A Thermodynamic and Biologically Inspired Kernel Similarity Method

Assessment of image similarity is ubiquitous and essential task to a wide range multimedia applications. In this paper we propose a similarity method which aims at providing an image classification scheme using multi-instances based representation of an image. In other words, the similarity measure is defined to be used within two sample sets where each set, which can be defined in an arbitrary metric space, consists in a set of local features used in describing the content of an image. This measure is a kernel based similarity method inspired from an interesting biological behavior of trees, derived from an energy scheme and induced mathematically by formulating it as a quadratic optimization problem in a reproducing kernel Hilbert space (RKHS).