Recognition of printed Urdu ligatures using convolutional neural networks

Abstract. We present a holistic technique for recognition of text in cursive scripts using printed Urdu ligatures as a case study. Convolutional neural networks (CNNs) are trained on high-frequency ligature clusters for feature extraction and classification. A query ligature presented to the system is first divided into primary and secondary ligatures that are separately recognized and later associated in a postprocessing step to recognize the complete ligature. Experiments are carried out using transfer learning on pretrained networks as well as by training a network from scratch. The technique is evaluated on ligatures extracted from two standard databases of printed Urdu text, Urdu printed text image (UPTI) and Center of Language Engineering (CLE), as well as by combining the ligatures of the two datasets. The system realizes high recognition rates of 97.81% and 89.20% on the UPTI and CLE databases, respectively.

[1]  Joshua Powell.  Pedestrian Detection with Convolutional Neural Networks , 2017 .

[2]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[3]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[4]  Sarmad Hussain,et al.  Segmentation Based Urdu Nastalique OCR , 2013, CIARP.

[5]  Imran Siddiqi,et al.  Classification of Urdu Ligatures Using Convolutional Neural Networks - A Novel Approach , 2017, 2017 International Conference on Frontiers of Information Technology (FIT).

[6]  David Bouchain.  Character Recognition Using Convolutional Neural Networks , 2006 .

[7]  Sarmad Hussain,et al.  Adapting Tesseract for Complex Scripts: An Example for Urdu Nastalique , 2014, 2014 11th IAPR International Workshop on Document Analysis Systems.

[8]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[9]  U. Pal,et al.  Recognition of printed Urdu script , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[10]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Junichi Kanai,et al.  Improving optical character recognition accuracy using adaptive image restoration , 1996, J. Electronic Imaging.

[12]  Srikanta Patnaik,et al.  Optical Character Recognition System for Urdu (Naskh Font) Using Pattern Matching Technique , 2009 .

[13]  L. Deng,et al.  The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web] , 2012, IEEE Signal Processing Magazine.

[14]  Sarmad Hussain,et al.  Framework of Urdu Nastalique Optical Character Recognition System , 2014 .

[15]  Muhammad Imran Razzak,et al.  Urdu Nasta’liq text recognition system based on multi-dimensional recurrent neural network and statistical features , 2017, Neural Computing and Applications.

[16]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Shehzad Khalid,et al.  Segmentation-free optical character recognition for printed Urdu text , 2017, EURASIP J. Image Video Process..

[18]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[19]  Shehzad Khalid,et al.  Recognition of Urdu ligatures - a holistic approach , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[20]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[21]  Koen E. A. van de Sande,et al.  Selective Search for Object Recognition , 2013, International Journal of Computer Vision.

[22]  Gurpreet Singh Lehal.  Ligature Segmentation for Urdu OCR , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[23]  Abdul Wahab,et al.  Optical character recognition system for Urdu , 2010, 2010 International Conference on Information and Emerging Technologies.

[24]  Mohammad Alshayeb,et al.  KHATT: Arabic Offline Handwritten Text Database , 2012, 2012 International Conference on Frontiers in Handwriting Recognition.

[25]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Sarmad Hussain,et al.  Segmentation Free Nastalique Urdu OCR , 2010 .

[27]  Xiaojie Wang,et al.  Offline Urdu Nastaleeq optical character recognition based on stacked denoising autoencoder , 2017, China Communications.

[28]  Arjun Sharma,et al.  Adapting off-the-shelf CNNs for word spotting & recognition , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[29]  Muhammad Imran Razzak,et al.  Evaluation of cursive and non-cursive scripts using recurrent neural networks , 2015, Neural Computing and Applications.

[30]  Imran Siddiqi,et al.  Urdu Nastaliq recognition using convolutional-recursive deep learning , 2017, Neurocomputing.

[31]  Chein-I Chang,et al.  Automated system for text detection in individual video images , 2003, J. Electronic Imaging.

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

[33]  David S. Doermann,et al.  Text Detection and Recognition in Imagery: A Survey , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Imran Siddiqi,et al.  Offline cursive Urdu-Nastaliq script recognition using multidimensional recurrent neural networks , 2016, Neurocomputing.

[35]  M. Pechwitz,et al.  IFN/ENIT: database of handwritten arabic words , 2002 .

[36]  Somaya Al-Máadeed,et al.  QUWI: An Arabic and English Handwriting Dataset for Offline Writer Identification , 2012, 2012 International Conference on Frontiers in Handwriting Recognition.

[37]  Sarmad Hussain,et al.  Context Sensitive Shape-Substitution in Nastaliq Writing System: Analysis and Formulation , 2007 .

[38]  Saad Bin Ahmed,et al.  Offline Printed Urdu Nastaleeq Script Recognition with Bidirectional LSTM Networks , 2013, 2013 12th International Conference on Document Analysis and Recognition.

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

[40]  Sarmad Hussain,et al.  Nastalique segmentation-based approach for Urdu OCR , 2015, International Journal on Document Analysis and Recognition (IJDAR).

[41]  Junaid Tariq,et al.  Softconverter: A novel approach to construct OCR for printed Urdu isolated characters , 2010, 2010 2nd International Conference on Computer Engineering and Technology.

[42]  Faisal Shafait,et al.  A segmentation-free approach to Arabic and Urdu OCR , 2013, Electronic Imaging.

[43]  Awais Adnan,et al.  OCR For Printed Urdu Script Using Feed Forward Neural Network , 2007 .

[44]  Guang Liu,et al.  Ligature based Urdu Nastaleeq sentence recognition using gated bidirectional long short term memory , 2017, Cluster Computing.

[45]  Awais Adnan,et al.  Urdu Nastaleeq Optical Character Recognition , 2007 .

[46]  Gurpreet Singh Lehal.  Choice of recognizable units for URDU OCR , 2012, DAR '12.

[47]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[48]  Stefan Winkler,et al.  Deep Learning for Emotion Recognition on Small Datasets using Transfer Learning , 2015, ICMI.