Object scale selection of hierarchical image segmentation with deep seeds
Open Access
- 6 December 2020
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 15 (1) , 191-205
Abstract
Hierarchical image segmentation is a prevalent technique in the literature for improving segmentation quality, where the segmentation result needs to be searched at different scales of the hierarchy to identify objects represented from various scales. In this paper, a novel framework for improving the quality of object segmentation is presented. To this end, the authors first select the optimal segments among several hierarchical scales of the input image using simple mid‐level features and dynamic programming. Simultaneously, deep seeds are localised on the input image for the foreground and background classes using a deep classification network and a saliency network, respectively. Then, a graphical model is constructed as a set of nodes that jointly propagate information from deep seeds to unmarked regions to obtain the final object segmentation. Comprehensive experiments are performed on different datasets for popular hierarchical image segmentation algorithms. The experimental results show that the proposed framework can significantly improve the quality of object segmentation at low computational costs and without training any segmentation network.Keywords
Funding Information
- National Natural Science Foundation of China (61772435, 61976247)
This publication has 53 references indexed in Scilit:
- Human perception‐based image segmentation using optimising of colour quantisationIET Image Processing, 2014
- Scale selection for supervised image segmentationImage and Vision Computing, 2012
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Parameter Selection for Graph Cut Based Image Segmentation2008
- SURF: Speeded Up Robust Features2006
- TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation2006
- Automatic seeded region growing for color image segmentationImage and Vision Computing, 2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004
- Fast approximate energy minimization via graph cutsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001