笔迹样本去噪方法分析研究  

作　　者：曹华军[1] 张强[1] CAO Hua-jun;ZHANG Qiang

机构地区：[1]山东协和学院机电工程学院,山东济南250100

出　　处：《信息技术与信息化》2016年第9期103-105,共3页Information Technology and Informatization

基　　金：2014年国创项目:基于笔迹识别样本入库处理系统研究;项目编号:201410825022

摘　　要：本文首先分析了在笔迹图像处理中所常见的各类噪声分类及特点,指出在笔迹识别领域对样本去噪的必要性及意义,根据字符图像的特点及大量实验,分析研究了对笔迹样本预处理中广泛使用的几种去噪方法,并对它们的优缺点及具体使用范畴进行了界定,提出了各种去噪滤波的算法,并给出了具体的实现方法及对比结果,在样本入库系统设计中具有重要现实意义。This paper first analyzes the classification and characteristics of various types of noise in common handwriting image processing,pointed out the necessity and significance of denoising samples in handwriting recognition field, according to the characteristics of the character image and a lot of experiments, analyzed several widely used samples of handwriting in the preprocessing denoising method, their advantages ,shortcomings and the use of specific areas were defined, put forward various filtering algorithm, and gives the realization method and comparison of specific results, this has important practical significance in the design of the whole system.

关 键 词：噪声特点 均值滤波 中值滤波 维纳滤波 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]