基于改进ISOMAP算法的手写数据非线性结构分析  

Nonlinear Structure Analysis of Handwritten Data Based on Improved ISOMAP Algorithm

作　　者：郭爱心 GUO Ai-xin(Shanxi Normal University,Taiyuan 030006,Shanxi)

机构地区：[1]山西师范大学物理与信息工程学院,山西太原030006

出　　处：《电脑与电信》2021年第10期1-4,共4页Computer & Telecommunication

基　　金：国家自然科学基金,项目编号:62004119。

摘　　要：手写数据的非线性结构分析对于手写数据识别和手写签名认证具有重要意义。然而,手写数据通常具有较高维度,需要进行非线性降维处理。提出了一种改进的ISOMAP算法,提高了ISOMAP算法的效率,并将其应用于手写数据的非线性结构分析。实验结果表明,本算法具有较高的效率和准确性,手写数据具有潜藏的本征维度和非线性结构。Nonlinear structure analysis of handwritten data is important for handwritten data recognition and signature authentication.However,handwritten data usually has high dimension and dimension reduction processing is required.In this paper,an improved ISOMAP algorithm is proposed,improving the efficiency of ISOMAP algorithm.It is applied to the nonlinear structure analysis of handwritten data.The experimental results show that the proposed algorithm has high efficiency and accuracy,and the handwritten data has latent intrinsic dimension and nonlinear structure.

关 键 词：ISOMAP 地标点 降维 非线性结构分析 手写数据 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]