Object Detection Combining Recognition and Segmentation

We develop an object detection method combining top-down recognition with bottom-up image segmentation. There are two main steps in this method: a hypothesis generation step and a verification step. In the top-down hypothesis generation step, we design an improved Shape Context feature, which is more robust to object deformation and background clutter. The improved Shape Context is used to generate a set of hypotheses of object locations and figureground masks, which have high recall and low precision rate. In the verification step, we first compute a set of feasible segmentations that are consistent with top-down object hypotheses, then we propose a False Positive Pruning(FPP) procedure to prune out false positives. We exploit the fact that false positive regions typically do not align with any feasible image segmentation. Experiments show that this simple framework is capable of achieving both high recall and high precision with only a few positive training examples and that this method can be generalized to many object classes. Disciplines Computer Sciences Comments Liming Wang, Jianbo Shi, Gang Song, and I-Fan Shen. 2007. Object detection combining recognition and segmentation. In Proceedings of the 8th Asian conference on Computer vision Volume Part I (ACCV'07), Yasushi Yagi, Sing Bing Kang, In So Kweon, and Hongbin Zha (Eds.), Vol. Part I. Springer-Verlag, Berlin, Heidelberg, 189-199. © ACM, 2007. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in Proceedings of the 8th Asian conference on Computer vision Volume Part I , {(2007)} This conference paper is available at ScholarlyCommons: http://repository.upenn.edu/cis_papers/524 Object Detection Combining Recognition and Segmentation Liming Wang, Jianbo Shi, Gang Song, and I-fan Shen 1 Fudan University,Shanghai,PRC,200433 {wanglm,yfshen}@fudan.edu.cn 2 University of Pennsylvania, 3330 Walnut Street, Philadelphia, PA 19104 [email protected],[email protected] Abstract. We develop an object detection method combining top-down recognition with bottom-up image segmentation. There are two main steps in this method: a hypothesis generation step and a verification step. In the top-down hypothesis generation step, we design an improved Shape Context feature, which is more robust to object deformation and background clutter. The improved Shape Context is used to generate a set of hypotheses of object locations and figureground masks, which have high recall and low precision rate. In the verification step, we first compute a set of feasible segmentations that are consistent with top-down object hypotheses, then we propose a False Positive Pruning(FPP) procedure to prune out false positives. We exploit the fact that false positive regions typically do not align with any feasible image segmentation. Experiments show that this simple framework is capable of achieving both high recall and high precision with only a few positive training examples and that this method can be generalized to many object classes. We develop an object detection method combining top-down recognition with bottom-up image segmentation. There are two main steps in this method: a hypothesis generation step and a verification step. In the top-down hypothesis generation step, we design an improved Shape Context feature, which is more robust to object deformation and background clutter. The improved Shape Context is used to generate a set of hypotheses of object locations and figureground masks, which have high recall and low precision rate. In the verification step, we first compute a set of feasible segmentations that are consistent with top-down object hypotheses, then we propose a False Positive Pruning(FPP) procedure to prune out false positives. We exploit the fact that false positive regions typically do not align with any feasible image segmentation. Experiments show that this simple framework is capable of achieving both high recall and high precision with only a few positive training examples and that this method can be generalized to many object classes.