Abstract not found

Perceptual organization refers to the process of organizing sensory input into coherent and interpretable perceptual structures. This process is challenging due to the chicken-and-egg nature between the various sub-processes such as image segmentation, figure-ground segregation and object recognition. Low-level processing requires the guidance of high-level knowledge to overcome noise; while high-level processing relies on low-level processes to reduce the computational complexity. Neither process can be sufficient on its own. Consequently, any system that carries out these processes in a sequence is bound to be brittle. An alternative system is one in which all processes interact with each other simultaneously. In this thesis, we develop a set of simple yet realistic interactive processing models for perceptual organization. We model the processing in the framework of spectral graph theory, with a criterion encoding the overall goodness of perceptual organization. We derive fast solutions for near-global optima of the criterion, and demonstrate the efficacy of the models on segmenting a wide range of real images. Through these models, we are able to capture a variety of perceptual phenomena: a unified treatment of various grouping, figure-ground and depth cues to produce popout, region segmentation and depth segregation in one step; and a unified framework for integrating bottom-up and top-down information to produce an object segmentation from spatial and object attention. We achieve these goals by empowering current spectral graph methods with a principled solution for multiclass spectral graph partitioning; expanded repertoire of grouping cues to include similarity, dissimilarity and ordering relationships; a theory for integrating sparse grouping cues; and a model ...

In this paper, we explore ways to combine boundary information and region segmentation to estimate regions corresponding to foreground objects. Boundary information is used to generate an object likelihood image which encodes the likelihood that each pixel belongs to a foreground object. This is done by combining evidence gathered from a large number of boundary fragments on training images by exploiting the relation between local boundary shape and relative location of the corresponding object region in the image. A region segmentation is used to generate a likely segmentation that is consistent with the boundary fragments out of a set of multiple segmentations. A mutual information criterion is used for selecting a segmentation from a set of multiple segmentations. Object likelihood and region segmentation are combined to yield the final proposed object region(s). 1.

Abstract not found