Building Fast and Compact Convolutional Neural Networks for Offline Handwritten Chinese Character Recognition

Understand

Like other problems in computer vision, offline handwritten Chinese character recognition (HCCR) has achieved impressive results using convolutional neural network (CNN)-based methods.

• However, larger and deeper networks are needed to deliver state-of-the-art results in this domain.
• Such networks intuitively appear to incur high computational cost, and require the storage of a large number of parameters, which renders them unfeasible for deployment in portable devices.
• To solve this problem, we propose a Global Supervised Low-rank Expansion (GSLRE) method and an Adaptive Drop-weight (ADW) technique to solve the problems of speed and storage capacity.