Image Classification with Segmentation Graph Kernels

We propose a family of kernels between images, defined as kernels between their respective segmentation graphs. The kernels are based on soft matching of subtree-patterns of the respective graphs, leveraging the natural structure of images while remaining robust to the associated segmentation process uncertainty. Indeed, output from morphological segmentation is often represented by a labelled graph, each vertex corresponding to a segmented region, with edges joining neighboring regions. However, such image representations have mostly remained underused for learning tasks, partly because of the observed instability of the segmentation process and the inherent hardness of inexact graph matching with uncertain graphs. Our kernels count common virtual substructures amongst images, which enables to perform efficient supervised classification of natural images with a support vector machine. Moreover, the kernel machinery allows us to take advantage of recent advances in kernel-based learni...

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Francis Bach, Zaïd Harchaoui
• Keywords: Computer Vision, CVPR 2007, Kernel Learning Algorithms, Labelled Images, Morphological Segmentation, Respective Segmentation Graphs, Segmentation Process Uncertainty