Hierarchical Bag of Paths for Kernel Based Shape Classification

TL;DR

This paper introduces a hierarchical bag of paths kernel for shape classification that enhances robustness to noise by encoding simplified path hierarchies, improving over existing graph kernel methods.

Contribution

It presents a novel kernel method based on hierarchical paths that increases robustness to noise in shape classification tasks.

Findings

Demonstrates improved robustness to structural noise

Shows flexibility and effectiveness over alternative methods

Validates approach through multiple experiments

Abstract

Graph kernels methods are based on an implicit embedding of graphs within a vector space of large dimension. This implicit embedding allows to apply to graphs methods which where until recently solely reserved to numerical data. Within the shape classification framework, graphs are often produced by a skeletonization step which is sensitive to noise. We propose in this paper to integrate the robustness to structural noise by using a kernel based on a bag of path where each path is associated to a hierarchy encoding successive simplifications of the path. Several experiments prove the robustness and the flexibility of our approach compared to alternative shape classification methods.