Lazy Random Walks for Superpixel Segmentation
Top Cited Papers
- 27 January 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 23 (4), 1451-1462
- https://doi.org/10.1109/tip.2014.2302892
Abstract
We present a novel image superpixel segmentation approach using the proposed lazy random walk (LRW) algorithm in this paper. Our method begins with initializing the seed positions and runs the LRW algorithm on the input image to obtain the probabilities of each pixel. Then, the boundaries of initial superpixels are obtained according to the probabilities and the commute time. The initial superpixels are iteratively optimized by the new energy function, which is defined on the commute time and the texture measurement. Our LRW algorithm with self-loops has the merits of segmenting the weak boundaries and complicated texture regions very well by the new global probability maps and the commute time strategy. The performance of superpixel is improved by relocating the center positions of superpixels and dividing the large superpixels into small ones with the proposed optimization algorithm. The experimental results have demonstrated that our method achieves better performance than previous superpixel approaches.Keywords
Funding Information
- National Basic Research Program of China (973 Program) (2013CB328805)
- Key Program of NSFC Guangdong Union Foundation (U1035004)
- National Natural Science Foundation of China (61272359, 61125106)
- Program for New Century Excellent Talents in University (NCET-11-0789)
- Shaanxi Key Innovation Team of Science and Technology (2012KCT-04)
- Beijing Higher Education Young Elite Teacher Project
- Specialized Fund for Joint Building Program of Beijing Municipal Education Commission
This publication has 22 references indexed in Scilit:
- VCells: Simple and Efficient Superpixels Using Edge-Weighted Centroidal Voronoi TessellationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Segmentation of Stochastic Images With a Stochastic Random Walker MethodIEEE Transactions on Image Processing, 2012
- Entropy rate superpixel segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- TurboPixels: Fast Superpixels Using Geometric FlowsIeee Transactions On Pattern Analysis and Machine Intelligence, 2009
- Geodesic Matting: A Framework for Fast Interactive Image and Video Segmentation and MattingInternational Journal of Computer Vision, 2008
- Superpixel latticesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- A Seeded Image Segmentation Framework Unifying Graph Cuts And Random Walker Which Yields A New AlgorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Random Walks for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Isoperimetric graph partitioning for image segmentationIeee Transactions On Pattern Analysis and Machine Intelligence, 2006
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004