Edge detection for optical image metrology using unsupervised neural network learning

Several unsupervised neural network learning methods are explored and applied to edge detection of microlithography optical images. Lack of a priori knowledge about correct state assignments for learning procedure in optical microlithography environment makes the metrology problem a suitable area for applying unsupervised learning strategies. The methods studied include a self-organizing competitive learner, a bootstrapped linear threshold classifier, and a constrained maximization algorithm. The results of the neural network classifiers were compared to the results obtained by a standard straight edge detector based on the Radon transform and good consistency was observed in the results together with superiority in speed for the neural network classifiers. Experimental results are presented and compared with measurements obtained via scanning electron microscopy