Abstract: Embodiments described herein relate to a system, methods, and non-transitory computer-readable mediums that accurately align subsequent patterned layers in a photoresist utilizing a deep learning model and utilizing device patterns to replace alignment marks in lithography processes. The deep learning model is trained to recognize unique device patterns called alignment patterns in the FOV of the camera. Cameras in the lithography system capture images of the alignment patterns. The deep learning model finds the alignment patterns in the field of view of the cameras. An ideal image generated from a design file is matched with the camera with respect to the center of the field of view of the camera. A shift model and a rotation model are output from the deep learning model to create an alignment model. The alignment model is applied to the currently printing layer.

Abstract: A trial frame includes a trial frame body and at least one measurement subject having a visual invariant geometric characteristic. The trial frame body has at least one key parameter. The measurement subject is disposed on the trial frame body and collaborates with a measurement method. A two-dimensional image of the measurement subject is recorded by an image capturing device when the trial frame body fits to a user, and the key parameter is deduced from the two-dimensional image of the measurement subject.

Abstract: A trial frame includes a trial frame body and at least one measurement subject having a visual invariant geometric characteristic. The trial frame body has at least one key parameter. The measurement subject is disposed on the trial frame body and collaborates with a measurement method. A two-dimensional image of the measurement subject is recorded by an image capturing device when the trial frame body fits to a user, and the key parameter is deduced from the two-dimensional image of the measurement subject.