{"title":"Integrating Low and High Level Object Recognition Steps by Probabilistic Networks","authors":"Andr\u00e1s Barta, Istv\u00e1n Vajk","volume":7,"journal":"International Journal of Computer and Information Engineering","pagesStart":2113,"pagesEnd":2123,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/15671","abstract":"
In pattern recognition applications the low level segmentation and the high level object recognition are generally considered as two separate steps. The paper presents a method that bridges the gap between the low and the high level object recognition. It is based on a Bayesian network representation and network propagation algorithm. At the low level it uses hierarchical structure of quadratic spline wavelet image bases. The method is demonstrated for a simple circuit diagram component identification problem.<\/p>\r\n","references":"[1] Barta A, Vajk I., Document Image Analysis by Probabilistic Network\r\nand Circuit Diagram Extraction, Informatica, An International Journal\r\nof Computing and Informatics, 29, pp. 291-301, 2005\r\n[2] Barta A., Vajk I, Processing Circuit Diagrams with Belief Network and\r\nIntelligent Agents., Transactions on Information Science and\r\nApplications, Issue 9, Vol. 2, September, pp. 1321-1329, 2005\r\n[3] Draper B., Hanson H., Riseman E., Knowledge-Directed Vision:\r\nControl, Learning and Integration,http:\/\/www.cs.colostate.edu\/ ~draper\/\r\npublications\/draper_ieee96.pdf Proceedings of the IEEE, 84(11), pp.\r\n1625-1637, 1996\r\n[4] Neopolitan R. E., Learning Bayesian networks, Pearson Prentice Hall,\r\n2004\r\n[5] Pearl, J., Probabilistic Reasoning in Intelligent Systems: Networks of\r\nPlausible Interference, Morgan Kauffmann Publishers, 1988\r\n[6] Okazaki A., Kondo T., Mori K., Tsunekawa S., Kawamoto E., An\r\nAutomatic Circuit Diagram Reader With Loop-Structure-Based Symbol\r\nRecognition, IEEE Trans. Pattern Analysis and Machine Intelligence,\r\nVol. 10, No. 3, pp. 331-341, May 1988\r\n[7] Takatsuka M., Caelli T. M., West G. A. W., Venkatesh S., An\r\napplication of \u00d4\u00c7\u00ff\u00d4\u00c7\u00ffagent-oriented-- techniques to symbolic matching and\r\nobject recognition, Pattern Recognition Letters 23, pp. 419-429, 2002\r\n[8] Siddiqi K., Subrahmonia J., Cooper D., Kimia B.B., Part-Based\r\nBayesian Recognition Using Implicit Polynomial Invariants,\r\nProceedings of the 1995 International Conference on Image Processing\r\n(ICIP), pp. 360-363, 1995\r\n[9] Storkey A.J., Williams C.K.I., Image Modeling with Position-Encoding\r\nDynamic Trees, IEEE Trans. Pattern Analysis and Machine Intelligence,\r\nVol. 25, No. 7, July pp. 859-871, 2003\r\n[10] Zou Song-Chun, Statistical Modeling and Conceptualization of Visual\r\nPatterns, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.\r\n25, No. 6, June, pp 691-712, 2003\r\n[11] Mallat S., A Wavelet Tour of Signal Processing, Academic Press, 1999\r\n[12] Burrus C. S, Introduction to Wavelets and Wavelet Transforms, Prentice\r\nHall, 1998\r\n[13] Freeman T.W., Adelson E.H., The Design and Use of Steerable Filters,\r\nIEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 13, No. 9,\r\nSeptember, pp 891-906, 1991\r\n[14] Sung J., Bang S.J., Choi S., A Bayesian network classifier and\r\nhierarchical Gabor features for Handwritten Numeral Recognition,\r\nPattern Recognition Letters, 27. pp 66-75, 2006\r\n[15] Deng S., Lati S., Regentova E., Document segmentation using\r\npolynomial spline wavelets, Pattern Recognition, 34. pp. 2533-2545,\r\n2001\r\n[16] Olshausen B.A, Anderson C.H., Van Essen D.C., A neurobiological\r\nmodel of visual attention and invariant pattern recognition based\r\ndynamic routing information, The Journal of Neuroscience, 13(11),\r\n4700-4719, 1993","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 7, 2007"}