Hybrid CNN-GRU model for high efficient handwritten digit recognition

Recognition of handwritten digits is a challenging research topic in Optical Character Recognition (OCR) in recent years. In this paper, a hybrid model combining convolutional neural network (CNN) and gate recurrent units (GRU) is proposed, in which GRU is used to replace the CNN fully connected layer part to achieve high recognition accuracy with lower running time. In this model, the features of the original image are firstly extracted by the CNN, and then they are dynamically classified by the GRU. Experiment performed on MNIST handwritten digit dataset suggests that the recognition accuracy of 99.21% while the training time and testing time is only 57.91s and 3.54s, respectively.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  U. Ravi Babu,et al.  Handwritten Digit Recognition Using K-Nearest Neighbour Classifier , 2014, 2014 World Congress on Computing and Communication Technologies.

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

[4]  H. A. Khan,et al.  MCS HOG Features and SVM Based Handwritten Digit Recognition System , 2017 .

[5]  Mahdi Jampour,et al.  Efficient Handwritten Digit Recognition based on Histogram of Oriented Gradients and SVM , 2014 .

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

[7]  Monika Drewnik,et al.  SVM Kernel Configuration and Optimization for the Handwritten Digit Recognition , 2017, CISIM.

[8]  Ujjwal Bhattacharya,et al.  CNN based common approach to handwritten character recognition of multiple scripts , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[9]  Zoubin Ghahramani,et al.  A Theoretically Grounded Application of Dropout in Recurrent Neural Networks , 2015, NIPS.

[10]  Qiang Guo,et al.  Convolutional feature learning and Hybrid CNN-HMM for scene number recognition , 2016, Neurocomputing.

[11]  Szilárd Vajda,et al.  A Fast k-Nearest Neighbor Classifier Using Unsupervised Clustering , 2016, RTIP2R.

[12]  Vijay Patil,et al.  Handwritten English character recognition using neural network , 2011 .

[13]  Yu Zhang,et al.  Advances in Joint CTC-Attention Based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM , 2017, INTERSPEECH.

[14]  Tanya Makkar,et al.  Analogizing time complexity of KNN and CNN in recognizing handwritten digits , 2017, 2017 Fourth International Conference on Image Information Processing (ICIIP).

[15]  Putra Sumari,et al.  Digital Recognition using Neural Network , 2009 .

[16]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[17]  Wu-Sheng Lu.  Handwritten digits recognition using PCA of histogram of oriented gradient , 2017, 2017 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM).

[18]  Min Chen,et al.  An adaptive deep Q-learning strategy for handwritten digit recognition , 2018, Neural Networks.

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

[20]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..