Parts of recognition

@article{Hoffman1984PartsOR,
  title={Parts of recognition},
  author={Donald D. Hoffman and Whitman Richards},
  journal={Cognition},
  year={1984},
  volume={18},
  pages={65-96}
}
Evidence for boundary-specific grouping
Part Segmentation for Object Recognition
TLDR
An approach to object recognition is described in which the image is segmented into parts using two simple, biologically-plausible mechanisms: a filtering operation to produce a large set of potential object parts, followed by a new type of network that searches among these part hypotheses to produce the simplest, most likely description of the image's part structure.
Evidence for Boundary-speciic Grouping
TLDR
The results of psychophysical experiments suggest that the visual system relies on geometric properties of bounding contours such as closure and not on the texture of the two-dimensional regions they partition.
Human Integration of Shape Primitives
TLDR
It is discovered that the relevant dimensions describing global object shape, in this case, are related to simple geometric deformations, which has implications for the construction of computer vision systems that recognize large ensembles of objects.
Independent Processing of Parts and of Their Spatial Organization in Complex Visual Objects
TLDR
The additivity of the effects demonstrates that information on parts and information on spatial organization are processed independently in visual search, and support theories of complex visual object perception that assume a parsing of the stimulus into its higher-order constituents.
From discs to parts of visual form
...
...

References

SHOWING 1-10 OF 47 REFERENCES
Parts Description And Acquisition Using Vision
  • M. Brady
  • Computer Science
    Other Conferences
  • 1982
TLDR
Curved shapes are described in terms of smoothed local symmetries that combine features of generalized cylinders and the Symmetric Axis Transform to determine grasp points for a parallel jaw gripper.
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
Outlines of a theory of visual pattern recognition in animals and man
  • N. Sutherland
  • Computer Science
    Proceedings of the Royal Society of London. Series B. Biological Sciences
  • 1968
TLDR
This paper lists twelve conditions that must be fulfilled by a satisfactory theory of visual pattern recognition in animals and man and shows how the properties of such a language could account for the facts listed above.
The Interpretation of Visual Motion
This book uses the methodology of artificial intelligence to investigate the phenomena of visual motion perception: how the visual system constructs descriptions of the environment in terms of
The Interpretation of Visual Illusions
Vision is a process of inference. What you see when you look around depends not only on what is there to be seen but also on how your visual system organizes and interprets the images that fall on
The interpretation of a moving retinal image
It is shown that from a monocular view of a rigid, textured, curved surface it is possible, in principle, to determine the gradient of the surface at any point, and the motion of the eye relative to
The ACRONYM Model-Based Vision System
ACRONYM Is a model-based image understanding system. It demonstrates mechanisms for interpretation of images with generic object classes and generic viewing conditions, in a way that is
Decomposition of a visual scene into three-dimensional bodies
TLDR
This work considers visual scenes composed by the optical image of a group of bodies that can be treated as a two-dimensional array of numbers, or as a function of two variables.
The Shape of Smooth Objects and the Way Contours End
TLDR
It is argued that a general shape is conceived of as a conglomerate of convex (‘ovoid’) elementary shapes, these shapes act as ‘figure’ and the way they are glued together is treated as the—relatively unimportant—‘ground’.
...
...