Ensemble of deep learning models for defect review in high volume manufacturing

    公开(公告)号:US12211196B2

    公开(公告)日:2025-01-28

    申请号:US18305287

    申请日:2023-04-21

    Abstract: Methods and systems for detecting defects in images of a specimen are provided. One system includes a computer subsystem configured for training an ensemble of deep learning models by altering one or more parameters of the ensemble until a pseudo-loss function determined based on output of the ensemble is approximately equal to but not greater than 0.5. The computer subsystem is also configured for detecting defects in runtime specimen images by inputting the runtime specimen images into the trained ensemble and generating runtime labels for the runtime specimen images indicating if a defect has been detected in the runtime specimen images based on outputs of the deep learning models in the trained ensemble.

    SYSTEM AND METHOD FOR REDUCING SAMPLE NOISE USING SELECTIVE MARKERS

    公开(公告)号:US20230408422A1

    公开(公告)日:2023-12-21

    申请号:US18139637

    申请日:2023-04-26

    CPC classification number: G01N21/93 G01N21/91 G01N2201/0636

    Abstract: An inspection is disclosed. The system may include an illumination source configured to illuminate a sample. The sample may include a multi-layer stack including a plurality of layers formed of a first material and at least a second material. The first material may include a light transmissive material and the second material may include light reflective material. A top layer within the stack may include absorptive markers configured to selectively bind to the top layer. The absorptive markers may be configured block light transmission through layers positioned below the top layer. The top layer may include photoluminescent markers configured to selectively bind to the light reflective material to enhance a feature of interest on the sample. The system may include detectors configured to detect photoluminescent emission emitted by the photoluminescent markers and optical elements may be configured to direct the photoluminescent emission to the detectors.

    MULTI-MODE OPTICAL INSPECTION
    3.
    发明公开

    公开(公告)号:US20230314336A1

    公开(公告)日:2023-10-05

    申请号:US18128125

    申请日:2023-03-29

    CPC classification number: G01N21/8851 G06T7/001 H01L22/12

    Abstract: An inspection system may develop an inspection recipe by generating N inspection images of a preliminary sample with one or more optical inspection sub-systems associated with N different optical inspection modes, generating probabilities that each of the locations of the preliminary sample are in background or defect classes using a classifier with the inspection images from at least some combinations of a number M of the optical inspection modes, where M is greater than one and less than N and corresponds to a number of the optical inspection modes to include in the inspection recipe, and selecting one of the combinations of M of the optical inspection modes based on a metric describing a distinction between the background and defect classes. The inspection system may further identify defects on a test sample using M inspection images generated with the selected combination of M of the optical inspection modes.

    System and method for reducing sample noise using selective markers

    公开(公告)号:US12298254B2

    公开(公告)日:2025-05-13

    申请号:US18139637

    申请日:2023-04-26

    Abstract: An inspection is disclosed. The system may include an illumination source configured to illuminate a sample. The sample may include a multi-layer stack including a plurality of layers formed of a first material and at least a second material. The first material may include a light transmissive material and the second material may include light reflective material. A top layer within the stack may include absorptive markers configured to selectively bind to the top layer. The absorptive markers may be configured block light transmission through layers positioned below the top layer. The top layer may include photoluminescent markers configured to selectively bind to the light reflective material to enhance a feature of interest on the sample. The system may include detectors configured to detect photoluminescent emission emitted by the photoluminescent markers and optical elements may be configured to direct the photoluminescent emission to the detectors.

Patent Agency Ranking