logo
banner

Journals & Publications

Publications Papers

Papers

Robust Offline Handwritten Character Recognition through Exploring Writer-Independent Features under the Guidance of Printed Data
Jul 10, 2018Author:
PrintText Size A A

 Title: Robust Offline Handwritten Character Recognition through Exploring Writer-Independent Features under the Guidance of Printed Data

Authors: Zhang, YP; Liang, S; Nie, S; Liu, WJ; Peng, SY  

Author Full Names: Zhang, Yaping; Liang, Shan; Nie, Shuai; Liu, Wenju; Peng, Shouye  

Source: PATTERN RECOGNITION LETTERS, 106 20-26; 10.1016/j.patrec.2018.02.006 APR 15 2018  

Language: English  

Abstract: Deep convolutional neural networks have made great progress in recent handwritten character recognition (HCR) by learning discriminative features from large amounts of labeled data. However, the large variance of handwriting styles across writers is still a big challenge to the robust HCR. To alleviate this issue, an intuitional idea is to extract writer-independent semantic features from handwritten characters, while standard printed characters are writer-independent stencils for handwritten characters. They could be used as prior knowledge to guide models to exploit writer-independent semantic features for HCR. In this paper, we propose a novel adversarial feature learning (AFL) model to incorporate the prior knowledge of printed data and writer-independent semantic features to improve the performance of HCR on limited training data. Different from available handcrafted features methods, the proposed AFL model exploits writer-independent semantic features automatically, and standard printed data as prior knowledge is learnt objectively. Systematic experiments on MNIST and CASIA-HWDB show that the proposed model is competitive with the state-of-the-art methods on the offline HCR task. (c) 2018 Elsevier B.V. All rights reserved.  

ISSN: 0167-8655  

eISSN: 1872-7344  

IDS Number: GB8KT  

Unique ID: WOS:000429325500004

*Click Here to View Full Record