Abstract
A model based two-dimensional object recognition system capable of performing under occlusion and geometric transformation is described in this paper. The system is based on the concept of associative search using overlapping local features. During the training phase, the local features are hashed to set up the associations between the features and models. In the recognition phase, the same hashing procedure is used to retrieve associations that participate in a voting process to determine the identity of the shape. Two associative retrieval techniques for discrete and continuous features, respectively, are described in the paper. The performance of the system is studied using a test set of 1,000 shapes that are corrupted versions of 100 models in the shape database. It is shown that the incorporation of a verification phase to confirm the retrieved associations can provide zero error performance with a small reject rate.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ayache N and Faugeras OD (1986) HYPER: a new approach for the recognition and positioning of twodimensional objects, IEEE Trans. Pattern Analysis Machine Intell. Vol. 8, No. 1, pp. 44–54
Bentley JL (1975) Multidimensional binary search trees used for associative searching, Communications of the ACM, Vol. 18, no. 9, pp. 509–517
Bhanu B and Faugeras OD (1984) Shape matching of twodimensional objects, IEEE Trans. Pattern Anal. and Machine Intell., Vol. 6, pp. 137–156
Bolles RC and Cain RA (1982) Recognizing and locating partially visible objects: the local feature focus method, Int. J. Robotics Res., Vol. 1, No. 2, pp. 57–82
Davis LS (1979) Shape matching using relaxation techniques, IEEE Trans. Pattern Anal. and Machine Intell., Vol. 1, pp. 60–72
Friedman JH, Bentley JL and Finkel RA (1977) An algorithm for finding best matches in logarithmic expected time, ACM Trans. Math. Software, Vol. 3, no. 3, pp. 209–226
Friedman JH, Baskett F and Shustek LJ (1975) An algorithm for finding nearest neighbors, IEEE Trans. on Comp., Vol. C-24, pp. 1000–1006
Fukunaga K and Narendra PM (1975) A branch and bound algorithm for computing k-nearest neighbors, IEEE Trans. on Comp., Vol. C-24, pp. 750–753
Grimson WEL and Lozano-Perez (1984) Model based recognition and localization from sparse range or tactile data, Int'l Journal or Robotics Research, Vol. 3, pp. 3–35
Hu MK (1962) Visual pattern recognition by moment invariants, IRE Trans. Information Theory, Vol. 8, pp. 179–187
Kalvin A, Schonberg E, Schwartz JT and Sharir M (1986) Two-dimensional model-based boundary matching using footprints, Int'l J. Robotics Res., Vol. 5, pp. 38–55
Knoll TF and Jain RC (1986) recognizing partially visible objects using feature indexed hypotheses, IEEE J. Robotics Automat., Vol. 2, No. 1, pp. 3–13
Kohonen T and Reuhkala E (1978) A very fast associative method for the recognition and correction of misspelt words based on redundant hash addressing, Proc. Fourth Int'l Joint Conf. on Pattern Recog., Tokyo, Japan, pp. 807–809
Kohonen T (1984) Self-Organization and Associative Memory, Springer-Verlag, New York
Lamdan Y, Schwartz JT and Wolfson HJ (1988) On recognition of 3-D objects from 2-D images, Proc. of IEEE Int'l Conf. on Robotics and Automation, Philadelphia, pp. 1407–1413
Lamdan Y and Wolfson HJ (1988) Geometric hashing: a general and efficient model-based recognition scheme, Proc. Second Int'l Conf. on Computer Vision, Tampa, Florida, pp. 238–249
Leu JG and Chen L (1988) Polygonal approximation of 2-D shapes through boundary merging, Pattern Recog. Lett., Vol. 7, pp. 231–238
McKee JW and Aggarwal JK (1977) Computer recognition of partial views of curved objects, IEEE Trans. Comput., Vol. 26, pp. 790–800
Mehrotra R and Grosky WI (1989) Shape matching utilizing indexed hypotheses generation and testing, IEEE Trans. Robotics Automat., Vol. 5, No. 1, pp. 70–77
O'Rourke J and Sloan KR Jr. (1984) Dynamic quantization: Two adaptive data structures for multidimensional spaces, IEEE Trans. Pattern Anal. and Machine Intell., Vol. 6, pp. 266–280
Sarvarayudu GPR and Sethi IK (1983) Walsh descriptors for polygonal curves, Pattern Recognition, Vol. 16, pp. 327–336
Selfridge OG (1958) Pandemonium: a paradigm for learning, mechanization of thought process, Proc. of a Symposium held at National Physical Lab., London, pp. 513–526
Sethi IK (1981) A fast algorithm for recognizing nearest neighbours, IEEE Trans. Systems Man, and Cyber., Vol. 11, pp. 245–248
Sethi IK and Ramesh N. (1989) 2-D Shape recognition using redundant hashing, Proc. SPIE Conf. on Intelligent Robots and Vision, Philadelphia, pp. 477–486
Stein F and Medioni G (1990) Efficient two dimensional object recognition, Proc. of Int'l Conf. on Pattern Recog., Atlantic City, New Jersey, pp. 13–17
Turney JL Mudge TN and Volz RA (1985) Recognizing partially occluded parts, IEEE Trans Pattern Analysis Machine Intell., Vol. 7, No. 6, pp. 410–421
Zahn CT and Roskies RZ (1972) Fourier descriptors for plane closed curves, IEEE Trans. Comput., Vol. 21, pp. 269–281
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Sethi, I.K., Ramesh, N. Local association based recognition of two-dimensional objects. Machine Vis. Apps. 5, 265–276 (1992). https://doi.org/10.1007/BF01212715
Issue Date:
DOI: https://doi.org/10.1007/BF01212715