Scene Text Analysis using Deep Belief Networks

This paper focuses on the recognition and analysis of text embedded in scene images using Deep learning. The proposed approach uses deep learning architectures for automated higher order feature extraction, thereby improving classification accuracies in comparison to handcrafted features used traditionally. Exhaustive experiments have been performed with Deep Belief Networks and Convolutional Deep Neural Networks with varied training algorithms like Contrastive Divergence, De-noising Score Matching and supervised learning algorithms such as logistic regression and Multi-layer perceptron. These algorithms have been validated on 4 standard datasets: Chars 74K English, Chars 74K Kannada, ICDAR 2003 Robust OCR dataset and SVT-CHAR dataset. The proposed network achieves improved recognition results on Chars74K English, Kannada and SVT-CHAR dataset in comparison to the state-of-art algorithms. For ICDAR 2003 dataset, the proposed network is marginally worse in comparison to Deep Convolutional networks. Although deep belief networks have been considerably used for several applications, according to the knowledge of the authors, this is the first paper to report scene text recognition using deep belief networks.

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

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

[3]  Tara N. Sainath,et al.  FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION Digital Object Identifier 10.1109/MSP.2012.2205597 , 2012 .

[4]  Allen R. Hanson,et al.  Scene Text Recognition Using Similarity and a Lexicon with Sparse Belief Propagation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Tapani Raiko,et al.  Improved Learning of Gaussian-Bernoulli Restricted Boltzmann Machines , 2011, ICANN.

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

[7]  Kai Wang,et al.  Word Spotting in the Wild , 2010, ECCV.

[8]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[9]  B. Schölkopf,et al.  Modeling Human Motion Using Binary Latent Variables , 2007 .

[10]  Ching Y. Suen,et al.  A trainable feature extractor for handwritten digit recognition , 2007, Pattern Recognit..

[11]  Zohra Saidane,et al.  Automatic Scene Text Recognition using a Convolutional Neural Network , 2007 .

[12]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

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

[14]  Andrew Y. Ng,et al.  Text Detection and Character Recognition in Scene Images with Unsupervised Feature Learning , 2011, 2011 International Conference on Document Analysis and Recognition.

[15]  Manik Varma,et al.  Character Recognition in Natural Images , 2009, VISAPP.

[16]  Andreas Dengel,et al.  ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images , 2011, 2011 International Conference on Document Analysis and Recognition.

[17]  Hartmut Neven,et al.  PhotoOCR: Reading Text in Uncontrolled Conditions , 2013, 2013 IEEE International Conference on Computer Vision.

[18]  Thomas Hofmann,et al.  Greedy Layer-Wise Training of Deep Networks , 2007 .

[19]  Tao Wang,et al.  End-to-end text recognition with convolutional neural networks , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[20]  C. V. Jawahar,et al.  Top-down and bottom-up cues for scene text recognition , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Frédo Durand,et al.  Learning to predict where humans look , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[22]  Kai Wang,et al.  End-to-end scene text recognition , 2011, 2011 International Conference on Computer Vision.

[23]  Dong Yu,et al.  Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[24]  C. V. Jawahar,et al.  Image Retrieval Using Textual Cues , 2013, 2013 IEEE International Conference on Computer Vision.

[25]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[26]  Jon Almazán,et al.  ICDAR 2013 Robust Reading Competition , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[27]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[28]  Jiri Matas,et al.  A Method for Text Localization and Recognition in Real-World Images , 2010, ACCV.

[29]  Yann LeCun,et al.  Regularization of Neural Networks using DropConnect , 2013, ICML.

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

[31]  Partha Pratim Roy,et al.  ICDAR 2011 Robust Reading Competition - Challenge 1: Reading Text in Born-Digital Images (Web and Email) , 2011, 2011 International Conference on Document Analysis and Recognition.

[32]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[33]  Philip H. S. Torr,et al.  Efficient discriminative learning of parametric nearest neighbor classifiers , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.