Piecing together the segmentation jigsaw using context

TitlePiecing together the segmentation jigsaw using context
Publication TypeConference Papers
Year of Publication2011
AuthorsChen X, Jain A, Gupta A, Davis LS
Conference NameComputer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Date Published2011/06//
Keywordsalgorithms;image, approximation, formulation;greedy, function, information;cost, manner;image, programming;approximation, recognition;image, segmentation;, segmentation;jigsaw, segmentation;quadratic, solution;contextual, theory;greedy

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.