Hierarchy-based salient regions: A region detector based on hierarchies of partitions

No hay miniatura disponible
Otiniano-Rodríguez K.
de A. Araújo A.
Cámara-Chávez G.
Cousty J.
Guimarães S.J.F.
Perret B.
Título de la revista
Revista ISSN
Título del volumen
Springer Verlag
Proyectos de investigación
Unidades organizativas
Número de la revista
This article introduces a novel region detector based on hierarchies of partitions, so-called Hierarchy-Based Salient Regions (HBSR). This approach enables to combine the clues given by a high quality contour detector with a custom salient region detection procedure. The evaluation of the proposed method HBSR with a standard feature detection assessment framework shows that HBSR outperforms the state-of-the-art methods, in average. These promising results may lead to improvements in many computer vision tasks.
This work received funding from FONDECYT-CONCYTEC (contract number 004-2016-FONDECYT), CAPES (PVE 125000/2014-00), FAPEMIG (PPM 00006-16), and CNPq (Universal 421521/2016-3 and PQ 307062/2016-3).
Palabras clave
State-of-the-art methods, Mathematical morphology, Feature detection, High quality, Salient region detections, Salient regions, Computer vision