Intelligent Work Order Recognition System Based on End-to-End Deep Neural Network

As the largest public service provider in the world, State Grid Corporation of China (SGCC) generates huge amounts of data every day, much of which are paper work order in offline businesses. Paper work orders greatly affect office efficiency and reduce the data processing capacity. To solve this problem, technicians of SGCC implement an intelligent work order recognition system. This system based on deep neural network such as CNN, CRNN, uses graphical morphology analysis, segmentation, recognizes handwritten numerals, handwritten Chinese characters and printed characters automatically, imports various paper work orders rapidly. In practice, the accuracy of handwritten numeral recognition is 96%, the accuracy of handwritten Chinese character recognition is 94%, the accuracy of printed character recognition is 99%. This system greatly improves the work order import efficiency of grass-roots staff.

[1]  Gui-Song Xia,et al.  Rotation-Sensitive Regression for Oriented Scene Text Detection , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[2]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Ernest Valveny,et al.  Word Spotting and Recognition with Embedded Attributes , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  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.

[5]  Jürgen Schmidhuber,et al.  Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks , 2006, ICML.

[6]  Ankush Gupta,et al.  Synthetic Data for Text Localisation in Natural Images , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Xiang Bai,et al.  An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[9]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[10]  Albert Gordo,et al.  Label Embedding: A Frugal Baseline for Text Recognition , 2015, International Journal of Computer Vision.

[11]  Ying Zhang,et al.  Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks , 2016, INTERSPEECH.

[12]  Lianwen Jin,et al.  Feature Enhancement Network: A Refined Scene Text Detector , 2017, AAAI.

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

[14]  Shitala Prasad,et al.  Using Object Information for Spotting Text , 2018, ECCV.

[15]  Alexander M. Rush,et al.  Image-to-Markup Generation with Coarse-to-Fine Attention , 2016, ICML.

[16]  Han Hu,et al.  WordSup: Exploiting Word Annotations for Character Based Text Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[17]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[18]  Andrew Zisserman,et al.  Deep Features for Text Spotting , 2014, ECCV.

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