Main Article Content
This paper presents a method for locating and imputing the damage on Atomic Force Microscopy (AFM) image. In imaging, the surface topography of the sample is constructed by mapping the motion of the probe tip which directly corresponds to the sample surface and its position along the scan lines. However, the combination of the dragging motion of the tip across the surface and the adhesive force between tip and sample surface potentially cause the damage to the sample and also other unspecified causes. Hence, Dual Threshold Median Filtering was employed in preparing the data, and it consequently was imported to the Extreme Learning Machine to determine the positions of the damage in the AFM image. And the image was recovered using Fast Digital Image Inpainting. The proposed algorithms had detected more than 63 percent of the damage locations, and the recovery of the damage did not effect on other areas of the image.
Atomic Force Microscope, Locating Damage on Image, Extreme Learning Machine
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.