Image Similarity Based on Hierarchies of ICA Mixtures [chapter]

Arturo Serrano, Addisson Salazar, Jorge Igual, Luis Vergara
Independent Component Analysis and Signal Separation  
This paper presents a novel algorithm to build hierarchies from independent component analyzer mixtures and its application to image similarity measure. The hierarchy algorithm composes an agglomerative (bottom-up) clustering from the estimated parameters (basis vectors and bias terms) of the ICA mixture. Merging at different levels of the hierarchy is made using the Kullback-Leibler distance between clusters. The procedure is applied to merge similar patches on a natural image, to group
more » ... nt images of an object, and to create hierarchical levels of clustering from images of different objects. Results show suitable image hierarchies obtained by clustering from basis functions to higher-level structures.
doi:10.1007/978-3-540-74494-8_98 dblp:conf/ica/SerranoSIV07 fatcat:l6ablkxlz5hffk3yisykvy64zy