摘要
离线笔迹鉴别在司法鉴定与历史文档分析中有重要作用.当前的主要离线笔迹鉴别都是基于局部特征提取的方法,其在笔迹检索中严重依赖于数据增强和全局编码,在笔迹识别中需要较多的笔迹信息.针对这一问题,本文提出一种基于统计的文档行分割与深度卷积神经网络相结合的离线笔迹鉴别方法(DLS-CNN).首先,使用基于统计的文档行分割方法将笔迹材料分割成小的像素块;然后,用优化后的残差神经网络作为识别模型;最后,对局部特征使用取均值法进行编码.在ICDAR2013和CVL这两个标准数据集上的实验结果表明,该方法能有效获得鲁棒的局部特征,从而仅需要少量的笔迹信息就能取得较高的识别率,而且不需依赖于数据增强和全局编码就能取得较好的检索效果.实验代码地址:https://github.com/shiming-chen/DLS-CNN.
O-line writer identi cation plays an important role in forensics and historical document analysis.The current well-known o-line writer identi cation approaches are based on local feature extraction.They rely heavily on data augmentation and global encoding for writer retrieval,and need a great number of written contents for writer recognition.This paper proposes a new o-line writer identi cation method,called DLS-CNN,which combines document line segmentation in terms of statistic and deep convolutional neural network.More precisely,handwriting documents are segmented into patches using document line segmentation at rst.Secondly,an improved residual neural network serves as the identi cation model.Finally,the mean value of all local features vectors are used as nal global features for writer identi cation.Experimental results on ICADAR2013 and CVL benchmark datasets show that,due to the extracted robust local features,DLS-CNN achieves higher identi cation rate with fewer written contents,and better retrieval result without data augmentation and global encoding.All the experiment codes are available at https://github.com/shiming-chen/DLS-CNN.
作者
陈使明
王以松
CHEN Shi-Ming;WANG Yi-Song(School of Computer Science and Technology,Guizhou Uni-versity,Guiyang 550025;Key Laborary of Intelligent Medi-cal Image Analysis and Precise Diagnosis of Guizhou Province,Guiyang 550025)
出处
《自动化学报》
EI
CSCD
北大核心
2020年第1期108-116,共9页
Acta Automatica Sinica
基金
国家自然科学基金(61370161,61562009,61976065)
贵州省优青年秀科技人才培养对象基金(2015(01))资助~~
关键词
笔迹鉴别
笔迹检索
文档行分割
卷积神经网络
特征提取
Writer identi cation
writer retrieval
document line segmentation
convolutional neural network(CNN)
features extraction