A New Radical Based Approach to Offline Handwritten East-Asian Character Recognition
A New Radical Based Approach to Offline Handwritten East-Asian Character Recognition
复制标题
DOI：
--
复制
发表时间：
2006-10
期刊：
影响因子：
--
通讯作者：
K. Chellapilla;Patrice Y. Simard
中科院分区：
文献类型：
--
作者：
K. Chellapilla;Patrice Y. Simard
东亚汉字具有丰富的等级结构，每个汉字都有独特的偏旁空间排列。在本文中，我们提出了一种新的激进的方法，缩放神经网络（NN）识别器成千上万的东亚字符。所提出的离线字符识别器包括排列在图中的神经网络。每个神经网络是三种类型之一：一个激进的位置（RAL）识别器，一个网关，或组合器。每个偏旁神经网络都是一个卷积神经网络，用于处理整个字符图像并识别字符中特定位置的偏旁。示例位置包括左半部分、右半部分、上半部分、下半部分、左上象限、右下象限等。通过允许每个RAL分类器处理整个字符图像，完全避免了分割。Gater-NN减少了需要在运行时评估的NN的数量，并且组合器NN联合收割机组合RAL分类器输出以用于最终识别。该方法在包含来自3665个类的1340万个手写体汉字样本的真实数据集上进行了测试。实验结果表明，该方法具有良好的可扩展性，并实现了低错误率。
East-Asian characters possess a rich hierarchical structure with each character comprising a unique spatial arrangement of radicals (sub-characters). In this paper, we present a new radical based approach for scaling neural network (NN) recognizers to thousands of East-Asian characters. The proposed off-line character recognizer comprises neural networks arranged in a graph. Each NN is one of three types: a radical-at-location (RAL) recognizer, a gater, or a combiner. Each radical-atlocation NN is a convolutional neural network that is designed to processes the whole character image and recognize radicals at a specific location in the character. Example locations include left-half, right-half, top-half, bottom-half, left-top quadrant, bottom-right quadrant, etc. Segmentation is completely avoided by allowing each RAL classifier to process the whole character image. Gater-NNs reduce the number of NNs that need to be evaluated at runtime and combiner-NNs combine RAL classifier outputs for final recognition. The proposed approach is tested on a real-world dataset containing 13.4 million handwritten Chinese character samples from 3665 classes. Experimental results indicate that the proposed approach scales well and achieves a low error rate.