Invariant models of vision between phenomenology, image statistics and neurosciences.
Gonzalo Sanguinetti
PhD thesis from Universidad de la República (Uruguay). Facultad de Ingeniería. IIE - 2011
Advisor: Gregory Randall
Co-advisor: Gregory Randall
Research Group(s): Tratamiento de Imagenes (gti)
Department(s): Procesamiento de Señales
Descargar la publicación : San11.pdf [16.6Mo]  


The objective of this thesis is to develop mathematical models of vision which integrate empirical data from three different scientific areas: phenomenology of perception, cognitive neurosciences and image statistics. We mainly focus on low level vision tasks and in particular we are interested in the completion and grouping of contours. Our scope is to identify common properties and structures within the experimental data and to explain them in terms of simple invariance principles, common to the three fields.

Datos adicionales


Referencias BibTex

Descargar BibTex bibtex

Otras publicaciones

» Gonzalo Sanguinetti