A Probabilistic Approach to Geometric Hashing Using Line Features

Most current object recognition algorithms assume reliable image segmentation, which in practice is often not available. We examine the combination of the Hough transform with a variation of geometric hashing as a technique for model-based object recognition in seriously degraded single intensity images. Prior work on the performance analysis of geometric hashing has focused on point features, which can be hard to detect in an environment affected by serious noise and occlusion. This paper uses line features to compute recognition invariants in a potentially more robust way. We investigate the statistical behavior of these line features analytically. Various viewing transformations, which 2-D (or flat 3-D) objects undergo during image formation, are considered. For the case of affine transformations, which are often suitable substitutes for more general perspective transformations, we show experimentally that the technique is noise resistant and can be used in highly occluded environments.

[1]  Micha Sharir,et al.  Identification of Partially Obscured Objects in Two and Three Dimensions by Matching Noisy Characteristic Curves , 1987 .

[2]  W. Daniel Hillis,et al.  The connection machine , 1985 .

[3]  Drew McDermott,et al.  Introduction to artificial intelligence , 1986, Addison-Wesley series in computer science.

[4]  Olivier D. Faugeras,et al.  HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Isidore Rigoutsos,et al.  A Bayesian Approach to Model Matching with Geometric Hashing , 1995, Computer Vision and Image Understanding.

[6]  W. Eric L. Grimson,et al.  On the Sensitivity of the Hough Transform for Object Recognition , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  I. Rigoutsos,et al.  Implementation of geometric hashing on the Connection Machine , 1991, [1991 Proceedings] Workshop on Directions in Automated CAD-Based Vision.

[8]  F. Dehne,et al.  Hypercube algorithms for parallel processing of pointer-based quadtrees , 1995 .

[9]  Rodney A. Brooks,et al.  Model-Based Three-Dimensional Interpretations of Two-Dimensional Images , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[11]  Robert M. Haralick,et al.  Optimal affine-invariant point matching , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[12]  Anil K. Jain,et al.  3D object recognition using invariant feature indexing of interpretation tables , 1992, CVGIP Image Underst..

[13]  O DudaRichard,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972 .

[14]  J. Schwartz,et al.  Object recognition by geometric hashing , 1989 .

[15]  Trevor N. Mudge,et al.  Efficient Recognition of Partially Visible Objects Using a Logarithmic Complexity Matching Technique , 1989, Int. J. Robotics Res..

[16]  W. Eric L. Grimson,et al.  Gaussian error models for object recognition , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Robert A. Hummel,et al.  Massively parallel model matching: geometric hashing on the Connection Machine , 1992, Computer.

[18]  H. Barrow,et al.  Computational vision , 1981, Proceedings of the IEEE.

[19]  Ingemar J. Cox,et al.  TWO DIMENSIONAL OPTIMUM EDGE RECOGNITION USING MATCHED AND WIENER FILTERS FOR MACHINE VISION. , 1987 .

[20]  David G. Lowe,et al.  Three-Dimensional Object Recognition from Single Two-Dimensional Images , 1987, Artif. Intell..

[21]  Frank C. D. Tsai.  Geometric hashing with line features , 1994, Pattern Recognit..

[22]  Felix Klein.  Elementary Mathematics from an Advanced Standpoint: Geometry , 1941 .

[23]  Yehezkel Lamdan,et al.  On the error analysis of 'geometric hashing' , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[24]  George C. Stockman,et al.  Object recognition and localization via pose clustering , 1987, Comput. Vis. Graph. Image Process..

[25]  Charles R. Dyer,et al.  Model-based recognition in robot vision , 1986, CSUR.

[26]  Esther M. Arkin,et al.  An efficiently computable metric for comparing polygonal shapes , 1991, SODA '90.

[27]  Peter E. Hart,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[28]  Jyh-Jong Liu,et al.  Geometric hashing with attributed features , 1994, Proceedings of 1994 IEEE 2nd CAD-Based Vision Workshop.

[29]  Isidore Rigoutsos.  Massively parallel Bayesian object recognition , 1992 .

[30]  Edith Schonberg,et al.  Two-Dimensional, Model-Based, Boundary Matching Using Footprints , 1986 .

[31]  Ramesh C. Jain,et al.  Three-dimensional object recognition , 1985, CSUR.

[32]  Azriel Rosenfeld,et al.  An Application of Relaxation Labeling to Line and Curve Enhancement , 1977, IEEE Transactions on Computers.

[33]  Yehezkel Lamdan,et al.  On recognition of 3-D objects from 2-D images , 2011, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[34]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[35]  David G. Lowe,et al.  Perceptual Organization and Visual Recognition , 2012 .

[36]  D. W. Thompson,et al.  Three-dimensional model matching from an unconstrained viewpoint , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[37]  Josef Kittler,et al.  A survey of the hough transform , 1988, Comput. Vis. Graph. Image Process..

[38]  Thomas Risse,et al.  Hough transform for line recognition: Complexity of evidence accumulation and cluster detection , 1989, Comput. Vis. Graph. Image Process..

[39]  W. Eric L. Grimson,et al.  On the sensitivity of geometric hashing , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[40]  Jiawei Hong,et al.  Recognize The Similarity Between Shapes Under Affine Transformation , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[41]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[42]  Ruud M. Bolle,et al.  Invariant feature matching in parameter space with application to line features , 1991, Optics & Photonics.

[43]  Yehezkel Lamdan,et al.  Geometric Hashing: A General And Efficient Model-based Recognition Scheme , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[44]  Frans C. A. Groen,et al.  3D object recognition from 2D images using geometric hashing , 1992, Pattern Recognit. Lett..

[45]  P. Zsombor-Murray,et al.  Elementary Mathematics from an Advanced Standpoint , 1940, Nature.

[46]  Nicholas Ayache,et al.  New developments on geometric hashing for curve matching , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[47]  Robert Hummel,et al.  A model-based three-dimensional object recognition system using geometric hashing with attributed features , 1996 .

[48]  Alfred V. Aho,et al.  The Design and Analysis of Computer Algorithms , 1974 .

[49]  R. Bolles,et al.  Recognizing and Locating Partially Visible Objects: The Local-Feature-Focus Method , 1982 .

[50]  L. W. Tucker,et al.  Object recognition using the Connection Machine , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[51]  Thomas O. Binford,et al.  Survey of Model-Based Image Analysis Systems , 1982 .

[52]  W. Eric L. Grimson,et al.  Localizing Overlapping Parts by Searching the Interpretation Tree , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.