Recognition of partially occluded shapes using a neural optimization network

• Autorzy: Banerjee B.
• Języki publikacji: EN

Abstrakty

EN

The current work presents an algorithm for recognition of partially occliided shapes in a cluttered scene The images are represented by a sequence of angles subtended at the corner points. The cost due to comparison between the input cluttered scene and the stored images is obtained from a cost function designed to storo the obtained information in the form of a cost matrix which is presented to the input of an optimization network. The parameters of the optimization network are determined so as, to minimize an energy function, the minima of which occur at the solutions of the problem. The results, as obtained in different domains (2D shapes and projected 3D shapes) with different degrees of occlusion, provide intereSting insights into the operation of the algorithm as well as avenues for future research.

Słowa kluczowe

EN

occlusion; angle coding; continuous Hopfield network; cost function; Liapunov energy function

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2004
• Tom: Vol. 13, No. 1/2
• Strony: 3--23
• Opis fizyczny: Bibliogr. 22 poz., il.

Twórcy

autor

Banerjee B.

• Labortory for AI Research, Dept. of Computer Science and Engineering The Ohio State University 395 Dreese Laboratory, 2015 Neil Ave, Columbus, OH 43210, USA,

Bibliografia

• [1] Attneave F.: Some informational aspects of visual perception. Psychology Review, 61(3), 183-193, 1954.
• [2] Freeman H.: On the encoding of arbitrary geometric configurations. IEEE Trans. Electr. Comput.. EC-10, 260-268, 1961.
• [3] Hopfield J. J.: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Nat. Acad. Sci. USA, Biophysics 81, 3088-3092, 1984.
• [4] Price K. E.: Matching closed contours. Proc. 7th Int. Conf. PR, 990-992, 1984.
• [5] Hopfield J. J., Tank D. W.: 'Neural' computation of decisions in optimization problems. Biolog. Cybern. 52, 141-152, 1985.
• [6] Tank D. W., Hopfield J. J.: Simple 'neural' optimization networks: An A/D converter, signal decision circuit and a linear programming circuit. IEEE Trans. Circuits Syst., CAS-33, 533-541, 1986.
• [7] Bhanu B., Ming J.: Recognition of occluded objects: A cluster structure algorithm. PR, 20(2), 199-211, 1987.
• [8] Brandt R. D., Wang Y., Laub A. J., Mitra S. K.: Alternative networks for solving the traveling salesman problem and the list matching problem. Proc. IEEE Int. Conf. Neural Networks, San Diego, CA, II-333-340, 1988.
• [9] Grimson W. E. L.: Object recognition by computer the role of geometric constraints. MIT Press. Cambridge, MA, 1990.
• [10] Ali M. K. M., Kamoun F.: Neural networks for shortest path computation and routing in computer networks. IEEE Trans. NN, 4(6), 1993.
• [11] Ansari N., Li K.: Landmark-based shape recognition by a modified Hopfield neural network. PR. 26(4), 531-542, 1993.
• [12] Protzel P. W., Palumbo D. L., Arras M. K.: Performance and fault-tolerance of neural networks for optimization. IEEE Trans. NN, 4(4), 1993.
• [13] Wiskott L., Malsburg C. v. d.: A neural system for the recognition of partially occluded objects in cluttered scenes. Intl. Journal PR&AI, 7(4), 935-948, 1993.
• [14] Kim J. H., Yoon S. H., Sohn K. H.: A robust boundary-based object recognition in occlusion environment by hybrid Hopfield neural networks. PR, 29, 2047-2060, 1996.
• [15] Liu T. L., Donahue M., Geiger D., Hummel R.: Image recognition with occlusions. Proc. European Conf. on Computer Vision (ECCV), Cambridge, UK, 1, 556-565, 1996.
• [16] Mokhtarian F.: Silhouette-based object recognition with occlusion through curvature scale space. Proc. European Conf. on Computer Vision (ECCV), Cambridge, UK, 1, 566-578, 1996.
• [17] Datta A., Pal T., Parui S. K.: A modified self-organizing neural net for shape extraction. Neuro-computing, 14, 3-14, 1997.
• [18] Kumar S., Segen J.: Gesture based 3D man-machine interaction using a single camera. IEEE Int. Conf on Multimedia Computing and Systems, 1, 1999.
• [19] Lai S. H.: Robust image matching under partial occlusion and spatially varying illumination change. CVIU, 78(1), 84-98, 2000.
• [20] Ramakrishnan S., Forte P.: MDL based Structural Interpretation of Images under Partial Occlusion. 12th British Machine Vision Conference, Manchester, UK, 2, 553-562, 2001.
• [21] Zhang Y., Kambhamettu C.: 3D Head Tracking under Partial Occlusion. PR, 35, 1545-1557, 2002.
• [22] Banerjee B.: A self-organizing auto-associative network for the generalized physical design of microstrip patches. IEEE Trans. Antennas and Propagation, 51(6), 1301-1306, 2003.