Litcius/Paper detail

Superpixel Segmentation Using Dynamic and Iterative Spanning Forest

Felipe C. Belem, Silvio Jamil F. Guimaraes, Alexandre X. Falcao

2020IEEE Signal Processing Letters43 citationsDOIOpen Access PDF

Abstract

As constituent parts of image objects, superpixels can improve several higher-level operations. However, image segmentation methods might have their accuracy severely compromised for reduced numbers of superpixels. To mitigate the problem, we introduce Dynamic Iterative Spanning Forest (DISF), a seed-based method that improves all components in the Iterative Spanning Forest (ISF) framework for superpixel segmentation. DISF relies on a new strategy for seed estimation that can find more relevant seeds, reconstruct relevant edges along with iterations, and guarantee the desired number of superpixels. DISF also assures optimal spanning forests for path costs based on dynamic arc-weight estimation, being faster as the desired number of superpixels grows. We show that DISF can improve effectiveness on three datasets with distinct object properties, requiring significantly fewer iterations than all seed-based baselines.

Topics & Concepts

Computer scienceImage segmentationIterative methodArtificial intelligenceSegmentationPath (computing)Pattern recognition (psychology)Image (mathematics)Object (grammar)Spanning treeObject detectionComputer visionMinimum spanning treeIterative refinementMarket segmentationScale-space segmentationIterative reconstructionAlgorithmData miningFeature extractionMedical Image Segmentation TechniquesAdvanced Neural Network ApplicationsAdvanced Image and Video Retrieval Techniques
Superpixel Segmentation Using Dynamic and Iterative Spanning Forest | Litcius