CVPR 2011 (2011)
June 20, 2011 to June 25, 2011
Xi Chen , Univ. of Maryland, College Park, MD, USA
A. Jain , Univ. of Maryland, College Park, MD, USA
A. Gupta , Carnegie Mellon Univ., Pittsburgh, PA, USA
L. S. Davis , Univ. of Maryland, College Park, MD, USA
We present an approach to jointly solve the segmentation and recognition problem using a multiple segmentation framework. We formulate the problem as segment selection from a pool of segments, assigning each selected segment a class label. Previous multiple segmentation approaches used local appearance matching to select segments in a greedy manner. In contrast, our approach formulates a cost function based on contextual information in conjunction with appearance matching. This relaxed cost function formulation is minimized using an efficient quadratic programming solver and an approximate solution is obtained by discretizing the relaxed solution. Our approach improves labeling performance compared to other segmentation based recognition approaches.
image recognition, jigsaw segmentation, greedy manner, contextual information, cost function formulation, quadratic programming, approximation solution, image segmentation
A. Jain, Xi Chen, L. S. Davis and A. Gupta, "Piecing together the segmentation jigsaw using context," CVPR 2011(CVPR), Providence, RI, 2011, pp. 2001-2008.