Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation

Pont-Tuset, Jordi; Arbeláez, Pablo; Barron, Jonathan T.; Marqués, Ferran; Malik, Jitendra

doi:10.1109/tpami.2016.2537320

articleIEEE Transactions on Pattern Analysis and Machine IntelligenceMar 2, 2016GREEN OA

Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation

JPJordi Pont-Tuset PAPablo Arbeláez JTJonathan T. Barron FMFerran Marqués JMJitendra Malik

Universitat Politècnica de Catalunya · Universidad de Los Andes · +1 more institution

PubMed

Indexed inarxivcrossrefpubmed

Abstract

We propose a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG). For this purpose, we first develop a fast normalized cuts algorithm. We then propose a high-performance hierarchical segmenter that makes effective use of multiscale information. Finally, we propose a grouping strategy that combines our multiscale regions into highly-accurate object proposals by exploring efficiently their combinatorial space. We also present Single-scale Combinatorial Grouping (SCG), a faster version of MCG that produces competitive proposals in under five seconds per image. We conduct an extensive and comprehensive…

Citation impact

615

total citations

FWCI: 45.11
Percentile: 100%
References: 51

Citations per year

Authors

5

Topics & keywords

Topics

Keywords

Computer science
Object (grammar)
Segmentation
Artificial intelligence
Image segmentation
Image (mathematics)
Pattern recognition (psychology)
Scale (ratio)

No related works found for this paper.