 2}, Sibt ul Hussain¹, and Frédéric Jurie¹

¹GREYC, CNRS UMR 6072, Université de Caen, France
gaurav.sharma@unicaen.fr
frederic.jurie@unicaen.fr

²LEAR, INRIA Grenoble Rhône-Alpes, France

Abstract. This paper proposes a new image representation for texture categorization and facial analysis, relying on the use of higher-order local differential statistics as features. In contrast with models based on the global structure of textures and faces, it has been shown recently that small local pixel pattern distributions can be highly discriminative. Motivated by such works, the proposed model employs higher-order statistics of local non-binarized pixel patterns for the image description. Hence, in addition to being remarkably simple, it requires neither any user specified quantization of the space (of pixel patterns) nor any heuristics for discarding low occupancy volumes of the space. This leads to a more expressive representation which, when combined with discriminative SVM classifier, consistently achieves state-of-the-art performance on challenging texture and facial analysis datasets outperforming contemporary methods (with similar powerful classifiers).

LNCS 7578, p. 1 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012