Learning-Based Object Segmentation Using Regional Spatial Templates and Visual Features
Semantically accurate segmentation of an object of interest (OOI) is a critical step in computer vision tasks. In order to bridge the gap between low-level visual features and high-level semantics, a more complete model of the OOI is needed. To this end, we revise the concept of directional spatial templates and introduce regional directional spatial templates as a means of including spatial relationships among OOI regions into the model. We present an object segmentation algorithm that learns a model which includes both visual and spatial information. Given a training set of images containing the OOI, each image is oversegmented into visually homogeneous regions. Next, Multiple Instance Learning identifies regions that are likely to be part of the OOI. For each pair of such regions and for each relationship, a regional template is formed. The computational cost of template generation is reduced by sampling the reference region with a pixel set that is descriptive of its shape. Experiments indicate that regional templates are an effective way of including spatial information into the model which in turn results in a very significant improvement in segmentation performance.
Unable to display preview. Download preview PDF.
- 2.Vicente, S., Kolmogorov, V., Rother, C.: Graph cut based image segmentation with connectivity priors. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008)Google Scholar
- 5.Viola, P., Platt, J.C., Zhang, C.: Multiple instance boosting for object detection. Advances in Neural Information Processing Systems 18, 1417–1424 (2006)Google Scholar
- 8.Todorovic, S., Ahuja, N.: Extracting subimages of an unknown category from a set of images. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 927–934 (2006)Google Scholar
- 9.Alam, F.I., Gondra, I.: A bayesian network-based tunable image segmentation algorithm for object recognition. In: Proceedings of IEEE International Symposium on Signal Processing and Information Technology, pp. 11–16 (2011)Google Scholar
- 10.Matsakis, P., Ni, J., Wang, X.: Object localization based on directional information: Case of 2d raster data. In: Proceedings of IAPR International Conference on Pattern Recognition, pp. 142–146 (2006)Google Scholar
- 11.Maron, O., Lozano-Perez, T.: A framework for multiple instance learning. In: Proceedings of the Conference on Advances in Neural Information Processing Systems, vol. 10, pp. 570–576 (1998)Google Scholar
- 12.Xu, T., Gondra, I., Chiu, D.: Adaptive kernel diverse density estimate for multiple instance learning. In: Proceedings of 2011 International Conference on Machine Learning and Data Mining, pp. 185–198 (2011)Google Scholar
- 14.Logan, G.D., Sadler, D.D.: A computational analysis of the apprehension of spatial relations. In: Language and Space. MIT Press, Cambridge (1996)Google Scholar
- 15.Gapp, K.P.: Basic meaning of spatial relations: Computation and evaluation in 3d space. In: Proceedings of National Conference on Artificial Intelligence, pp. 1393–1398 (1994)Google Scholar
- 18.Arthur, D., Vassilvitskii, S.: K-means++: The advantages of careful seeding. Technical Report 2006-13, Stanford InfoLab (June 2006)Google Scholar