Rozpoznawanie kształtów w sekwencjach wizyjnych z zastosowaniem algorytmu wstecznej propagacji błędów

• Autorzy: Głowacz A. , Głowacz W.

Warianty tytułu

EN

Shape recognition of film sequence with application of backpropagation algorithm

• Języki publikacji: PL

Abstrakty

PL

Przedstawiono nowe podejście do automatycznego rozpoznawania kształtów. Podejście to jest oparte na algorytmie wstecznej propagacji błędów. Badania przeprowadzono dla sekwencji filmu. Wyniki badań potwierdzają dużą skuteczność sieci neuronowej w rozpoznawaniu kształtów dla sekwencji wizyjnych.

EN

A new approach to automatic shape recognition is presented. This approach is based on backpropagation neural network. Investigations of the shape recognition were carried out for film sequences. Results of investigations with application of backpropagation neural network show that shape recognition efficiency is very high.

Słowa kluczowe

PL

filtr; identyfikacja; sieć neuronowa; rozpoznawanie; trening

EN

filter; identification; neural network; recognition; shape; training

• Wydawca: Wydawnictwa AGH
• Czasopismo: Automatyka / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie
• Rocznik: 2008
• Tom: T. 12, z. 1
• Strony: 41--54
• Opis fizyczny: Bibliogr. 25 poz., rys., wykr.

Twórcy

autor

Głowacz A.

• Katedra Automatyki, Akademia Górniczo-Hutnicza w Krakowie

autor

Głowacz W.

• Katedra Automatyki, Akademia Górniczo-Hutnicza w Krakowie

Bibliografia

• [1] Ahn S.J., Rauh W., Recknagel M., Geometrie Fitting of Line, Plane, Circle, Sphere, and Ellipse. Proc. of 6. ABW-Workshop Optische 3D-Formerfassung (Esslingen, Germany, 25-26 January, 1999), Technical Academy Esslingen, 1999.
• [2] Anderson J.A., An Introduction to Neural Networks. Ist ed., MIT Press, 1995.
• [3] Belongie S., Malik J., Puzicha J., Shape Context: A New Descriptor for Shape Matching and Object Recognition. Advances in Neural Information Processing Systems 13: Proc. 2000 Conf., T.K. Leen, T.G. Dietterich D.E., Tresp V., 2001, 831-837.
• [4] Chauvin Y., Rumelhart D.E., Backpropagation: Theory, Architectures, and Applications. Hillsdale, NJ: Erlbaum, 1995.
• [5] Cootes T., Cooper D., Taylor C, Graham J., Active Shape Models - Their training and Application. Computer Vision and Image Understanding (CVIU), vol. 61, no. 1, Jan. 1995, 38-59.
• [6] Fausett L.V., Fundamentals of Neural Networks: Architectures, Algorithms, and Applications. Englewood Cliffs, NJ: Prentice-Hall, 1994.
• [7] Gavrila D., Philomin V., Real-Time Object Detection for Smart Fehicles. Proc. Conf. Computer Vision, 1999, 87-93.
• [8] Girosi F., Jones M., Poggio T., Regularization Theory and Neural Networks Architectures. Neural Computation, vol. 7, no. 2, 1995, 219-269.
• [9] He Y., Kundu A., 2-D Shape Classification Using Hidden Markov Model. IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 11, Nov. 1991, 1172-1184.
• [10] Hirose Y, Yamashita K., Hijiya S., Back-propagation algorithm which varies the number of hidden units. Neural Networks, vol. 4, no. 1, 1991, 61-66.
• [11] Golden R.M., Mathematical Methods for Neural Network analysis and Design. MIT Press, 1996.
• [12] Johnson A.H., Hebert M., Recognizing Objects by Matching Oriented Points. Proc. IEEE Conf. Computer Vision and Pattern Recognition, 1997, 684-689.
• [13] Johnson A., Bron L., Brussee P., Irene de Goede, Hoogland S., Learning from Mistakes. Proceedings of Human System Interaction, 1-3 November 2000, Maastricht, Nederlands, 235-239
• [14] Kothari B., Paya B., Esat I., Machinery fault diagnostics using direct encoding graph syntax for optimizing artificial neural network structure. Proc. 1996 3rd Biennial Joint Conf. Engineering Systems Design and Analysis, ESDA, Part 7 (of 9). New York: ASME, 1996, 205-210.
• [15] Lanitis A., Taylor C.J., Cootes T.F., A Generic System for Classifying Fariable Objects Using Flexible Template Matching. Proc. British Machine Vision Conf., vol. 1, 1993, 329-338.
• [16] Leung T., Malik J., Contour continuity in region based image segmentation. Lecture Notes in Computer Science, 1406, 1998, 544-559.
• [17] Liu H.-C, Srinath M.D., Partial Shape Classification Using Contour Matching in Distance Transformation. IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 11, Nov. 1990, 1072-1078.
• [18] Malik J., Belongie S., Leung T.K., Shi J., Contour and Texture Analysis for Image Segmentation. International Journal of Computer Vision, 43(1), 2001, 7-27.
• [19] Persoon E., Fu K., Shape Discrimination Using Fourier Descriptors. IEEE Trans. Systems, Man and Cybernetics, vol. 7, no. 3, Mar 1977, 170-179.
• [20] Prokop R.J., Reeves A.P., A Survey of Moment-Based Techniques for Unoccluded Object Representation and Recognition. CVGIP: Graphical Models and Image Processing, vol. 54, no. 5, pp. 438^60, Sept. 1992.
• [21] Skaf A., David B., Descotes-Genon B., Binder Z., General approach to man-machine system design: ergonomie and technical specification of actions. Proceedings of Human System Interaction, 1-3 November 2000, Maastricht, Nederlands, 355-367.
• [22] Sekita I., Kurita T, Otsu N., Complex Autoregressive Model for Shape Recognition. IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 4, Apr. 1992, 489-496.
• [23] Shen J., Castan S., An optimal linear operator for step edge detection. Computer Vision, Graphics, and Image Processing: Graphical Models and Understanding, 54(2), 1992, 112-133.
• [24] Williams C.K., Combining Deformable Models and Neural Networks for Hand-Printed Digit Recognition. Dept. Computer Science, Univ. of Toronto, 1994 (PhD Thesis).
• [25] http://www.jens-langner.de/lrecog/