Abstract
The importance of boundaries for shape decomposition into component parts has been discussed from different points of view by Koenderink and van Doorn (1982), and by Hoffman and Richards (1984). The former define part boundaries as parabolic contours, whereas the latter propose that part boundaries should be defined by contours of negative minima (or maxima) of principal curvature. In this article, building on aspects of both approaches, we develop a new method for shape decomposition. This method relies exclusively on global properties of the surface which are fully characterized by local surface properties. We propose that a useful parcellation of shapes into parts can be obtained by decomposing the shape boundary into the largest convex surface patches and the smallest nonconvex surface patches. The essential computational steps of this method are the following: (i) build initial parts from the largest locally convex patches, (ii) consider an initial part as a constituent part if it is essentially convex, and (iii) obtain the remaining constituent parts by merging adjacent initial parts generated by the largest locally convex and the smallest nonconvex patches of nearly the same sizes. The method is illustrated on both smooth and continuous shapes. We show that the decomposition of shapes into the largest convex patches aims to maximize the “thingness” in an object, and to minimize its “non-thingness”. The method is conducive to a natural parcellation of shapes into constituent parts useful for recognition and for inferring function.
Similar content being viewed by others
References
Bajcy R, Solina F (1987) Three dimensional object representation revisted. Proc First Int Conf Comput Vision: 231–241
Bartlett FC (1932) Remembering: a study in experimental and social psychology. Cambridge University Press, London New York
Bennett B, Hoffman D (1987) Shape decompositions for visual recognition: the role of transversality. In: Richards W, Ullman S (eds) Image understanding. MIT Press, Cambridge, pp 215–256
Biederman I (1985) Human image understanding recent research and a theory. Comp Vis Graph Imag Process 32:29–73
Binford TO (1971) Visual perception by computer. IEEE Conference on Systems and Control, Miami
Blum H (1973) Biological shape and visual science. J Theor Biol 38:205–287
Brady MJ (1983) Criteria for representations of shapes. In: Rosenfeld A, Hope B, Beck J (eds.) Human and machine vision. Academic Press, New York
Brady JM, Asada H (1984) Smoothed local symmetries and their implications. Int Robot Res 3
Brady JM, Ponce J, Yuille AL, Asada H (1985) Describing surfaces. Comp Vis Graph Imag Process
Faux ID, Pratt MJ (1978) Computational geometry for design and manufacture. Ellis Horwood Press
Gibson J (1979) The ecological approach to visual perception. Houghton Miflin, Boston
Gregory RL (1964) Stereoscopic shadow images. Nature (London) 193:1407–1408
Hilbert D, Cohn-Vossen S (1932) Anschauliche Geometrie. Springer, Berlin Heidelberg New York
Hoffman D, Richards W (1984) Parts of recognition. Cognition, pp 1865–1896
Horn BKPH (1986) Robot vision. McGraw-Hill, New York
Koenderink J (1987) An internal representation for solid shape based on the topological properties of the apparent contour. In: Richards W, Ullman S (eds) Image understanding, pp 257–285
Koenderink J, van Doorn A (1982) The shape of smooth objects and the way contours end. Perception 11:129–137
Marr D, Nishihara, HK (1978) Representation and recognition of the spatial organisation of three dimensional shapes. Proc R Soc London B 200:269–294
Pentland A (1986) Perceptual organization and the representation of natural form artificial intelligence 283:1–16
Pentland A (1987) Recognition by parts. First International Conference on Computer Vision, pp 612–621
Phillips T, Cannon R, Rosenfeld A (1986) Decomposition and approximation of three-dimesnional solids. Comput Vision, Graph, Image Process 33:307–317
Rosch E (1973) On the internal structure of perceptual and semantic categories. Cognitive development and the acquisition of language. Academic Press, New York
Rosenfeld A (1988) An overview of computer vision (keynote address). SPIE Apl Artif Intell 937:382–384
Serrat J (1982) Image analysis and mathematical morphology. Academic Press, New York
Vaina LM (1983) From shapes and movements to objects and actions. Synthese 54:3–37
Vaina LM, Jaulent MCh (1989) Object structure and action requirements: a compatibility model for functional recognition. Int J Intell Syst 7:73–92
Warrington EK, James M (1986) Visual object recognition in patients with right hemisphere lesions: axes or features? Perception 15:355–366
Warrington EK, Taylor AM (1973) The contribution of the right parietal lobe to object recognition. Cortex 9:152–164
Weatherburn CE (1927) Differential geometry of three dimensions. Cambridge University Press, Cambridge
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Vaina, L.M., Zlateva, S.D. The largest convex patches: A boundary-based method for obtaining object parts. Biol. Cybern. 62, 225–236 (1990). https://doi.org/10.1007/BF00198097
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00198097