Recognition by Functional Parts

Abstract We present an approach to function-based object recognition that reasons about the functionality of an object's intuitive parts. We extend the popular "recognition by parts" shape recognition framework to support "recognition by functional parts," by combining a set of functional primitives and their relations with a set of abstract volumetric shape primitives and their relations. Previous approaches have relied on more global object features, often ignoring the problem of object segmentation and thereby restricting themselves to range images of unoccluded scenes. We show how these shape primitives and relations can be easily recovered from superquadric ellipsoids which, in turn, can be recovered from either range or intensity images of occluded scenes, Furthermore, the proposed framework supports both unexpected (bottom-up) object recognition and expected (top-down) object recognition, We demonstrate the approach on a simple domain by recognizing a restricted class of hand-tools from 2-D images.

[1]  Barr,et al.  Superquadrics and Angle-Preserving Transformations , 1981, IEEE Computer Graphics and Applications.

[2]  Prasanna G. Mulgaonkar,et al.  Matching 'sticks, plates and blobs' objects using geometric and relational constraints , 1984, Image and Vision Computing.

[3]  Irving Biederman,et al.  Human image understanding: Recent research and a theory , 1985, Comput. Vis. Graph. Image Process..

[4]  Alex Pentland,et al.  Perceptual Organization and the Representation of Natural Form , 1986, Artif. Intell..

[5]  Dimitris N. Metaxas,et al.  Dynamic 3D models with local and global deformations: deformable superquadrics , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[6]  Kevin W. Bowyer,et al.  Generic recognition through qualitative reasoning about 3-D shape and object function , 1991, CVPR.

[7]  L. Stark,et al.  Dissertation Abstract , 1994, Journal of Cognitive Education and Psychology.

[8]  Dimitris N. Metaxas,et al.  Dynamic 3D Models with Local and Global Deformations: Deformable Superquadrics , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Sven Dickinson,et al.  Using qualitative shape to constrain deformable model fitting , 1992, Other Conferences.

[10]  Azriel Rosenfeld,et al.  3-D Shape Recovery Using Distributed Aspect Matching , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Azriel Rosenfeld,et al.  From volumes to views: An approach to 3-D object recognition , 1992, CVGIP Image Underst..

[12]  Sven J. Dickinson,et al.  Integration of quantitative and qualitative techniques for deformable model fitting from orthographic, perspective, and stereo projections , 1993, 1993 (4th) International Conference on Computer Vision.

[13]  Dmitry B. Goldgof,et al.  Function-based recognition from incomplete knowledge of shape , 1993 .

[14]  Lawrence O. Hall,et al.  Methods for Combination of Evidence in Function-Based 3-D Object Recognition , 1993, Int. J. Pattern Recognit. Artif. Intell..

[15]  Kevin W. Bowyer,et al.  Function-based generic recognition for multiple object categories , 1994 .