摘要
针对人耳特点在Canny边缘检测基础上采用不变矩算法提取特征向量。Canny算法能不漏检真实边缘,也不会把非边缘点作为边缘点检出,它检测出的边缘点都尽可能在实际边缘的中心,而且Canny算法对虚假边缘响应有抑制作用。采用不变矩算法进行特征提取,该算法具有不受平移、旋转和比例变化限制的特点。
A moment invariants algorithm was used to extract the eigenvector for the characteristics of the human ear, and was not subject to restrict on translation, rotation and the ratio of changes. Canny algorithm was used for edge detection of human ear based on moment invariants. Experimental results show that Canny algorithm can not miss the real edge and regard the non-edgo points as the edge points. It detects the edge points as close as possible in the actual center of the edge and inhibits the false edge response.
出处
《计算机应用》
CSCD
北大核心
2010年第A01期159-161,共3页
journal of Computer Applications
基金
上海市教委科研创新基金资助项目(09YZ223)
关键词
人耳识别
不变矩算法
CANNY算法
七阶矩
边缘检测
identification of human ear
moment invariants algorithm
Canny algorithm
seven-order moments
edge detection
