eduzhai > Applied Sciences > Engineering >

Machine learning techniques applied for detection of nanoparticles on surfaces using Coherent Fourier Scatterometry

  • Save

... pages left unread,continue reading

Document pages: 24 pages

Abstract: We present an efficient machine learning framework for detection andclassification of nanoparticles on surfaces that are detected in the far-fieldwith Coherent Fourier Scatterometry (CFS). We study silicon wafers contaminatedwith spherical polystyrene (PSL) nanoparticles (with diameters down to$ lambda 8$). Starting from the raw data, the proposed framework does thepre-processing and particle search. Further, the unsupervised clusteringalgorithms, such as K-means and DBSCAN, are customized to be used to define thegroups of signals that are attributed to a single scatterer. Finally, theparticle count versus particle size histogram is generated.The challenging cases of the high density of scatterers, noise and drift inthe dataset are treated. We take advantage of the prior information on the sizeof the scatterers to minimize the false-detections and as a consequence,provide higher discrimination ability and more accurate particle counting.Numerical and real experiments are conducted to demonstrate the performance ofthe proposed search and cluster-assessment techniques. Our results illustratethat the proposed algorithm can detect surface contaminants correctly andeffectively.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×