Title :
FIR stack hybrid filters
Author :
Zhou, Hongbing ; Zeng, Bing ; Neuvo, Yrjo
Author_Institution :
Signal Process. Lab., Tampere Univ., of Technol., Finland
Abstract :
A recently developed approach to synthesizing optimal stack filters under the mean absolute error (MAE) criterion (see B. Zong et al., 1991) is extended to FIR (finite impulse response) stack hybrid (FSH) filters, where FIR filters are assumed to be the average filter. This approach is demonstrated through synthesizing a group of optimal FSH filters in the minimum MAE sense for the standard image `Bridge´, where the task is to restore the image from impulsive noise. Practical testing results show that optimal FSH filters can do much better than the corresponding FIR median hybrid filters
Keywords :
errors; filtering and prediction theory; picture processing; probability; FIR stack hybrid filters; finite impulse response; image-restoration; impulsive noise; mean absolute error criterion; probability estimation; Algorithm design and analysis; Boolean functions; Filtering theory; Finite impulse response filter; Image restoration; Laboratories; Process design; Signal processing; Signal processing algorithms; Testing;
Conference_Titel :
Circuits and Systems, 1991., IEEE International Sympoisum on
Print_ISBN :
0-7803-0050-5
DOI :
10.1109/ISCAS.1991.176311
