手写邮政编码的模糊识别方法  

Fuzzy Recognition of Handwritten Postcodes

作　　者：尹朝庆[1] 宋化[1] 陈波[1] 

机构地区：[1]武汉理工大学计算机科学与技术学院,湖北武汉430063

出　　处：《武汉理工大学学报（信息与管理工程版）》2005年第2期154-157,共4页Journal of Wuhan University of Technology：Information & Management Engineering

摘　　要：提出一种基于神经网络的手写邮政编码的模糊识别方法,它包括邮编框边缘检测与分离、图像二值化、去噪、倾斜校正、提取邮编数字、窗格缩放、位置归一化、数字细化、数字识别特征提取和基于BP网络的模糊识别等10个环节。经实验表明,该方法的正确识别率达90%以上。A new fuzzy recognition method of handwritten postcodes based on neural network is presented. This method includes ten links: edge detection and separation of a postcode box, binarization, denoising, incline correction, extraction of postcode numerals, window scaling, location standardization, thinning, extraction of numeral feature and fuzzy recognition based on BP neural network. Through testing, the recognition rate of this method can be over 90%.

关 键 词：识别方法 邮政编码 手写 图像二值化 神经网络 边缘检测 倾斜校正 模糊识别 BP网络 特征提取 数字识别 归一化 识别率 缩放 细化 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] G894.1[自动化与计算机技术—计算机科学与技术]