Title :
Iterative smoothed residuals: a low-pass filter for smoothing with controlled shrinkage
Author :
Wheeler, Mark D. ; Ikeuchi, Katsushi
Author_Institution :
Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
fDate :
3/1/1996 12:00:00 AM
Abstract :
We present a linear smoothing operator which has low-pass characteristics similar to a Butterworth filter and limited spatial extent similar to a Gaussian. The smoothing operator also has closed forms in the spatial and frequency domains which facilitate analysis and implementation. A formula is derived that allows us to explicitly control shrinkage
Keywords :
Gaussian distribution; Gaussian processes; computer vision; curve fitting; edge detection; frequency-domain analysis; iterative methods; low-pass filters; smoothing methods; splines (mathematics); Butterworth filter; Gaussian filter; computer vision; frequency domains; iterative smoothed residuals; linear smoothing operator; low-pass filter; shrinkage; smoothing splines; spatial domains; Computer vision; Filtering; Fourier transforms; Frequency domain analysis; Gaussian noise; Image recognition; Low pass filters; Nonlinear filters; Signal processing; Smoothing methods;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
