Jm. Reed et S. Hutchinson, IMAGE FUSION AND SUBPIXEL PARAMETER-ESTIMATION FOR AUTOMATED OPTICAL INSPECTION OF ELECTRONIC COMPONENTS, IEEE transactions on industrial electronics, 43(3), 1996, pp. 346-354
We present a new approach to automated optical inspection (AOI) of cir
cular features that combines image fusion with subpixel edge detection
and parameter estimation. in our method, several digital images are t
aken of each part as it moves past a camera, creating an image sequenc
e. These images are fused to produce a high-resolution image of the fe
atures to be inspected, Subpixel edge detection is performed on the hi
gh-resolution image, producing a set of data points that is used for e
llipse parameter estimation, The fitted ellipses are then back-project
ed into 3-space in order to obtain the sizes of the circular features
being inspected, assuming that the depth is known. The method is is ac
curate, efficient, and easily implemented. We present experimental res
ults for real intensity images of circular features of varying sizes,
Our results demonstrate that our algorithm shows greatest improvement
over traditional methods in cases where the feature size is small rela
tive to the resolution of the imaging device.