動径基底関数ネットワークを用いた画像の補間

概要

論文の詳細を見る
Interpolation of digital images is one of the important problems in image processing [1]. Because image information as two-dimensional signals is possibly nonlinear, then linear interpolation of images cannot efficiently solve the problem of interpolation. Although there are several interpolation method, such as nearest neighbor interpolation (NNI), bi-linear interpolation (BLI) and cubic convolution interpolation (CCI) [1], one of the popular methods in the field of nonlinear functional approximation is back propagation learning in neural networks [2], [3]. However, back propagation learning in neural networks requires larger amount of computational time than radial basis function (RBF) networks. In this paper, we apply standard radial basis interpolation (RBI) [4], [5] to digital image data interpolation problems. We propose an algorithm for determining the parameters of RBF by the variance of images. As a result, it is shown that interpolation with radial basis function networks exhibits better signal-to-noise ratio (SNR).
社団法人電子情報通信学会の論文
1997-03-06