A hierarchical feature learning for isolated Farsi handwritten digit recognition using sparse autoencoder

In recent years, the recognition of Farsi handwritten digits is drawing increasing attention. Feature extraction is a very important stage in handwritten digit recognition systems. Recently deep feature learning got promising results in English handwritten digit recognition, though there are very few papers in this area for Farsi handwritten digits. The contribution of this paper is to propose a new framework utilizing a two layer sparse autoencoder for feature learning directly from data and using the learned weights for feature extraction. In the classification stage of our proposed framework Softmax regression is applied. This recognition method is applied to Farsi handwritten digits in the HODA dataset. The experimental results support our claim that use of deep feature learning as feature extraction stage improves the performance compared with conventional methods.

[1]  Ehsanollah Kabir,et al.  Introducing a very large dataset of handwritten Farsi digits and a study on their varieties , 2007, Pattern Recognit. Lett..

[2]  Ali Aghagolzadeh,et al.  A New Pattern for Handwritten Persian/Arabic Digit Recognition , 2007 .

[3]  Karim Faez,et al.  Language-Based Feature Extraction Using Template-Matching in Farsi/Arabic Handwritten Numeral Recognition , 2007 .

[4]  Mohammad Rahmati,et al.  Recognition of Persian handwritten digits using image profiles of multiple orientations , 2004, Pattern Recognit. Lett..

[5]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[6]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[7]  K. Faez,et al.  Recognition of isolated handwritten Farsi/Arabic alphanumeric using fractal codes , 2004, 6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004..

[8]  Karim Faez,et al.  Recognition of handwritten Persian/Arabic numerals by shadow coding and an edited probabilistic neural network , 1995, Proceedings., International Conference on Image Processing.

[9]  Karim Faez,et al.  Recognition of isolated handwritten Persian/Arabic characters and numerals using support vector machines , 2003, 2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718).

[10]  Davar Giveki,et al.  Farsi/Arabic handwritten digit recognition based on ensemble of SVD classifiers and reliable multi-phase PSO combination rule , 2012, International Journal on Document Analysis and Recognition (IJDAR).

[11]  Saeed Mozaffari,et al.  Structural decomposition and statistical description of Farsi/Arabic handwritten numeric characters , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[12]  Zhenghao Chen,et al.  On Random Weights and Unsupervised Feature Learning , 2011, ICML.

[13]  Reza Ebrahimpour,et al.  Hand Written Digit Recognition by Multiple Classifier Fusion based on Decision Templates Approach , 2009 .

[14]  Chee Seng Chan,et al.  A New Approach to Feature Selection in Handwritten Farsi/Arabic Character Recognition , 2012, 2012 International Conference on Advanced Computer Science Applications and Technologies (ACSAT).

[15]  Honglak Lee,et al.  An Analysis of Single-Layer Networks in Unsupervised Feature Learning , 2011, AISTATS.

[16]  Ching Y. Suen,et al.  A novel hybrid CNN-SVM classifier for recognizing handwritten digits , 2012, Pattern Recognit..

[17]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Mark W. Schmidt,et al.  Optimizing Costly Functions with Simple Constraints: A Limited-Memory Projected Quasi-Newton Algorithm , 2009, AISTATS.

[19]  Honglak Lee,et al.  Sparse deep belief net model for visual area V2 , 2007, NIPS.

[20]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[21]  Fatemeh Sharifizadeh,et al.  A Modified Decision Templates Method for Persian Handwritten Digit Recognition , 2012 .

[22]  M. Dehghan,et al.  Farsi handwritten character recognition with moment invariants , 1997, Proceedings of 13th International Conference on Digital Signal Processing.