A NOISE PEAK ELIMINATION FILTER

被引:11
作者
IMME, M
机构
[1] Philips GmbH Forschungslaboratorium Hamburg, D-2000 Hamburg 54
来源
CVGIP-GRAPHICAL MODELS AND IMAGE PROCESSING | 1991年 / 53卷 / 02期
关键词
Computer Programming - Algorithms - Signal Filtering and Prediction;
D O I
10.1016/1049-9652(91)90062-O
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
This paper describes a new approach to eliminating noise pixels within an image. This approach is compared with five other well known filter algorithms taken from the literature; it is shown that the new method, on the one hand, is simple and fast and, on the other hand, smoothes the objects within an image without losing edge information and without creating undesired structures. The central idea of the algorithm is to replace a pixel with its next neighbor in value within a 3 × 3 window, if this pixel has been found to be a noise pixel. © 1991.
引用
收藏
页码:204 / 211
页数:8
相关论文
共 6 条
  • [1] IMAGE SEGMENTATION SCHEMA FOR LOW-LEVEL COMPUTER VISION
    ASANO, T
    YOKOYA, N
    [J]. PATTERN RECOGNITION, 1981, 14 (1-6) : 267 - 273
  • [2] Huang T.-C., 1978, Proceedings of the Geological Society of China, P128
  • [3] ITERATIVE ENHANCEMENT OF NOISY IMAGES
    LEV, A
    ZUCKER, SW
    ROSENFELD, A
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1977, 7 (06): : 435 - 442
  • [4] EDGE PRESERVING SMOOTHING
    NAGAO, M
    MATSUYAMA, T
    [J]. COMPUTER GRAPHICS AND IMAGE PROCESSING, 1979, 9 (04): : 394 - 407
  • [5] NEWMAN TG, 1973, IEEE T COMPUT, P869
  • [6] 1983, SPIDER USERS MANUAL