AUTOMATED X-RAY INSPECTION OF ALUMINUM CASTINGS

被引:46
作者
BOERNER, H
STRECKER, H
机构
[1] Philips GmbH, Hamburg, West Ger, Philips GmbH, Hamburg, West Ger
关键词
IMAGE PROCESSING - Image Analysis - NONDESTRUCTIVE EXAMINATION - Imaging Techniques;
D O I
10.1109/34.3869
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The experience gained with several approaches to automatic flaw detection in X-ray images of cast aluminum wheels is described. Basic problems are mentioned, and the applicability of segmentation methods to actual inspection tasks is demonstrated. The discussion focuses on the definition, extraction, and combination of local features for pixel classification. Results of recent pilot tests are described briefly. Further investigations are suggested, aiming at more generality of the methods and greater stability of the segmentation.
引用
收藏
页码:79 / 91
页数:13
相关论文
共 28 条
[1]  
BARSCHDORF H, 1985, 65185 PHIL RES LAB I
[2]  
BEAUDET PR, 1978, P 4 JOINT C PATT REC, P578
[3]  
BLANZ WE, 1983, THESIS U STUTTGART S
[4]  
Born M., 1975, PRINCIPLES OPTICS, VFifth
[5]  
CANNY JJ, 1983, MIT AI TR720 TECH RE, P65
[6]  
CLOSIER MJ, 1981, NDT INT APR, P59
[7]   COOPERATING PROCESSES FOR LOW-LEVEL VISION - A SURVEY [J].
DAVIS, LS ;
ROSENFELD, A .
ARTIFICIAL INTELLIGENCE, 1981, 17 (1-3) :245-263
[8]   A difference technique for automatic inspection of casting parts [J].
Decker, H. .
PATTERN RECOGNITION LETTERS, 1983, 2 (02) :125-129
[9]   A SURVEY ON IMAGE SEGMENTATION [J].
FU, KS ;
MUI, JK .
PATTERN RECOGNITION, 1981, 13 (01) :3-16
[10]  
FUKUNAGA K, 1972, ELECTRICAL SCI SERIE