摘要
人耳识别技术是一门新型的个体生物识别技术,头部转动是影响人耳识别的重要原因之一.本文提出一种基于加权高阶不变矩特征方法的人耳个体生物识别系统,并初步建立60只人耳图像库.通过实验得出了主要测试数据,识别准确率可达到95%,证明该系统能够克服因头部转动对识别的影响.表明不变矩方法在人耳识别中具有一定优势.
Ear recognition is a new biological identification technology for individuals, but head moving is one of primary reasons, which has influence on ear recognition performance. The ear biological identification based on high rank moment invariants with coefficient is put forward and an image data including 60 ears is primarily built in the paper. The 95% recognition accuracy rate has been reached by experimental data, and it proves the method can well conquer the influence of head moving. Thus it has the advantage in ear recognition.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2004年第4期502-505,共4页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金(No.60375002)
关键词
人耳识别
不变矩
人耳图像库
Ear Recognition
Moment Invariant
Ear Database
