Published Articles >> Table of Contents >> Abstract

17th International Conference on Pattern Recognition (ICPR'04) - Volume 2   pp. 132-135
Object Categorization via Local Kernels
Barbara Caputo, NADA/CVAP, KTH, Stockholm, Sweden
Christian Wallraven, MPI for Biological Cybernetics, Germany
Maria-Elena Nilsback, NADA/CVAP, KTH, Stockholm, Sweden

Full Article Text:

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICPR.2004.1334079
Send link to a friend

Abstract
This paper considers the problem of multi-object categorization. We present an algorithm that combines support vector machines with local features via a new class of Mercer kernels. This class of kernels allows us to perform scalar products on feature vectors consisting of local descriptors, computed around interest points (like corners); these feature vectors are generally of different lengths for different images. The resulting framework is able to recognize multi-object categories in different settings, from lab-controlled to real-world scenes. We present several experiments, on different databases, and we benchmark our results with state-of-the-art algorithms for categorization, achieving excellent results.
Back to Top Additional Information
Citation:  Barbara Caputo, Christian Wallraven, Maria-Elena Nilsback, "Object Categorization via Local Kernels," icpr, pp. 132-135,  17th International Conference on Pattern Recognition (ICPR'04) - Volume 2,  2004