所属 明治大学 総合数理学部 職種 専任教授
|標題||Extended Component-Separating Nonlinear Digital Filter with Optimization|
and Its Application to Face Image Beautification
|掲載誌名||Proc. IEEE ISPACS2003|
|著者・共著者||Kaoru Arakawa and Hiroo Naito|
|概要||Authors proposed before a nonlinear digital filter named as a component-separating nonlinear digital filter (CS filter for short) in order to reduce smallamplitude random noise on signals which contain both continuous changes and abrupt ones. However, this filter has a drawback that it cannot suppress low-frequency components in noise adequately.|
In this paper, an extended version of the CS filter is proposed. This filter can suppress the low-frequency
noise adequately as well as the high-frequency one.
Moreover, a method for its optimum design is also
proposed. As to the application, this filter is shown to be
quite effective for face image processing to make the skin
look smooth and beautified.