摘要
不变矩是1种高度浓缩的图像特征,具有平移、灰度、尺度、旋转等多畸变不变性。1961年,M.K.Hu首先提出了7个几何不变矩用于图像描述。后来人们进行多方面研究,发现正交矩具有绝对的独立性,没有信息冗余现象,抽样性能好,抗噪声能力强,更适合用于多畸变不变图像描述和识别。性能较好的正交矩有Legendre矩、Zern ike矩、正交傅立叶-梅林矩、切比雪夫矩和变形雅可比(p=4,q=3)-傅立叶矩等。近几年,用正交矩进行图像分析、图像处理以及图像识别的研究报道很多,这表明不变矩理论及其在图像信息处理与识别中的应用技术具有很好的发展前景和应用商机。本文系统介绍了不变矩的概念、特性以及它在图像分析中的简单应用。
Invariant moments are highly concentrated image features that are shift-, rotation-, scale- and intensity-invariant. M. K. Hu first introduced seven moment invariants in 1961, based on methods of algebraic invariants. Later studies indicated that the orthogonal moments have the best overall performance in terms of noise sensitivity, information redundancy, and capability of image description. The ideal orthogonal moments are Zernike Moments , Orthogonal Fourier-Mellin Moments , Chebyshev-Fourier Moments , Pseudo-Jacobi （ p=4, q=3）-Fourier Moments. Especially, many reports have been published about image analysis and pattern recagnition with orthogonal moments in recent years. Therefore, the theory of invariant moments and their application to image analysis and pattern recognition have a good future. The concepts and the applications of the invariant moments were systematically introduced in this paper.
出处
《内蒙古农业大学学报（自然科学版）》
CAS
2005年第4期146-150,共5页
Journal of Inner Mongolia Agricultural University(Natural Science Edition)
基金
国家自然科学基金资助项目(60467001)
内蒙古自然科学基金资助项目(200408020109)
内蒙古自治区高等学校科学研究资助项目(NJ03037)
关键词
不变矩
多畸变不变性
图像分析
图像识别
Invariant moments
Multi-distortional Invariants
Image analysis
Pattern recognition
