Leave-One-Out Kernel Optimization for Shadow Detection
Authors:
- Tomas F. Yago VicenteTVTomas F. Yago Vicente
- Minh HoaiMHMinh Hoai
- Dimitris SamarasDSDimitris Samaras
- 1 December 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3388-3396
Abstract
The objective of this work is to detect shadows in images. We pose this as the problem of labeling image regions, where each region corresponds to a group of superpixels. To predict the label of each region, we train a kernel Least-Squares SVM for separating shadow and non-shadow regions. The parameters of the kernel and the classifier are jointly learned to minimize the leave-one-out cross validation error. Optimizing the leave-one-out cross validation error is typically difficult, but it can be done efficiently in our framework. Experiments on two challenging shadow datasets, UCF and UIUC, show that our region classifier outperforms more complex methods. We further enhance the performance of the region classifier by embedding it in an MRF framework and adding pairwise contextual cues. This leads to a method that significantly outperforms the state-of-the-art.Keywords
This publication has 26 references indexed in Scilit:
- Regularized Max Pooling for Image Categorization2014
- Single Image Shadow Detection Using Multiple Cues in a Supermodular MRF2013
- What characterizes a shadow boundary under the sun and sky?2011
- Learning to recognize shadows in monochromatic natural images2010
- More generality in efficient multiple kernel learning2009
- Recovering Surface Layout from an ImageInternational Journal of Computer Vision, 2007
- Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive StudyInternational Journal of Computer Vision, 2006
- Support vector machines for region-based image retrieval2003
- Classifying Images of Materials: Achieving Viewpoint and Illumination Independence2002
- The Nature of Statistical Learning Theory1995