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.
CITATION STYLE
Rao, Z., Zeng, C., Zhao, N., Liu, M., Wu, M., & Wang, Z. (2018). A deep network with composite residual structure for handwritten character recognition. In Lecture Notes on Data Engineering and Communications Technologies (Vol. 6, pp. 160–166). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-319-59463-7_16
Mendeley helps you to discover research relevant for your work.