Object Recognition Using Shape-from-Shading

Investigates whether surface topography information extracted from intensity images using a shape-from-shading (SFS) algorithm can be used for the purposes of 3D object recognition. We consider how curvature and shape-index information delivered by this algorithm can be used to recognize objects based on their surface topography. We explore two contrasting object recognition strategies. The first of these is based on a low-level attribute summary and uses histograms of curvature and orientation measurements. The second approach is based on the structural arrangement of constant shape-index maximal patches and their associated region attributes. We show that region curvedness and a string ordering of the regions according to size provides recognition accuracy of about 96 percent. By polling various recognition schemes, including a graph matching method, we show that a recognition rate of 98-99 percent is achievable.

[1]  David J. Kriegman,et al.  What is the set of images of an object under all possible lighting conditions? , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Chitra Dorai,et al.  Shape Spectrum Based View Grouping and Matching of 3D Free-Form Objects , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  E. Rouy,et al.  A viscosity solutions approach to shape-from-shading , 1992 .

[4]  Benoit Huet,et al.  Fuzzy relational distance for large-scale object recognition , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[5]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Alfred M. Bruckstein,et al.  Tracking Level Sets by Level Sets: A Method for Solving the Shape from Shading Problem , 1995, Comput. Vis. Image Underst..

[7]  Michael J. Brooks,et al.  The variational approach to shape from shading , 1986, Comput. Vis. Graph. Image Process..

[8]  Anil K. Jain,et al.  Three-Dimensional Object Recognition Systems , 1993 .

[9]  Jan J. Koenderink,et al.  Solid shape , 1990 .

[10]  Edwin R. Hancock,et al.  Region-Based Object Recognition Using Shape-from-Shading , 2000, ECCV.

[11]  Benoit Huet,et al.  Line Pattern Retrieval Using Relational Histograms , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Georgy L. Gimel'farb,et al.  On retrieving textured images from an image database , 1996, Pattern Recognit..

[13]  Edwin R. Hancock,et al.  3D surface topography from intensity images , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[14]  Alex Pentland,et al.  A simple algorithm for shape from shading , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Edwin R. Hancock,et al.  New Constraints on Data-Closeness and Needle Map Consistency for Shape-from-Shading , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  A. Tversky.  Features of Similarity , 1977 .

[17]  J. Koenderink,et al.  Surface perception in pictures , 1992, Perception & psychophysics.

[18]  Edwin R. Hancock,et al.  Needle map recovery using robust regularizers , 1999, Image Vis. Comput..

[19]  Alfred M. Bruckstein,et al.  Shape From Shading , 2006, Handbook of Mathematical Models in Computer Vision.

[20]  Chitra Dorai,et al.  COSMOS - A Representation Scheme for 3D Free-Form Objects , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  P. Dupuis,et al.  An Optimal Control Formulation and Related Numerical Methods for a Problem in Shape Reconstruction , 1994 .

[22]  Edwin R. Hancock,et al.  Histogram-based object recognition using shape-from-shading , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[23]  Andrea J. van Doorn,et al.  Surface shape and curvature scales , 1992, Image Vis. Comput..