Toward high-performance online HCCR: a CNN approach with DropDistortion, path signature and spatial stochastic max-pooling

Abstract

This paper presents an investigation of several techniques that increase the accuracy of online handwritten Chinese character recognition (HCCR). We propose a new training strategy named DropDistortion to train a deep convolutional neural network (DCNN) with distorted samples. DropDistortion gradually lowers the degree of character distortion during training, which allows the DCNN to better generalize. Path signature is used to extract effective features for online characters. Further improvement is achieved by employing spatial stochastic max-pooling as a method of feature map distortion and model averaging. Experiments were carried out on three publicly available datasets, namely CASIA-OLHWDB 1.0, CASIA-OLHWDB 1.1, and the ICDAR2013 online HCCR competition dataset. The proposed techniques yield state-of-the-art recognition accuracies of 97.67%, 97.30%, and 97.99%, respectively.

10 pages, 7 figures

References in corpus (2)

• Fractional Max-Pooling
• Improved Deep Convolutional Neural Network For Online Handwritten Chinese Character Recognition using Domain-Specific Knowledge

Cited by in corpus (3)

• Detecting early signs of depressive and manic episodes in patients with bipolar disorder using the signature-based model
• Offline Writer Identification based on the Path Signature Feature
• Design of a Very Compact CNN Classifier for Online Handwritten Chinese Character Recognition Using DropWeight and Global Pooling