A Linear Programming Based Method for Joint Object Region Matching and Labeling
Object matching can be achieved by finding the superpixels matched across the image and the object template. It can therefore be used for detecting or labeling the object region. However, the matched superpixels are often sparsely distributed within the image domain, and there could therefore be a significant proportion of incorrectly detected or labeled regions even though there are few outlier matches. Consequently, the labeled regions may be unreliable for locating, extracting or representing the object. To address these problems, we propose to impose label priors that were previously incorporated in segmentation on the object matching. Specifically, in order to label as many regions as possible on the object, we propose to adopt the boundary-weighted smoothness prior. To reduce the singular outlier matches as much as possible, we propose to adopt the minimum description length principle adopted in segmentation. We then linearize the priors and incorporate them in the linear programming (LP) formulation of matching. The above gives rise to a novel general LP model for joint object region matching and labeling. This work extends the scope of conventional LP based object matching. The experimental results show that our method compares favorably to the LP based matching methods for object region labeling on a challenging dataset.
KeywordsFeature Match Object Region Linear Programming Formulation Region Label Convex Quadratic Programming
Unable to display preview. Download preview PDF.
- 2.Berg, A.C., Berg, T.L., Malik, J.: Shape matching and object recognition using low distortion correspondences. In: CVPR (2005)Google Scholar
- 4.Jiang, H., Drew, M.S., Li, Z.N.: Convex quadratic programming for object localization. In: ICPR (2006)Google Scholar
- 5.Jiang, H., Yu, S.: Linear solution to scale and rotation invariant object matching. In: CVPR (2009)Google Scholar
- 6.Li, H., Kim, E., Huang, X., He, L.: Object matching with a locally affine-invariant constraint. In: CVPR (2010)Google Scholar
- 10.Kim, T.H., Lee, K.M., Lee, S.U.: A unified probabilistic approach to feature matching and object segmentation. In: ICPR (2010)Google Scholar
- 14.Jiang, H., Tian, T.P., Sclaroff, S.: Scale and rotation invariant matching using linearly augmented trees. In: CVPR (2011)Google Scholar
- 15.Li, H., Huang, J., Zhang, S., Huang, X.: Optimal object matching via convexification and composition. In: ICCV (2011)Google Scholar
- 16.Jiang, H., Tian, T.P., He, K., Sclaroff, S.: Scale resilient, rotation invariant articulated object matching. In: CVPR (2012)Google Scholar
- 18.Li, S.Z.: Markov random field modeling in image analysis, 3rd edn. Springer-Verlag New York, Inc. (2009)Google Scholar
- 22.Vazirani, V.V.: Approximation algorithms. Springer (2001)Google Scholar