Kernels on bags for multi-object database retrieval

In this paper, a kernel-based method for multi-object retrieval in large image database is presented. First, our approach exploits a fuzzy region segmentation approach in order to get robust local feature extraction and characterization. All the region features are summarized in bags representing the image index. The main part of this work concerns the kernel functions to deal with sets of features. Based on the linear combination of minor kernels, a family of kernels on bags is introduced. Several weighting

• Type: Conference
• Year: 2007
• Where: CIVR
• Authors: Philippe Henri Gosselin, Matthieu Cord, Sylvie Philipp-Foliguet
• Keywords: CIVR 2007, Large Image Database, Region Segmentation Approach, Robust Local Feature