| 部分级联特征的离线手写体汉字识别方法 |
| |
| 引用本文： | 叶锋,邓衍晨,汪敏,廖茜,郑子华,林晖. 部分级联特征的离线手写体汉字识别方法[J]. 计算机系统应用, 2017, 26(8): 134-140 |
| |
| 作者姓名： | 叶锋 邓衍晨 汪敏 廖茜 郑子华 林晖 |
| |
| 作者单位： | 福建师范大学 数学与计算机科学学院, 福州 350007;福建星网锐捷通讯股份有限公司 通讯产品研究院, 福州 350002,重庆大学 计算机学院, 重庆 400044,福建师范大学 数学与计算机科学学院, 福州 350007,福建师范大学 数学与计算机科学学院, 福州 350007,福建师范大学 数学与计算机科学学院, 福州 350007,福建师范大学 数学与计算机科学学院, 福州 350007 |
| |
| 基金项目： | 福建省引导项目（2016Y0031）；福建省教育厅项目（JA15136）；福建师范大学教学改革研究项目（I201602015）；福建师范大学2015年省级大学生创新训练计划项目（201510394044） |
| |
| 摘 要： | 针对汉字类别多、风格多等识别难点，提出了一种基于LS-SVM的部分级联特征分类的离线手写体识别方法.具体包括霍夫空间加权采样和局部二值分布直方图两种新的特征提取算法，其可将任意大小的图像映射到固定长度的特征向量上，克服了已有特征提取算法的需要归一化、对笔画密度分布敏感等缺点；提出了基于部分级联特征的分类方式；提出了常见多分类方式的类别与正确率的关系，并给出了相应的数学证明.
|
| 关 键 词： | 离线手写体识别 LS-SVM 多分类 部分级联特征 |
| 收稿时间： | 2016-12-09 |
Offline Hand-Written Chinese Character Recognition Based on Partial Cascade Feature |
| |
| YE Feng,DEN Yan-Chen,WANG Min,LIAO Xi,ZHEN Zi-Hua and LIN Hui. Offline Hand-Written Chinese Character Recognition Based on Partial Cascade Feature[J]. Computer Systems& Applications, 2017, 26(8): 134-140 |
| |
| Authors: | YE Feng DEN Yan-Chen WANG Min LIAO Xi ZHEN Zi-Hua LIN Hui |
| |
| Affiliation: | School of Mathematics and Computer Science, Fujian Normal University, Fuzhou 350007, China;Fujian STAR-NET Communications Co. Ltd., Fuzhou 350002, China,College Of Compute Science, Chongqing University, Chongqing 400044, China,School of Mathematics and Computer Science, Fujian Normal University, Fuzhou 350007, China,School of Mathematics and Computer Science, Fujian Normal University, Fuzhou 350007, China,School of Mathematics and Computer Science, Fujian Normal University, Fuzhou 350007, China and School of Mathematics and Computer Science, Fujian Normal University, Fuzhou 350007, China |
| |
| Abstract: | A method for offline hand-written Chinese character recognition is proposed based on partial cascade feature classification, which is of much research value and highly innovative. Two feature extracting algorithms are proposed as follows: weighted Low Threshold Hough Space Sampling(wHHS) and Histogram of Local Binary Distribution(HLBD). These algorithms can map images of various sizes into vectors with fixed dimension, but eliminate the disadvantages of existing algorithms, which has high sensitivity of the distribution of strokes destiny, and demand uniformization. A strategy of classification based on partial cascade feature is proposed and the relationship between number of category for classification and accuracy is put forward with the corresponding mathematical proof. |
| |
| Keywords: | offline hand-written Chinese character recognition LS-SVM muti-classification partial cascade feature |
|
| 点击此处可从《计算机系统应用》浏览原始摘要信息 |
|
点击此处可从《计算机系统应用》下载全文 |
|
