基于索引的快速手写中文文档关键词检索  

Fast Keyword Spotting in Handwritten Chinese Documents Using Index

作　　者：喻庚 殷飞[2] 陈友斌[1] 刘成林[2] 

机构地区：[1]华中科技大学自动化学院,武汉430074 [2]中国科学院自动化研究所模式识别国家重点实验室,北京100190

出　　处：《模式识别与人工智能》2015年第11期1033-1040,共8页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.61305005;61273269;61175021)资助

摘　　要：手写文档检索很难同时保证较高的检索精度和速度.基于上述原因,文中提出快速手写中文文档关键词检索方法,大幅提高检索速度并保持检索精度.该方法基于文本行识别的候选切分-识别网格预先生成压缩的索引文件,然后在索引上快速检索关键词.在手写中文文档数据库CASIA-HWDB上的实验证明文中方法的有效性,该方法不但压缩索引大小,而且缩短词检索的耗时.In document retrieval, high retrieval precision and speed can hardly be achieved simultaneously. A fast keyword spotting method for handwritten Chinese documents is proposed. By this method, keyword spotting is accelerated with accuracy preserved. Firstly, compressed index files are generated from the candidate segmentation recognition lattice of text lines recognition, then keywords are retrieved from the index files. Experimental results demonstrate the effectiveness of the retrieval time. on the handwritten Chinese proposed method. Moreover, documents database CASIA-HWDB it reduces the size of index and the retrieval time.

关 键 词：手写中文文档图像 关键词检索 索引压缩 快速检索 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]