Conditional random field-based image labelling combining features of pixels, segments and regions
Authors:
- 21 September 2012
- journal article
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 6 (5) , 459-467
Abstract
Conditional random field (CRF)-based framework is the most popular approach to image labelling. Pixel-based CRF and segment-based CRF correspond to image representations on different scales. Hierarchical CRF models are the main technique to combine multi-scale information of an image. In this study, the authors propose a single-layered segment-based CRF, instead of multi-layered hierarchical CRF, to integrate multi-scale features of pixels, segments and regions. The unary potential associated with a segment in the CRF is determined by the features of pixels in it, instead of by the statistical features of the segment. On the other hand, the features of a pixel contain features of multiple segments it belongs to. By this means, features of pixels and segments computed at different levels are integrated naturally. Furthermore, to alleviate the problem of local minima and to capture long-range semantic context, the authors propose a region-based CRF to model co-occurrence. Compared with some existing approaches to model co-occurrence, it is relatively fast and can correct some co-occurrence constraints violation errors. Experiments on MSRC-21 database show that our model achieves comparable results to the state-of-the-art algorithms but with lower complexity.Keywords
This publication has 10 references indexed in Scilit:
- Context based object categorization: A critical surveyComputer Vision and Image Understanding, 2010
- An Efficient Approach to Semantic SegmentationInternational Journal of Computer Vision, 2010
- Robust Higher Order Potentials for Enforcing Label ConsistencyInternational Journal of Computer Vision, 2009
- Multi-Class Segmentation with Relative Location PriorInternational Journal of Computer Vision, 2008
- TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and ContextInternational Journal of Computer Vision, 2007
- Sharing Visual Features for Multiclass and Multiview Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- A hierarchical field framework for unified context-based classification2005
- An experimental comparison of min-cut/max- flow algorithms for energy minimization in visionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- What energy functions can be minimized via graph cuts?IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Fast approximate energy minimization via graph cutsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001