MEASURING HEIGHT DIFFERENCE IN PATTERNS ON SEMICONDUCTOR WAFERS

    公开(公告)号:US20180336675A1

    公开(公告)日:2018-11-22

    申请号:US15982918

    申请日:2018-05-17

    Abstract: An improved technique for determining height difference in patterns provided on semiconductor wafers uses real measurements (e.g., measurements from SEM images) and a height difference determination model. In one version of the model, a measurable variable of the model is expressed in terms of a function of a change in depth of shadow (i.e. relative brightness), wherein the depth of shadow depends on the height difference as well as width difference between two features on a semiconductor wafer. In another version of the model, the measurable variable is expressed in terms of a function of a change of a measured distance between two characteristic points on the real image of a periodic structure with respect to a change in a tilt angle of a scanning electron beam.

    TECHNIQUE FOR INSPECTING SEMICONDUCTOR WAFERS

    公开(公告)号:US20180336671A1

    公开(公告)日:2018-11-22

    申请号:US15982876

    申请日:2018-05-17

    Abstract: A height of a pattern on a semiconductor wafer is determined by comparing a measured image of the pattern with a predicted image of the pattern, as produced by a shadow model. An estimated height of the pattern is provided as an input to the shadow model. The shadow model produces occluding contours that are used to generate predicted images. A set of predicted images are generated, each predicted image being associated with an estimated height. The estimated height corresponding to the predicted image most closely matching with the measured image is used as the height calculated by the shadow model.

    DEFECT DETECTION USING A MACHINE LEARNING ALGORITHM

    公开(公告)号:US20250166154A1

    公开(公告)日:2025-05-22

    申请号:US18518025

    申请日:2023-11-22

    Abstract: There are provided systems and methods comprising obtaining a first inspection image informative of a first area of a specimen acquired by an examination tool, feeding at least the first inspection image to a machine learning algorithm configured to determine, for each given pixel of a plurality of pixels of the first inspection image, or for each given group of pixels of a plurality of groups of pixels of the first inspection image, one or more given parameters of a given model informative of pixel intensity distribution, for said each given pixel or given group of pixels, using at least some of the one or more given parameters, or the given model associated with the one or more given parameters, and measured pixel intensity of the given pixel or group of pixels, to determine whether a defect is present in the given pixel or in the given group of pixels.

Patent Agency Ranking