Recognition of Geons by Parametric Deformable Contour Models

This paper presents a novel approach to the detection and recognition of qualitative parts like geons from real 2D intensity images. Previous works relied on semi-local properties of either line drawings or good region segmentation. Here, in the framework of Model-Based Optimisation, whole geons or substantial sub-parts are recognised by fitting parametric deformable contour models to the edge image by means of a Maximum A Posteriori estimation performed by Adaptive Simulated Annealing, accounting for image clutter and limited occlusions. A number of experiments, carried out both on synthetic and real edge images, are presented.

[1]  David G. Lowe,et al.  Fitting Parameterized Three-Dimensional Models to Images , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Anil K. Jain,et al.  Obtaining generic parts from range data using a multiview representation , 1992, Defense, Security, and Sensing.

[3]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

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

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

[6]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[7]  Ruzena Bajcsy,et al.  Recovery of Parametric Models from Range Images: The Case for Superquadrics with Global Deformations , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Pascal Fua,et al.  Objective functions for feature discrimination: applications to semiautomated and automated feature extraction , 1989 .

[9]  I. Biederman,et al.  Dynamic binding in a neural network for shape recognition. , 1992, Psychological review.

[10]  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.

[11]  Martin D. Levine,et al.  Recovering parametric geons from multiview range data , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[12]  John R. Kender,et al.  What is a 'Degenerate' View? , 1987, IJCAI.

[13]  Robert Bergevin.  Primal access recognition of visual objects , 1989 .