【作者】 胡学龙； 张根生； 杨义军；

【Author】 HU Xue-long1,2,ZHANG Gen-sheng1,YANG Yi-jun3(1 School of Information Engineering,Yangzhou University,Yangzhou 225009,China;2.Jiangsu Province Key Lab for Image Processing and Image Communication,Nanjing University of Posts and Communications,Nanjing 210003,China;3 School of Physical Science and Technology,Yangzhou University,Yangzhou 225009,China)

【机构】 扬州大学信息工程学院； 南京邮电大学江苏省图像处理与图像通信重点实验室； 扬州大学物理科学与技术学院；

【摘要】 提出了一种通过相位叠合模型来检测角点和边缘的算法,这种方法利用图像傅里叶分量在特征叠合次数最多的概念,采用相位叠合后的关键点来确定角点和边缘信息,利用相位叠合来标记特征点比用梯度方法有明显的优点:相位叠合是一种无量纲量,而且对图像的亮度或对比度是不变的,因此它能提供对特征点的绝对度量.实验结果证明本算法提取的角点和边缘特征不随图像照度而改变,提高了不同照度下提取图像边缘特征的可靠性.更多还原

【Abstract】 This paper describes a new corner and edge detector developed from the phase congruency information to determine corner and edge information.This method makes use of the concept which Fourier components have maximum congruency at feature points,and using phase congruency for marking features has significant advantages over gradient based methods.It is a dimensionless number that is invariant to change of brightness or contrast,hence it provides an absolute measure of the significance of feature point.The experimental results prove the corner and edge operator have response that are invariant to image contrast and more reliable edge feature detection effect under varying illumination conditions.更多还原