Title :
Multivariate order statistic filters in color image processing
Author :
Tang, Kaijun ; Astola, Jaakko ; Neuvo, Yrjö
Author_Institution :
Signal Process. Lab., Tampere Univ. of Technol., Finland
Abstract :
A new class of multivariate order statistic (OS) filters is proposed with application to color image processing. The proposed multivariate OS filters have detail-preserving abilities while attenuating different types of noise in color images. In certain noisy conditions, they outperform the vector median filter. A statistical analysis of multivariate OS filtering for color images is provided
Keywords :
filtering and prediction theory; image processing; statistical analysis; color image processing; detail-preserving abilities; multivariate order statistic filters; noise attenuation; Color; Colored noise; Filtering; Filters; Laboratories; Smoothing methods; Statistical analysis; Statistics; TV; Video sequences;
Conference_Titel :
Systems Engineering, 1992., IEEE International Conference on
Conference_Location :
Kobe
Print_ISBN :
0-7803-0734-8
DOI :
10.1109/ICSYSE.1992.236959
