Computational Models of Perceptual Organization

Stella Yu
doctoral dissertation, tech. report CMU-RI-TR-03-14, Robotics Institute, Carnegie Mellon University, May, 2003


Download
  • Adobe portable document format (pdf) (4MB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
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 for representing and integrating higher-order relationships. These computational tools are also useful more generally in other domains where data need to be organized effectively.


Keywords
perceptual organization,image segmentation, figure-ground,depth segregation,attention, bias, popout, visual search,clustering, graph partitioning, constrained optimization

Notes
Note: CNBC and HumanID

Text Reference
Stella Yu, "Computational Models of Perceptual Organization," doctoral dissertation, tech. report CMU-RI-TR-03-14, Robotics Institute, Carnegie Mellon University, May, 2003

BibTeX Reference
@phdthesis{Yu_2003_4393,
   author = "Stella Yu",
   title = "Computational Models of Perceptual Organization",
   booktitle = "",
   school = "Robotics Institute, Carnegie Mellon University",
   month = "May",
   year = "2003",
   number= "CMU-RI-TR-03-14",
   address= "Pittsburgh, PA",
   Notes = "CNBC and HumanID"
}