Title :
A comparison of adaptive order statistic filters using different images
Author :
Martens, Renée L J ; Venetsanopoulos, A.N.
Author_Institution :
Dept. of Electr. Eng., Toronto Univ., Ont., Canada
Abstract :
Histogram windowing, a local statistic-based edge detector, an adaptive window size, and a median filter are compared to the median filter, the SAM filter, and the moving average filter. The five filters are compared using the peak-to-peak signal-to-noise ratio (PSNR). Four different images are used for comparison: (1) Lenna, (2) geometrical, (3) harbour, and (4) face. Three noise types are used: (1) additive, (2) impulse, and (3) a combination of the two. The results of the experiment show that the PSNR depends very much on what kinds of image are used.<>
Keywords :
adaptive filters; computerised picture processing; filtering and prediction theory; SAM filter; adaptive order statistic filters; adaptive window size; additive noise; histogram windowing; impulsive noise; local statistic-based edge detector; median filter; moving average filter; peak-to-peak signal-to-noise ratio; Adaptive filters; Filtering; Image processing; Prediction methods;
Conference_Titel :
Systems Engineering, 1989., IEEE International Conference on
Conference_Location :
Fairborn, OH, USA
DOI :
10.1109/ICSYSE.1989.48624
