Adaptive image thresholding for real‐time particle monitoring

Abstract

Image thresholding is critical to computer vision systems designed to detect very small numbers of contaminant particles from analysis of images acquired by in-line process monitoring. The objective of this work was to obtain a thresholding method that would permit in-line, \real-time," determination of both the number of particles in an image and their size. An additional requirement was that it automatically adapt to inevitable variations in the image quality. A new global image thresholding method, the MaxMin method (\MaxMin"), was developed. MaxMin notes the size of the smallest detected particle in an image as threshold value is progressively changed from black to white. The selected threshold value is the one providing the largest size. MaxMin was tested on thousands of images, and it was shown to readily adapt to images of different background noise levels and provided particle counts as accurate as those of a human observer in less than three seconds per image. Error in particle size measurement was a function of the particle size and the image resolution. It was about 3% for 50 m particles, using a CCD camera with 2Â lens, calibrated for each pixel to represent *5 m 2 . The error was significantly higher for smaller particles, when the same system resolution was used.

Atomic-number ( Z )-correlated atomic sizes for deciphering electron microscopic molecular images

“…3 C , where we see an obvious effect of noise on the apparent signal height and also on the apparent radius of the signal, the noise acting like the sea of clouds that truncates the view of mountains. Thus, we set the SD of the background noise as the threshold for visual recognition ( 35 ). Cutting the triangle of the noise-free atom signals at low and high noise levels (LN and HN, blue and red lines in Fig.…”