Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition
Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition
复制标题
使用全卷积循环网络学习空间语义上下文，用于在线手写中文文本识别
DOI：
10.1109/tpami.2017.2732978
复制
发表时间：
2018-08-01
影响因子：
23.6
通讯作者：
Lyons, Terry
中科院分区：
文献类型：
--
作者：
Xie, Zecheng;Sun, Zenghui;Lyons, Terry
联机手写中文文本识别是一个具有挑战性的问题，因为它涉及到大规模的字符集，歧义切分和可变长度的输入序列。在本文中，我们利用路径签名的出色能力，将在线笔尖轨迹转化为信息丰富的签名特征图，成功地捕获了具有强局部不变性和鲁棒性的笔划的分析和几何特性。提出了一种多空间上下文全卷积递归网络（MC-FCRN），利用签名特征图中的多个空间上下文，生成预测序列，同时完全避免了难以分割的问题。此外，隐式语言模型的开发，使预测的特征序列内的语义上下文的基础上进行预测，提供了一个新的视角，将词典的约束和先验知识的某种语言的识别过程。在两个标准基准数据集（Dataset-CASIA和Dataset-ICDAR）上进行的实验取得了出色的结果，正确率分别为97.50%和96.58%，明显优于文献中迄今为止报道的最佳结果。
Online handwritten Chinese text recognition (OHCTR) is a challenging problem as it involves a large-scale character set, ambiguous segmentation, and variable-length input sequences. In this paper, we exploit the outstanding capability of path signature to translate online pen-tip trajectories into informative signature feature maps, successfully capturing the analytic and geometric properties of pen strokes with strong local invariance and robustness. A multi-spatial-context fully convolutional recurrent network (MC-FCRN) is proposed to exploit the multiple spatial contexts from the signature feature maps and generate a prediction sequence while completely avoiding the difficult segmentation problem. Furthermore, an implicit language model is developed to make predictions based on semantic context within a predicting feature sequence, providing a new perspective for incorporating lexicon constraints and prior knowledge about a certain language in the recognition procedure. Experiments on two standard benchmarks, Dataset-CASIA and Dataset-ICDAR, yielded outstanding results, with correct rates of 97.50 and 96.58 percent, respectively, which are significantly better than the best result reported thus far in the literature.