Salience of visual parts

@article{Hoffman1997SalienceOV,
  title={Salience of visual parts},
  author={Donald D. Hoffman and Manish Singh},
  journal={Cognition},
  year={1997},
  volume={63},
  pages={29-78}
}
PART-BASED REPRESENTATIONS OF VISUAL SHAPE AND IMPLICATIONS FOR VISUAL COGNITION
Human vision organizes object shapes in terms of parts and their spatial relationships. Converging experimental evidence suggests that parts are computed rapidly and early in visual processing. We
Part-Based Representations of Visual Shape and Implications for Visual Cognition
Curvature and the visual perception of shape: theory on information along object boundaries and the minima rule revisited.
TLDR
This work proposes an alternative mathematical formulation for information measure of contour curvature that addresses issues of fundamental errors in Feldman and Singh's derivation and outlines a modified version of the minima rule relating to part segmentation using curvature in 3D shape.
Early computation of part structure: Evidence from visual search
TLDR
It is demonstrated that the visual system segments shapes into parts, using negative minima of curvature, and that it does so rapidly in early stages of visual processing.
Visual representation of contour and shape
TLDR
It is concluded that, as far as the visual representation of shape is concerned, contour geometry cannot ultimately be studied in isolation, but must be considered conjointly with region-based geometry.
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.
The visual system prioritizes locations near corners of surfaces (not just locations near a corner)
TLDR
The enhancement is not based on spatial aspects of the regions in the image, but critically depends on figure–ground stratification, supporting the link between the prioritization of corners and the representation of surface layout.
Information along contours and object boundaries.
TLDR
The authors show that for closed contours, segments of negative curvature literally carry greater information than do corresponding regions of positive curvature (i.e., concave segments), and extend Attneave's claim to incorporate the role of sign of curvature, not just magnitude of curvatures.
Perceptual representation of visible surfaces
TLDR
These findings indicate that randomly generated smooth surface patches contain perceptually salient landmarks that have a high degree of viewpoint invariance and are considered for the recognition of smooth surface patch and for the depiction of such surfaces in line drawings.
...
...

References

SHOWING 1-10 OF 96 REFERENCES
Parts of Visual Form: Psychophysical Aspects
TLDR
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.
Parts of Visual Objects: An Experimental Test of the Minima Rule
TLDR
Two different methods provide converging evidence, from two different methods, which supports Hoffman and Richards's minima rule, which divides three-dimensional shapes into parts at negative minima of curvature.
Parts of recognition
Parts of Visual Form: Computational Aspects
TLDR
Computational support for the limb-based and neck-based parts is presented by showing that they are invariant, robust, stable, and yield a hierarchy of parts.
Recognition-by-components: a theory of human image understanding.
TLDR
Recognition-by-components (RBC) provides a principled account of the heretofore undecided relation between the classic principles of perceptual organization and pattern recognition.
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.
Description of solid shape and its inference from occluding contours
TLDR
It is shown that the part boundaries of an object can be inferred from its occluding contours, at least up to a number of ambiguities.
The Concave Cusp as a Determiner of Figure—Ground
TLDR
Evidence is presented that figure—ground assignment can be determined solely on the basis of the concave cusp feature, and that the salience of the cusp derives from local geometry and not from adjacent contour convexity.
Feature analysis in early vision: evidence from search asymmetries.
TLDR
The results of a series of search experiments are interpreted as evidence that focused attention to single items or to groups is required to reduce background activity when the Weber fraction distinguishing the pooled feature activity with displayscontaining a target and with displays containing only distractors is too small to allow reliable discrimination.
...
...