Research on a handwritten character recognition algorithm based on an extended nonlinear kernel residual network

• Zheheng Rao,
• Chunyan Zeng,
• Minghu Wu,
• Zhifeng Wang,
• Nan Zhao,
• Min Liu Xiangkui Wan,

Vol. 12, No. 1, January 30, 2018
10.3837/tiis.2018.01.020, Download Paper (Free):

• unsupervised priori algorithm
• “high-capacity” convolution layers
• residual network
• multi-level quick link
• Dropout layer

Abstract

Although the accuracy of handwritten character recognition based on deep networks has been shown to be superior to that of the traditional method, the use of an overly deep network significantly increases time consumption during parameter training. For this reason, this paper took the training time and recognition accuracy into consideration and proposed a novel handwritten character recognition algorithm with newly designed network structure, which is based on an extended nonlinear kernel residual network. This network is a non-extremely deep network, and its main design is as follows:(1) Design of an unsupervised apriori algorithm for intra-class clustering, making the subsequent network training more pertinent; (2) presentation of an intermediate convolution model with a pre-processed width level of 2;(3) presentation of a composite residual structure that designs a multi-level quick link; and (4) addition of a Dropout layer after the parameter optimization. The algorithm shows superior results on MNIST and SVHN dataset, which are two character benchmark recognition datasets, and achieves better recognition accuracy and higher recognition efficiency than other deep structures with the same number of layers.

Statistics

Cite this article