Overlapped text segmentation using Markov random field and aggregation
DAS '10 Proceedings of the 9th IAPR International Workshop on Document Analysis Systems
A compositional exemplar-based model for hair segmentation
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part III
Inference scene labeling by incorporating object detection with explicit shape model
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part III
A Numerical Study of the Bottom-Up and Top-Down Inference Processes in And-Or Graphs
International Journal of Computer Vision
Distance images and intermediate-level vision
SSVM'11 Proceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision
Object Recognition by Sequential Figure-Ground Ranking
International Journal of Computer Vision
From meaningful contours to discriminative object shape
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Two-granularity tracking: mediating trajectory and detection graphs for tracking under occlusions
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
A generative model for simultaneous estimation of human body shape and pixel-level segmentation
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Fast planar correlation clustering for image segmentation
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
Object class detection: A survey
ACM Computing Surveys (CSUR)
Hi-index | 0.14 |
We construct a segmentation scheme that combines top-down with bottom-up processing. In the proposed scheme, segmentation and recognition are intertwined rather than proceeding in a serial manner. The top-down part applies stored knowledge about object shapes acquired through learning, whereas the bottom-up part creates a hierarchy of segmented regions based on uniformity criteria. Beginning with unsegmented training examples of class and non-class images, the algorithm constructs a bank of class-specific fragments and determines their figure-ground segmentation. This bank is then used to segment novel images in a top-down manner: the fragments are first used to recognize images containing class objects, and then to create a complete cover that best approximates these objects. The resulting segmentation is then integrated with bottom-up multi-scale grouping to better delineate the object boundaries. Our experiments, applied to a large set of four classes (horses, pedestrians, cars, faces), demonstrate segmentation results that surpass those achieved by previous top-down or bottom-up schemes. The main novel aspects of this work are the fragment learning phase, which efficiently learns the figure-ground labeling of segmentation fragments, even in training sets with high object and background variability; combining the top-down segmentation with bottom-up criteria to draw on their relative merits; and the use of segmentation to improve recognition.