Fast and smart object proposals for object detection

Simple item page
dc.contributor.authorAmrane, Abdesalam
dc.contributor.authorMeziane, Abdelkrim
dc.contributor.authorBoulekrinat, Houda
dc.contributor.authorAtik, Ali
dc.date.accessioned2017-04-10T10:25:56Z
dc.date.available2017-04-10T10:25:56Z
dc.date.issued2017-05-11
dc.description.abstractObject localization plays an important role in object detection and classification. In the last years, several methods have shifted from sliding windows techniques to object proposals techniques. The latter produces a small set of windows submitted to an object classifier to reduce the computational time. In this paper, we propose a fast unsupervised method that combines the edge feature and saliency map to generate less than hundred bounding boxes from the processed image. Our approach exploits a number of rules based on edges information plus saliency regions to decide if an object is present in a window. We have carried out several experiments to validate our approach on ImageNet dataset and obtained very promising results.fr_FR
dc.identifier.isrnCERIST-DSISM/RR-17-00000007--DZfr_FR
dc.identifier.urihttp://dl.cerist.dz/handle/CERIST/884
dc.publisherCERIST
dc.relation.ispartofRapports de recherche internes
dc.relation.placeAlger
dc.structureSystèmes et Documents Multimédia Structurés (SDMS)fr_FR
dc.subjectObject proposalsfr_FR
dc.subjectBounding boxfr_FR
dc.subjectObject detectionfr_FR
dc.subjectSaliency mapfr_FR
dc.subjectSliding windowfr_FR
dc.titleFast and smart object proposals for object detectionfr_FR
dc.typeTechnical Report
Files
Collections
Research Reports