Robust offline handwritten character recognition through exploring writer-independent features under the guidance of printed data
Robust offline handwritten character recognition through exploring writer-independent features under the guidance of printed data
复制标题
通过在印刷数据的指导下探索独立于书写者的特征，实现鲁棒的离线手写字符识别
DOI：
10.1016/j.patrec.2018.02.006
复制
发表时间：
2018
影响因子：
5.1
通讯作者：
Peng Shouye
中科院分区：
文献类型：
--
作者：
Zhang Yaping;Liang Shan;Nie Shuai;Liu Wenju;Peng Shouye
深度卷积神经网络通过从大量标记数据中学习区分特征，在最近的手写字符识别（HCR）中取得了很大进展。然而，手写体风格的巨大差异仍然是一个很大的挑战，强大的HCR。为了缓解这个问题，一个直观的想法是从手写字符中提取与书写者无关的语义特征，而标准印刷字符是手写字符的与书写者无关的语义特征。它们可以作为先验知识来指导模型开发与作者无关的HCR语义特征。在本文中，我们提出了一种新的对抗性特征学习（AFL）模型，将打印数据的先验知识和与作者无关的语义特征结合起来，以提高HCR在有限训练数据上的性能。与现有的手工特征提取方法不同，AFL模型自动提取与作者无关的语义特征，并客观地学习标准印刷数据作为先验知识。在MNIST和CASIA-HWDB上的系统实验表明，该模型在离线HCR任务上与现有方法相比具有较强的竞争力。
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.