Hierarchy-Based Salient Regions: A Region Detector Based on Hierarchies of Partitions

Karla Otiniano-Rodríguez (1, 2) , Arnaldo de A. Araújo (1) , Guillermo Cámara-Chávez (3) , Jean Cousty (2) , Silvio Jamil F. Guimarães (4) , Benjamin Perret (2)

1 UFMG - Universidade Federal de Minas Gerais = Federal University of Minas Gerais [Belo Horizonte, Brazil]
2 LIGM - Laboratoire d'Informatique Gaspard-Monge
3 UFOP - Universidade Federal de Ouro Preto
4 VIPLAB - Audio-visual Information Processing Lab [Sao Gabriel]

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.

Domaines: Traitement des images [eess.IV]

Karla Otiniano-Rodríguez, Arnaldo de A. Araújo, Guillermo Cámara-Chávez, Jean Cousty, Silvio Jamil F. Guimarães, et al.. Hierarchy-Based Salient Regions: A Region Detector Based on Hierarchies of Partitions. CIARP 2018: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, , pp.444-452, 2019, ⟨10.1007/978-3-030-13469-3_52⟩. ⟨hal-02064718⟩