Abstract: A method for automated defect classification of a sample: scanning, by a scanning acoustic microscope, a sample in a predefined frequency range, the scanning acoustic microscope comprises one or more ultrasonic transducers, the sample is positioned stepwise relative to the one or more ultrasonic transducers at raster points, one or more ultrasound signals are generated at each raster point and recorded after at least one of reflection on the sample and transmission by the sample, digitizing one or more chronological sequences of the one or more recorded ultrasound signals; analyzing the digitized one or more chronological sequences; and classifying the analyzed one or more chronological sequences into defect classifications using at least one neural network that is trained based on a deep learning model that uses training data including scanning acoustic microscope scans of one or more control samples of the same type as the sample.

Abstract: A method for operating a scanning acoustic microscope. The method including: scanning a sample in an X-Y plane by a transducer unit having one or more transducers. Wherein the scanning includes: moving the transducer unit in the X direction for a linear scanning of the sample; after the linear scanning of the sample by the transducer unit, displacing the transducer unit in the Y direction by a displacement increment; and varying a size of the displacement increment of the transducer unit in the Y direction for the scanning of the sample.