数字图像处理_变换技术与其应用.pptVIP

Dr. JI ZHEN * The kernel matrix for the Haar transform(N=8) Dr. JI ZHEN * The Haar transform basis images(N=8) Dr. JI ZHEN * The K-L Transform(Hotelling) The K-L transform is variously called Hotelling transform, the eigenvector transform, or the method of principal componets. Suppose image set ：{ f1(x,y), f2(x,y), …, fi(x,y), …, fL(x,y)} \ Where the correlation between fi(x,y) is commonly rather high. fi(x,y) can be represented as N2-by-1 vector Xi xij is the jth row of image fi(x,y) . i=1,2,…,L Dr. JI ZHEN * The K-L Transform The covariance matrix of vector X is defined as, Cf = E{(X-mf)(X-mf)T} The mean vector mf is mf =E{X} mf is N2-by-1 vector, Cf is N2×N2 matrix. In generally, mf and Cf can be represented approximately as, Dr. JI ZHEN * The K-L Transform Let ei and ?i be the eigenvectors and eigenvalues of Cf . Where i=1,2,…,N2, Suppose The K-L transform is g = A(X-mf) Dr. JI ZHEN * The Properties of the K-L transform A)The mean vector of g, mg=0 mg =E{g}=E{A(X-mg)}=A E{X}-A mg=0 B) The covariance matrix of g, Cg=A Cf AT Cg = E{(Y-mg)(Y-mg)T} = E{ggT} = E{(AX-Amg)(AX-Amg)T} = E{A(X-mg)(X-mg)TAT} = AE{(X-mg)(X-mg)T} AT = A Cf AT Dr. JI ZHEN * The Properties of the K-L transform C)Cg is a diagonal matrix having the eigenvalues of Cg along its diagonal. The elements of g are uncorrelated. D) The K-L transform is invertible.The original image can be reconstructed by A-1 = AT f = A-1f + mf Dr. JI ZHEN * K-L变换的几点说明 K-L变换是在特征向量上展开，最大限度地去除图像的相关性（冗余度）。在误差所允许的范围之内，实现最小均方误差意义上的压缩。 在理论上，K-L变换是最佳变换，原因就是变换是在特征向量与上展开的。 一般不具有可分性，没有快速算法，只在一定条件下，用近似方法找到快速算法。 变换的核矩阵随图像的不同而不同 Dr. JI ZHEN * K-L变换的几点说明 当利用与最大特征值相对应的k个特征矢量代替所有特征矢量Cf形成A，那么g矢量将是k维的,利用 进行重建就不再是精确的了，求出的知识近似的f,但均方误差 将是最小的。 Dr. JI ZHEN * 5.Rotation In polar coordinates, f (x,y) and F