Estamos realizando la búsqueda. Por favor, espere...


Semi-supervised object recognition based on Connected Image Transformations

Abstract: We present a novel semi-supervised classifier model based on paths between unlabeled and labeled data through a sequence of local pattern transformations. A reliable measure of path-length is proposed that combines a local dissimilarity measure between consecutive patters along a path with a global, connectivity-based metric. We apply this model to problems of object recognition, for which we propose a practical classification algorithm based on sequences of "Connected Image Transformations" (CIT). Experimental results on four popular image benchmarks demonstrate how the proposed CIT classifier outperforms state-of-the-art semi-supervised techniques. The results are particularly significant when only a very small number of labeled patterns is available: the proposed algorithm obtains a generalization error of 4.57% on the MNIST data set trained on 2000 randomly chosen patterns with only 10 labeled patterns per digit class.

 Autoría: Van Vaerenbergh S., Santamaría I., Barbano P.,

 Fuente: Expert Systems with Applications, 2013, 40(17), 7069-7079

Editorial: Elsevier Ltd

 Fecha de publicación: 01/12/2013

Nº de páginas: 11

Tipo de publicación: Artículo de Revista

 DOI: 10.1016/j.eswa.2013.06.029

ISSN: 0957-4174,1873-6793

Proyecto español: TEC2010-19545-C04-03 ; CSD2008-00010

Url de la publicación: https://doi.org/10.1016/j.eswa.2013.06.029