A Bayesian network for combining descriptors: application to symbol recognition

In this paper, we propose a descriptor combination method, which enables to improve significantly the recognition rate compared to the recognition rates obtained by each descriptor. This approach is based on a probabilistic graphical model. This model also enables to handle both discrete and continuous-valued variables. In fact, in order to improve the recognition rate, we have combined two kinds of features: discrete features (corresponding to shape measures) and continuous features (corresponding to shape descriptors). In order to solve the dimensionality problem due to the large dimension of visual features, we have adapted a variable selection method. Experimental results, obtained in a supervised learning context, on noisy and occluded symbols, show the feasibility of the approach.

[1]  Clément Chatelain,et al.  A simple one class classifier with rejection strategy : application to symbol classification , 2007 .

[2]  Yunde Jia,et al.  Probabilistic classification based image regions labeling , 2004, ICIG.

[3]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Laurent Wendling,et al.  Symbol Recognition Using a 2-class Hierarchical Model of Choquet Integrals , 2007 .

[5]  Josef Kittler,et al.  Floating search methods in feature selection , 1994, Pattern Recognit. Lett..

[6]  Shih-Fu Chang,et al.  A knowledge engineering approach for image classification based on probabilistic reasoning systems , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

[7]  Laurent Wendling,et al.  Technical symbols recognition using the two-dimensional Radon transform , 2002, Object recognition supported by user interaction for service robots.

[8]  Rafael Rumí,et al.  Supervised classification using probabilistic decision graphs , 2009, Comput. Stat. Data Anal..

[9]  Sergio Escalera,et al.  Report on the Third Contest on Symbol Recognition , 2007, GREC.

[10]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[11]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[12]  Hatice Gunes,et al.  Maximum-likelihood dimensionality reduction in gaussian mixture models with an application to object classification , 2008, 2008 19th International Conference on Pattern Recognition.

[13]  Ernest Valveny,et al.  On the Combination of Ridgelets Descriptors for Symbol Recognition , 2007, GREC.

[14]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[15]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[16]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .

[17]  Nir Friedman,et al.  Bayesian Network Classifiers , 1997, Machine Learning.

[18]  Su Yang.  Symbol Recognition via Statistical Integration of Pixel-Level Constraint Histograms: A New Descriptor , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Paul L. Rosin.  Measuring rectangularity , 1999, Machine Vision and Applications.

[20]  David G. Stork,et al.  Pattern Classification , 1973 .

[21]  Ernest Valveny,et al.  Optimal Classifier Fusion in a Non-Bayesian Probabilistic Framework , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[23]  Ernest Valveny,et al.  A Review of Shape Descriptors for Document Analysis , 2007 .

[24]  Josep Lladós,et al.  Symbol Recognition by Error-Tolerant Subgraph Matching between Region Adjacency Graphs , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[26]  Guojun Lu,et al.  Generic Fourier descriptor for shape-based image retrieval , 2002, Proceedings. IEEE International Conference on Multimedia and Expo.

[27]  Mickaël Coustaty,et al.  On the Joint Use of a Structural Signature and a Galois Lattice Classifier for Symbol Recognition , 2007, GREC.

[28]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[29]  Michael I. Jordan.  Learning in Graphical Models , 1999, NATO ASI Series.

[30]  Michael I. Jordan.  Graphical Models , 2003 .

[31]  Guojun Lu,et al.  Review of shape representation and description techniques , 2004, Pattern Recognit..

[32]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[33]  Sergio Escalera,et al.  Hand Drawn Symbol Recognition by Blurred Shape Model Descriptor and a Multiclass Classifier , 2007, GREC.

[34]  M. Teague.  Image analysis via the general theory of moments , 1980 .

[35]  Thierry,et al.  Dimensionality reduction and visualization of interval and fuzzy data : a survey , 2007 .

[36]  James M. Keller,et al.  A fuzzy K-nearest neighbor algorithm , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[37]  Dong-Gyu Sim,et al.  A modified Zernike moment shape descriptor invariant to translation, rotation and scale for similarity-based image retrieval , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

[38]  Kun Zhang,et al.  Symbol Recognition with Kernel Density Matching , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[39]  Judea Pearl,et al.  A Computational Model for Causal and Diagnostic Reasoning in Inference Systems , 1983, IJCAI.

[40]  R. Tibshirani,et al.  Least angle regression , 2004, math/0406456.

[41]  David A. Landgrebe,et al.  A survey of decision tree classifier methodology , 1991, IEEE Trans. Syst. Man Cybern..

[42]  Laurent Wendling,et al.  Symbol Recognition Using a 2-class Hierarchical Model of Choquet Integrals , 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

[43]  Ernest Valveny,et al.  A Review of Shape Descriptors for Document Analysis , 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

[44]  Robert M. Haralick,et al.  A Statistical, Nonparametric Methodology for Document Degradation Model Validation , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[45]  Sven Sandow,et al.  A Decision-Theoretic Motivation for L1-Regularized Maximum Likelihood Modeling , 2005 .