Scale-Invariance of Support Vector Machines based on the Triangular Kernel

Hichem Sahbi (1) , François Fleuret (1)

1 IMEDIA - Image and multimedia indexing, browsing and retrieval

This report focuses on the scale-invariance and the good performances of Support Vector Machines based on the triangular kernel. After a mathematica- l analysis of the scale-invariance of learning with that kernel, we illustrate its behavior with a simple 2D classification problem and compare its performances to those of a Gaussian kernel on face detection and handwritten character recognition

Mots clés: SUPPORT VECTOR MACHINE; KERNEL METHODS; STATISTICAL LEARNING; OBJECT RECOGNITION

Domaines: Autre [cs.OH]

Hichem Sahbi, François Fleuret. Scale-Invariance of Support Vector Machines based on the Triangular Kernel. [Research Report] RR-4601, INRIA. 2002. ⟨inria-00071984⟩