基于SVM的藏文古籍版面分割  

SVM-based layout segmentation of ancient Tibetan books

作　　者：任方针 王秀友 朱弋 时如梦 王胜波 刘华明 REN Fangzhen;WANG Xiuyou;ZHU Yi;SHI Rumeng;WANG Shengbo;LIU Huaming(School of Computer and Information Engineering,Fuyang Normal University,Fuyang Anhui 236037,China)

机构地区：[1]阜阳师范大学计算机与信息工程学院,安徽阜阳236037

出　　处：《阜阳师范大学学报（自然科学版）》2021年第2期92-96,共5页Journal of Fuyang Normal University:Natural Science

基　　金：国家自然科学基金面上项目(61772430);安徽省高校自然科学基金重大项目(KJ2020ZD46);阜阳师范大学高层次人才科研启动项目(2020KYQD0032);阜阳师范大学年青年人才重点项目(rcxm202001)资助。

摘　　要：古籍图像版面分割是古籍数字化保护过程中非常重要的一步,藏文古籍版面分割是藏文版面分析的基础。针对藏文古籍版面分割问题,把图像切分为150×150的图像块,提取图像块的灰度特征、颜色特征、纹理特征组合成18维的特征向量,用图像块样本训练SVM,得到每个图像块的分类结果,以获取粗略古籍版面分割结果,然后结合投影法得到精确的版面分割结果。实验结果表明,该方法能有效分割文本区域,为藏文古籍图像版面分割提供了一种可行的思路。The image layout segmentation of ancient books is a very important step in the process of digital protection of an-cient books.The layout segmentation of ancient Tibetan books is the basis of Tibetan layout analysis.Aiming at the problem of dividing the layout of Tibetan ancient books,the image is divided into 150×150 image blocks,then extract the gray-scale feature,color feature,and texture feature of the image block,these feature are combined into an 18-dimensional feature vector,and the SVM is trained with the image block sample.The classification result of each image block is used to obtain the rough ancient book layout segmentation result,and then combined with the projection method to obtain the accurate layout segmentation re-sult.Experimental results show that this method can effectively segment text area,and provides a feasible idea for image layout segmentation of Tibetan ancient books.

关 键 词：版面分割 支持向量机 特征提取 藏文古籍 

分 类 号：TP312[自动化与计算机技术—计算机软件与理论]