图像分类中的分割模型.ppt

Part 4: combined segmentation and recognition Aim Given an image and object category, to segment the object In this section: brief paper reviews Jigsaw approach: Borenstein Ullman, 2001, 2002 Concurrent recognition and segmentation: Yu and Shi, 2002 Image parsing: Tu et al. 2003 Interleaved segmentation: Liebe Schiele, 2004, 2005 OBJCUT: Kumar et al. 2005 LOCUS: Winn and Jojic, 2005 Jigsaw approach: Borenstein and Ullman, 2001, 2002 Jigsaw approach Object-Specific Figure-Ground Segregation Object-Specific Figure-Ground Segregation Image parsing: Tu, Zhu and Yuille 2003 Image parsing: Tu, Zhu and Yuille 2003 Implicit Shape Model - Recognition Segmentation Cows: Results Segmentations from interest points Single-frame recognition - No temporal continuity used! OBJCUT:shape prior -- Layered Pictorial Structures (LPS) Generative model Composition of parts + spatial layout OBJCUT OBJCUT: Results LOCUS model Summary Strength Explains every pixel of the image Useful for image editing, layering, etc. Issues Invariance issues (especially) scale, view-point variations * Perceptual and Sensory Augmented Computing * Interleaved Object Categorization and Segmentation Perceptual and Sensory Augmented Computing Interleaved Object Categorization and Segmentation * * Li Fei-Fei Segmentation should (ideally) be shaped like the object e.g. cow-like obtained efficiently in an unsupervised manner able to handle self-occlusion Segmentation Object Category Model Cow Image Segmented Cow Each patch has foreground/background mask Stella X. Yu and Jianbo Shi, 2002 Some segmentation/detection results Yu and Shi, 2002 BackprojectedHypotheses Interest Points Matched Codebook Entries Probabilistic Voting Voting Space(continuous) Backprojectionof Maxima Segmentation Refined Hypotheses(uniform sampling) Liebe and Schiele, 2003, 2005 Interpretation of p(figure) map per-pixel confidence in object hypothesis Use for hypothesis verification p(figure) p(ground) Segment