Auto-Context and Its Application to High-Level Vision Tasks and 3D Brain Image Segmentation
Top Cited Papers
- 1 December 2009
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Ieee Transactions On Pattern Analysis and Machine Intelligence
- Vol. 32 (10), 1744-1757
- https://doi.org/10.1109/tpami.2009.186
Abstract
The notion of using context information for solving high-level vision and medical image segmentation problems has been increasingly realized in the field. However, how to learn an effective and efficient context model, together with an image appearance model, remains mostly unknown. The current literature using Markov Random Fields (MRFs) and Conditional Random Fields (CRFs) often involves specific algorithm design in which the modeling and computing stages are studied in isolation. In this paper, we propose a learning algorithm, auto-context. Given a set of training images and their corresponding label maps, we first learn a classifier on local image patches. The discriminative probability (or classification confidence) maps created by the learned classifier are then used as context information, in addition to the original image patches, to train a new classifier. The algorithm then iterates until convergence. Auto-context integrates low-level and context information by fusing a large number of low-level appearance features with context and implicit shape information. The resulting discriminative algorithm is general and easy to implement. Under nearly the same parameter settings in training, we apply the algorithm to three challenging vision applications: foreground/background segregation, human body configuration estimation, and scene region labeling. Moreover, context also plays a very important role in medical/brain images where the anatomical structures are mostly constrained to relatively fixed positions. With only some slight changes resulting from using 3D instead of 2D features, the auto-context algorithm applied to brain MRI image segmentation is shown to outperform state-of-the-art algorithms specifically designed for this domain. Furthermore, the scope of the proposed algorithm goes beyond image analysis and it has the potential to be used for a wide variety of problems for structured prediction problems.Keywords
This publication has 37 references indexed in Scilit:
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- SmcHD1, containing a structural-maintenance-of-chromosomes hinge domain, has a critical role in X inactivationNature Genetics, 2008
- A Bayesian model for joint segmentation and registrationNeuroImage, 2006
- Performance-Based Classifier Combination in Atlas-Based Image Segmentation Using Expectation-Maximization Parameter EstimationIEEE Transactions on Medical Imaging, 2004
- Neighbor-Constrained Segmentation With Level Set Based 3-D Deformable ModelsIEEE Transactions on Medical Imaging, 2004
- Fast robust automated brain extractionHuman Brain Mapping, 2002
- Shape matching and object recognition using shape contextsIeee Transactions On Pattern Analysis and Machine Intelligence, 2002
- Boosting the margin: a new explanation for the effectiveness of voting methodsThe Annals of Statistics, 1998
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- MRI-PET Registration with Automated AlgorithmJournal of Computer Assisted Tomography, 1993