Effect of ensemble classifier composition on offline cursive character recognition

In this paper we present novel ensemble classifier architectures and investigate their influence for offline cursive character recognition. Cursive characters are represented by feature sets that portray different aspects of character images for recognition purposes. The recognition accuracy can be improved by training ensemble of classifiers on the feature sets. Given the feature sets and the base classifiers, we have developed multiple ensemble classifier compositions under four architectures. The first three architectures are based on the use of multiple feature sets whereas the fourth architecture is based on the use of a unique feature set. Type-1 architecture is composed of homogeneous base classifiers and Type-2 architecture is constructed using heterogeneous base classifiers. Type-3 architecture is based on hierarchical fusion of decisions. In Type-4 architecture a unique feature set is learned by a set of homogeneous base classifiers with different learning parameters. The experimental results demonstrate that the recognition accuracy achieved using the proposed ensemble classifier (with best composition of base classifiers and feature sets) is better than the existing recognition accuracies for offline cursive character recognition.

[1]  Ashraf A. Kassim,et al.  Dual classifier system for handprinted alphanumeric character recognition , 1998, Pattern Analysis and Applications.

[2]  George D. C. Cavalcanti,et al.  An ensemble classifier for offline cursive character recognition using multiple feature extraction techniques , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[3]  Nikos Fakotakis,et al.  Handwritten word recognition based on structural characteristics and lexical support , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[4]  Ching Y. Suen,et al.  A genetic framework using contextual knowledge for segmentation and recognition of handwritten numeral strings , 2007, Pattern Recognit..

[5]  Daniel Hernández-Lobato,et al.  An Analysis of Ensemble Pruning Techniques Based on Ordered Aggregation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[7]  Brijesh Verma,et al.  Binary Segmentation with Neural Validation for Cursive Handwriting Recognition , 2009, 2009 International Joint Conference on Neural Networks.

[8]  Sargur N. Srihari.  Handwriting Recognition, Automatic , 2006 .

[9]  Robert Sabourin,et al.  Fusing High- and Low-Level Features for Handwritten Word Recognition , 2006 .

[10]  Francesco Camastra,et al.  Offline Cursive Character Challenge: a New Benchmark for Machine Learning and Pattern Recognition Algorithms. , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[11]  Nafiz Arica,et al.  An overview of character recognition focused on off-line handwriting , 2001, IEEE Trans. Syst. Man Cybern. Syst..

[12]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[13]  R. Schapire.  The Strength of Weak Learnability , 1990, Machine Learning.

[14]  Xin Yao,et al.  Non-uniform Layered Clustering for Ensemble Classifier Generation and Optimality , 2010, ICONIP.

[15]  R. Manmatha,et al.  Boosted decision trees for word recognition in handwritten document retrieval , 2005, SIGIR '05.

[16]  R. Polikar,et al.  Ensemble based systems in decision making , 2006, IEEE Circuits and Systems Magazine.

[17]  Ioannis Pratikakis,et al.  Efficient Off-Line Cursive Handwriting Word Recognition , 2006 .

[19]  Ping Zhang,et al.  Reliable recognition of handwritten digits using a cascade ensemble classifier system and hybrid features , 2006 .

[20]  Francesco Camastra,et al.  Cursive character recognition by learning vector quantization , 2001, Pattern Recognit. Lett..

[21]  Paul D. Gader,et al.  Fusion of multiple handwritten word recognition techniques , 2001, Pattern Recognit. Lett..

[22]  Loris Nanni,et al.  FuzzyBagging: A novel ensemble of classifiers , 2006, Pattern Recognit..

[23]  Francesco Camastra,et al.  A SVM-based cursive character recognizer , 2007, Pattern Recognit..

[24]  Fatos T. Yarman-Vural,et al.  Optical Character Recognition for Cursive Handwriting , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Ludmila I. Kuncheva,et al.  Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy , 2003, Machine Learning.

[26]  Luiz Eduardo Soares de Oliveira,et al.  Automatic Recognition of Handwritten Numerical Strings: A Recognition and Verification Strategy , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Brijesh Verma,et al.  Over-segmentation and Neural Binary Validation for cursive handwriting recognition , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[28]  Mohamed S. Kamel,et al.  A generalized adaptive ensemble generation and aggregation approach for multiple classifier systems , 2009, Pattern Recognit..

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

[30]  Ashfaqur Rahman,et al.  A novel ensemble classifier approach using weak classifier learning on overlapping clusters , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[31]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[32]  Hiromichi Fujisawa,et al.  Forty years of research in character and document recognition - an industrial perspective , 2008, Pattern Recognit..

[33]  Ron Kohavi,et al.  Bias Plus Variance Decomposition for Zero-One Loss Functions , 1996, ICML.