A Deep Network with Composite Residual Structure for Handwritten Character Recognition

This paper presents a new deep network (non – very deep network) with composite residual for handwritten character recognition. The main network design is as follows: (1) Introduces an unsupervised FCM clustering algorithm to preprocess the experimental data. (2) By exploiting a composite residual structure the multilevel shortcut connection is proposed which is more suitable for the learning of residual. (3) In order to solve the problem of overfitting and time-consuming for training the network parameters, a dropout layer is added after the completion of all convolution operations of each extended nonlinear residual kernel. Comparing with general deep network structures of same deep on handwritten character MNIST database, the proposed algorithm shows better recognition accuracy and higher recognition efficiency.

[1]  Rubem Pereira,et al.  Future internet: trends and challenges , 2015, Int. J. Space Based Situated Comput..

[2]  P. Mahesha,et al.  Support vector machine-based stuttering dysfluency classification using GMM supervectors , 2015, Int. J. Grid Util. Comput..

[3]  G. Varaprasad,et al.  Design and development of efficient algorithm for mobile ad hoc networks using cache , 2011, Int. J. Space Based Situated Comput..

[4]  Fei Yin,et al.  Online and offline handwritten Chinese character recognition: Benchmarking on new databases , 2013, Pattern Recognit..

[5]  Cheng-Lin Liu,et al.  Contextual text/non-text stroke classification in online handwritten notes with conditional random fields , 2014, Pattern Recognit..

[6]  Hui Li,et al.  Privacy-preserving logistic regression outsourcing in cloud computing , 2013, Int. J. Grid Util. Comput..

[7]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[8]  Jianshe Kang,et al.  Research on Fault Diagnosis Method Using Improved Multi-Class Classification Algorithm and Relevance Vector Machine , 2015, Int. J. Inf. Technol. Web Eng..

[9]  Dhiya Al-Jumeily,et al.  Using adaptive neural networks to provide self-healing autonomic software , 2015, Int. J. Space Based Situated Comput..

[10]  Abdullah Alamareen,et al.  Image Mosaicing Using Binary Edge Detection Algorithm in a Cloud-Computing Environment , 2016, Int. J. Inf. Technol. Web Eng..

[11]  Tao Lin,et al.  Explore the Use of Handwriting Information and Machine Learning Techniques in Evaluating Mental Workload , 2016, Int. J. Technol. Hum. Interact..

[12]  Yoshua Bengio,et al.  Online and offline handwritten Chinese character recognition: A comprehensive study and new benchmark , 2016, Pattern Recognit..