计算机应用研究2016，Vol.33Issue(11)：3499-3502,4.DOI:10.3969/j.issn.1001--3695.2016.11.066
基于两方向动态时间规整的无分割手写汉字检测
Two-directional dynamic time warping based Chinese handwritten segmentation-free word spotting
摘要
Abstract
Large variety of Chinese characters and handwriting styles and the complexity of Chinese handwritten documents layout lead a huge challenging for the Chinese handwriting word spotting.This paper proposed a segmentation-free word spot-ting method for Chinese handwritten documents.Firstly,the method used the SIFT keypoint detector to locate the candidate keypoints in document images.Then it determined the candidate character regions by the keypoints’locations and the size of query word image.At last,it applied the two-directional dynamic time warping (DTW)to refine the candidate regions.The experimental results show that the proposed method can detect the query word in the document images with high mean average precision and the two-directional DTW outperforms the traditional DTW.关键词
手写汉字检测/无分割/SIFT/动态时间规整Key words
Chinese handwritten word spotting/segmentation-free/SIFT/dynamic time warping分类
信息技术与安全科学引用本文复制引用
黄志敏,姚舜奕,熊玉洁..基于两方向动态时间规整的无分割手写汉字检测[J].计算机应用研究,2016,33(11):3499-3502,4.基金项目
国家科技支撑计划资助项目（2011BAK05B04）；上海市科委资助项目 （）
