@article{oai:ir.kagoshima-u.ac.jp:00010362,
 author = {Nakamori, Seiichi},
 journal = {鹿児島大学教育学部研究紀要. 自然科学編, Bulletin of the Faculty of Education, Kagoshima University. Natural science},
 month = {2016-10-28},
 note = {This paper proposes an image restoration technique by the recursive least-squares (RLS) Wiener fixed-point smoother and filter in linear discrete-time stochastic systems. The RLS Wiener estimators use the auto-covariance function of the signal，the system matrix φ for the n by 1 zero-mean signal vector s(i，j)，which is obtained by subtracting the mean of the image signal x(i，j) from the signal values of the image，the variance of s(i，j) and the variance of the white observation noise. Here，for the two-dimensional zero-mean values s(i，j)，i= 1，2，・・・，M，j=1，2，・・・，N，the n by 1 vector consisting of the components s(i，j)， i=1，2，・・・，n，are estimated along the horizontal direction for j=1，2，・・・，N.Next，the n by 1 vector consisting of s(i，j)，i=n+1，n+2，・・・，2n，are estimated，recursively from the left to the right column，similarly. This procedure is continued，at last，to the last columnj=N for the bottom n by 1 vector of s(i，j). Finally，the estimates of the image are obtained by adding the mean to the estimates of s(i，j).},
 pages = {29--38},
 title = {Image Restoration Technique by RLS Wiener Fixed-Point Smoother and Filter},
 volume = {60},
 year = {}
}