Combined Top-Down/Bottom-Up Segmentation

Eran Borenstein, Shimon Ullman

Abstract

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.
BibTeX
@article{borenstein2008combined,
  author = {Eran Borenstein and Shimon Ullman},
  title = {{Combined Top-Down/Bottom-Up Segmentation}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {2008},
  doi = {10.1109/tpami.2007.70840},
}

Loading related content...

Figure