MUSE - A NEW TOOL FOR INTERACTIVE IMAGE-ANALYSIS AND SEGMENTATION BASED ON MULTIVARIATE-STATISTICS

被引:11
作者
BENGTSSON, E
NORDIN, B
PEDERSEN, F
机构
[1] Centre for Image Analysis, Uppsala University, S-75237 Uppsala
关键词
MULTIVARIATE IMAGE ANALYSIS; BIOMEDICAL IMAGE ANALYSIS; IMAGE SEGMENTATION; CLASSIFICATION; PRINCIPAL COMPONENT ANALYSIS; INTERACTIVE SOFTWARE;
D O I
10.1016/0169-2607(94)90128-7
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
MUSE - a new software tool for the interactive exploration of multivariate images and the development of image segmentation methods has been designed, implemented, and tested in a number of real application projects. The multivariate statistical classification and projection methods in MUSE can be used not only to analyze multispectral images but also, in special cases, multitemporal images and volume images. Additionally MUSE can be applied to normal greyscale images provided they are made multivariate through an initial processing step. This step may consist in the application of filters designed to enhance any existing texture differences between different regions in the images. MUSE has been successfully applied to medical images (color photographs, MR, PET, SPECT) as well as to satellite images (Landsat TM).
引用
收藏
页码:181 / 200
页数:20
相关论文
共 27 条
[1]  
BENGTSSON E, 1991, 7TH P SCIA, P798
[2]  
BENGTSSON E, 1987, 5TH P SCAND C IM AN, P217
[3]  
Devijver PA, 1982, PATTERN RECOGNITION
[4]  
DRAPER N, 1966, APPLIED REGRESSION A
[5]  
Duda R. O., 1973, PATTERN CLASSIFICATI, V3
[6]  
ENGSTROM N, 1989, P C PATHOGENESIS WOU
[7]  
ESBENSEN K, 1989, CHEMOMETRICS INTELLI, P67
[8]   The use of multiple measurements in taxonomic problems [J].
Fisher, RA .
ANNALS OF EUGENICS, 1936, 7 :179-188
[9]   PRINCIPAL COMPONENT ANALYSIS OF MULTIVARIATE IMAGES [J].
GELADI, P ;
ISAKSSON, H ;
LINDQVIST, L ;
WOLD, S ;
ESBENSEN, K .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1989, 5 (03) :209-220
[10]  
Geladi P., 1989, J CHEMOMETR, V3, P419, DOI DOI 10.1002/CEM.1180030209