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 figure-ground 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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Recovering Human Body Configurations: Combining Segmentation and Recognition

    Mori, G. / Ren, X. / Efros, A. et al. | British Library Conference Proceedings | 2004


    Recovering human body configurations: combining segmentation and recognition

    Mori, G. / Xiaofeng Ren, / Efros, A.A. et al. | IEEE | 2004


    Object Recognition by Combining Paraperspective Images

    Sugimoto, A. | British Library Online Contents | 1996


    Combining Generative Models and Fisher Kernels for Object Recognition

    Holub, A. / Welling, M. / Perona, P. et al. | British Library Conference Proceedings | 2005


    Combining generative models and Fisher kernels for object recognition

    Holub, A.D. / Welling, M. / Perona, P. | IEEE | 2005