Part-Based Representations of Visual Shape and Implications for Visual Cognition

  title={Part-Based Representations of Visual Shape and Implications for Visual Cognition},
  author={Manish Singh and Donald D. Hoffman},
  journal={Advances in psychology},
Visual explanations
This work discusses how analyzing these structures and realizing them in formal representations can allow computer graphics to engage with perceptual science, to mutual benefit.
Abstraction of 2D shapes in terms of parts
This work develops a computational method for the abstract depiction of 2D shapes by organizing the shape into parts using a new synthesis of holistic features of the part shape, local Features of the shape boundary, and global aspects of shape organization.
What change detection tells us about the visual representation of shape.
This study investigates how the human visual system represents the shape of objects by demonstrating a previously unknown influence on detection of changes in shape: the sign of contour curvature.
Curious Objects: How Visual Complexity Guides Attention and Engagement
This work algorithmically generated a library of geometric shapes and determined their complexity by computing the cumulative surprisal of their internal skeletons-essentially quantifying the "amount of information" within each shape- and explored the function of complexity.
Shape Information Mediating Basic- and Subordinate-Level Object Recognition Revealed by Analyses of Eye Movements
It is argued that both basic- and subordinate-level classification are mediated by object representations that make explicit internal part boundaries, and distinguish concave and convex regions of bounding contour.
The Role of Part Structure in the Perceptual Localization of a Shape
Results show that the part structure of a shape plays a role in the representation of its location, and that for complex shapes the perceived location of an embedded element depends more on the parts within which it is embedded, rather than on the whole shape.
Perceived orientation of complex shape reflects graded part decomposition.
It is suggested that Robust Statistics may provide a useful framework for quantifying the influence of part segmentation on visual estimation and a quantitative characterization of part salience in terms of part independence.
Planar shape decomposition made simple
This work revisits the problem assuming the medial axis representation and introduces a new computational model referred to as medial axis decomposition (MAD), which is argued that this representation is both efficient and robust, at least as far as decomposition is concerned, and as long as a part hierarchy is not sought.


Parts of recognition
Object-Based Visual Selection: Evidence From Perceptual Completion
A large body of evidence suggests that visual attention selects objects as well as spatial locations. If attention is to be regarded as truly object based, then it should operate not only on object
Salience of visual parts
Image Segmentation Cues in Motion Processing: Implications for Modularity in Vision
Findings in psychophysical and neurophysiological experiments have shown that the primate visual system's normally veridical interpretation of moving patterns is attained through utilization of image segmentation cues unrelated to motion per se challenge notions of modularity.
Parts of Visual Form: Psychophysical Aspects
A partitioning theory for visual form based on two types of parts that is based on a pair of negative curvature minima is proposed, suggesting that there are high levels of both intrasubject and intersubject consistency and that a large majority of the perceived parts do in fact correspond to the parts computed on the basis of the model.
Hierarchical structure in perceptual representation
Perceptual Organization and the Representation of Natural Form
Representation and recognition of the spatial organization of three-dimensional shapes
  • D. Marr, H. Nishihara
  • Computer Science
    Proceedings of the Royal Society of London. Series B. Biological Sciences
  • 1978
The human visual process can be studied by examining the computational problems associated with deriving useful information from retinal images. In this paper, we apply this approach to the problem
Preattentive Object Files: Shapeless Bundles of Basic Features