Paper Info
Title
A Thresholding Approach for Segmenting Deteriorated SEM Images in an Automated X-ray Mask Visual Inspection System
Abstract
The most t roublesome problem in automated X- ray mask inspection is how to exactly determine the threshold level for extracting the pattern portions of each scanning electron microscopic (SEM) image. An exact determination is difficult because the histogram shows, in most cases, a complicated multi-modal pattern and the true threshold level often varies too much with each successive image t o b e d educed f rom t hreshold values determined for the preceding image. This paper p resents a novel thresholding approach for segmenting SEM images of X-ray masks. In this a pproach, the s hape of the h istogram of each image is iteratively analyzed until a reli- able threshold value satisfying all criteria for determining thresholds is obtained. This new approach is used in an a utomated i nspection system. When the input image resolution is set to 0.05
Year
Venue
Keywords
1994
MVA
image resolution,satisfiability,scanning electron microscope,visual inspection
Field
DocType
Citations 
Computer vision,Histogram,Visual inspection,X-ray,Pattern recognition,Threshold limit value,Artificial intelligence,Mask inspection,Thresholding,Image resolution,Mathematics
Conference
0
PageRank 
References 
Authors
0.34
1
1
Name
Order
Citations
PageRank
Minoru Ito1368.27