摘要
针对计算机对手写输入字符的识别需求,本文基于k邻近算法构建了手写识别系统,并采取平滑、归一化等方法进行数据预处理,提取结构与统计特征,达到提高手写字符识别精度与准确率的目的。计算机测试后表明,本算法对手写字符识别的精度可以达到95%以上。
In order to satisfy the requirement of the handwriting recognition, a professional recognition system based on kNNis realized in this paper. The learning samples are smoothed and normalized. Then the structure and statistical features are extracted to improve the accuracy of handwritten character recognition.The results show that the accuracy of the proposed algorithm is more than 95%.
作者
辛英
XIN Ying(College of Mathematic and Information Science, Shandong Technology and Business University, Yantai 264005, Chin)
出处
《电子设计工程》
2018年第7期27-30,共4页
Electronic Design Engineering
关键词
模式识别
手写识别
k-邻近
识别精度
pattern recognition
handwriting recognition
kNN
recognition accuracy
