Image co-segmentation based on image complexity analysis and pixel-correspondences

Autor:	Hamid El Ouardi, Rachida Es-salhi, Imane Daoudi
Rok vydání:	2018
Předmět:	Pixel Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Image segmentation Class (biology) Image (mathematics) Set (abstract data type) Simple (abstract algebra) Task analysis Computer vision Segmentation Artificial intelligence business
Zdroj:	ISIVC
DOI:	10.1109/isivc.2018.8709208
Popis:	Image co-segmentation refers to the task of segmenting jointly a set of images sharing objects of a specific class. Recent methods can co-segment simple images well, however their performance may degrade significantly on more cluttered images. In this paper a novel method is presented to jointly segment out common objects from a set of images using image complexity analysis and dense correspondences. The images are first ranked based of their complexity scores. Then a set of simple images is selected and segmented. Finally the segmentation results of simple images are propagated to more cluttered images via multi-scale dense correspondences in order to guide their segmentation. The comparison experiments conducted on iCoseg dataset demonstrate the performance of the proposed method.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::a0deb432c7300f9957c2e6a08440eec9 https://doi.org/10.1109/isivc.2018.8709208 Zobrazit plný text záznamu