Wavelet transform and gradient direction based feature extraction method for off-line handwritten Tibetan letter recognition
基于小波变换和梯度方向的脱机手写藏文字符特征提取方法(英文)作者机构:东南大学自动化学院南京210096 青海师范大学计算机学院西宁810008 福坦莫大学计算机与信息科学系纽约10458
出 版 物:《Journal of Southeast University(English Edition)》 (东南大学学报(英文版))
年 卷 期:2014年第30卷第1期
页 面:27-31页
核心收录:
学科分类:1305[艺术学-设计学(可授艺术学、工学学位)] 0810[工学-信息与通信工程] 13[艺术学] 08[工学] 081104[工学-模式识别与智能系统] 0804[工学-仪器科学与技术] 0805[工学-材料科学与工程(可授工学、理学学位)] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术(可授工学、理学学位)]
基 金:The National Natural Science Foundation of China(No.60963016) the National Social Science Foundation of China(No.17BXW037)
主 题:pattern recognition wavelet transform gradient direction Tibetan handwritten character
摘 要:To improve the recognition accuracy of off-line handwritten Tibetan characters the local gradient direction histograms based on the wavelet transform are proposed as the recognition *** for a Tibetan character sample image the first level approximation component of the Haar wavelet transform is *** the approximation component is partitioned into several equal-sized zones. Finally the gradient direction histograms of each zone are calculated and the local direction histograms of the approximation component are considered as the features of the character sample *** proposed method is tested on the recently developed off-line Tibetan handwritten character sample *** experimental results demonstrate the effectiveness and efficiency of the proposed feature extraction *** compared with the detail components the approximation component contributes more to the recognition accuracy.