Multi-column Deep Neural Network for Offline Arabic Handwriting Recognition

In recent years Deep Neural Networks (DNNs) have been successfully applied to several pattern recognition filed. For example, Multi-Column Deep Neural Networks (MCDNN) achieve state of the art recognition rates on Chinese characters database. In this paper, we utilized MCDNN for Offline Arabic Handwriting Recognition (OAHR). Through several settings of experiments using the benchmarking IFN/ENIT Database, we show incremental improvements of the words recognition comparable to approaches used Deep Belief Network (DBN) or Recurrent Neural Network (RNN.) Lastly, we compare our best result to those of previous state-of-the-arts.

[1]  Mohamed A. Ali,et al.  Arabic Handwritten Characters Classification Using Learning Vector Quantization Algorithm , 2008, ICISP.

[2]  Alessandro Vinciarelli,et al.  A survey on off-line Cursive Word Recognition , 2002, Pattern Recognit..

[3]  Dan Ciresan,et al.  Multi-Column Deep Neural Networks for offline handwritten Chinese character classification , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[4]  Abdurazzag Ali Aburas,et al.  Arabic handwriting recognition: Challenges and solutions , 2008, 2008 International Symposium on Information Technology.

[5]  Fei Yin,et al.  ICDAR 2011 Chinese Handwriting Recognition Competition , 2011, 2011 International Conference on Document Analysis and Recognition.

[6]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[7]  Sargur N. Srihari,et al.  An Assessment of Arabic Handwriting Recognition Technology , 2012 .

[8]  Jürgen Schmidhuber,et al.  Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks , 2008, NIPS.

[9]  Venu Govindaraju,et al.  The Role of Holistic Paradigms in Handwritten Word Recognition , 2009 .

[10]  Zaher Al Aghbari,et al.  Gabor Wavelet Recognition Approach for Off-Line Handwritten Arabic Using Explicit Segmentation , 2013, IP&C.

[11]  María José Castro Bleda,et al.  Holistic cursive word recognition based on perceptual features , 2007, Pattern Recognit. Lett..

[12]  Abdel Belaïd,et al.  Towards Arabic Handwritten Word Recognition via Probabilistic Graphical Models , 2014, 2014 14th International Conference on Frontiers in Handwriting Recognition.

[13]  Jun Sun,et al.  Handwritten Character Recognition by Alternately Trained Relaxation Convolutional Neural Network , 2014, 2014 14th International Conference on Frontiers in Handwriting Recognition.

[14]  Yann LeCun,et al.  Convolutional networks and applications in vision , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[15]  Monji Kherallah,et al.  Improving MDLSTM for Offline Arabic Handwriting Recognition Using Dropout at Different Positions , 2016, ICANN.

[16]  Ching Y. Suen,et al.  Legal amount recognition based on the segmentation hypotheses for bank check processing , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[17]  Chafic Mokbel,et al.  Combining Slanted-Frame Classifiers for Improved HMM-Based Arabic Handwriting Recognition , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Jürgen Schmidhuber,et al.  Multi-column deep neural network for traffic sign classification , 2012, Neural Networks.

[19]  Monji Kherallah,et al.  Deep Learning for Feature Extraction of Arabic Handwritten Script , 2015, CAIP.

[20]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.