摘要
针对目前银行卡号识别算法的不足,基于模式识别技术,提出一种改进的特征匹配算法,并将其应用于银行卡号识别.改进的特征提取算法改变了特征向量,并增加特征学习次数,解决了传统方法识别银行卡号正确率较低的问题,并保证了识别效率.仿真实验结果表明,改进的特征提取算法可有效提高银行卡号识别的正确率.
Aiming at the shortcomings of current bank card number recognition algorithm, we proposed an improved feature matching algorithm based on pattern recognition technique, and applied it to bank card number recognition. The improved feature extraction algorithm transformed feature vectors and increased the number of feature learnings, solved the problem of traditional method identifying bank card number with low accuracy, and ensured the recognition efficiency. Simulation experimental results show that the improved feature extraction algorithm can effectively improve the correct rate of bank card number recognition.
出处
《吉林大学学报（理学版）》
CAS
CSCD
北大核心
2018年第1期126-129,共4页
Journal of Jilin University:Science Edition
基金
国家自然科学基金(批准号：21606099)和吉林师范大学国家级大学生创新创业训练计划项目(批准号：201610203016).
关键词
数字识别
改进特征匹配
特征向量
欧氏距离
numerical recognition
improved feature matching
feature vector
Euclidean distance
