Statistical strategy for object class recognition using part detectors

This paper presents a method for the recognition of object classes once parts have been detected. The recognition task is formulated as a graph problem searching for the characteristic geographical arrangements of (possibly missing) parts. The objective function is Bayesian maximum a posteriori estimation, integrating the image likelihood as a posteriori probability of the part detectors. The variability in the arrangement of object parts is captured by a Gaussian distribution after translation normalization. By employing two special properties of a Gaussian distribution, we are able to deal with missing parts situation where the chosen origin is not detected. We use an A∗ algorithm to find the optimal solution for the graph search problem. Experiments are performed on both synthetic and real data to demonstrate good results and fast performance of the recognition.

[1]  Donald Geman,et al.  An Active Testing Model for Tracking Roads in Satellite Images , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Joseph A. O'Sullivan,et al.  Automatic target recognition organized via jump-diffusion algorithms , 1997, IEEE Trans. Image Process..

[3]  D L Streiner,et al.  An Introduction to Multivariate Statistics , 1993, Canadian journal of psychiatry. Revue canadienne de psychiatrie.

[4]  Andrew Blake,et al.  A probabilistic contour discriminant for object localisation , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[5]  Anuj Srivastava,et al.  Probability Models for Clutter in Natural Images , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Alan L. Yuille,et al.  An A* perspective on deterministic optimization for deformable templates , 2000, Pattern Recognit..

[7]  Arnold W. M. Smeulders,et al.  A casestudy in performance analysis of recognition of graphical signs. Detecting Arrows , 2001 .

[8]  Dennis Koelma,et al.  Efficient applications in user transparent parallel image processing , 2002, Proceedings 16th International Parallel and Distributed Processing Symposium.

[9]  Marcel Worring,et al.  Searching in document images: what does the appearance of a document tell us about what it means? , 2001 .

[10]  William Grimson,et al.  Object recognition by computer - the role of geometric constraints , 1991 .

[11]  Marco Aiello,et al.  Document understanding for a broad class of documents , 2002, Int. J. Document Anal. Recognit..

[12]  Joost van de Weijer,et al.  Fast Anisotropic Gauss Filtering , 2002, ECCV.

[13]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[14]  James S. Duncan,et al.  Boundary Finding with Parametrically Deformable Models , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Timothy F. Cootes,et al.  Training Models of Shape from Sets of Examples , 1992, BMVC.

[16]  K. Mardia,et al.  General shape distributions in a plane , 1991, Advances in Applied Probability.

[17]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  van Marie-Colette Lieshout,et al.  Recognition of overlapping objects using Markov spatial processes , 1991 .

[19]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[20]  Arnold W. M. Smeulders,et al.  Strings: Variational Deformable Models of Multivariate Ordered Features , 2001 .

[21]  Pietro Perona,et al.  Unsupervised Learning of Models for Recognition , 2000, ECCV.

[22]  Takeo Kanade,et al.  Neural Network-Based Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  David E. Booth,et al.  Analysis of Incomplete Multivariate Data , 2000, Technometrics.

[24]  Song-Chun Zhu,et al.  Prior Learning and Gibbs Reaction-Diffusion , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Dan Roth,et al.  Learning a Sparse Representation for Object Detection , 2002, ECCV.

[26]  Pietro Perona,et al.  Recognition of planar object classes , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[27]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[28]  A.W.M. Smeulders,et al.  Requirements for generic grouping in vision and an algorithm , 2001 .

[29]  Tomaso A. Poggio,et al.  Example-Based Learning for View-Based Human Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[31]  D. Kendall.  A Survey of the Statistical Theory of Shape , 1989 .