Abstract: A system has detectors configured to receive a beam of light reflected from a wafer. For example, three detectors may be used. Each of the detectors is a different channel. Images from the detectors are combined into a pseudo-color RGB image. A convolutional neural network unit (CNN) can receive the pseudo-color RGB image and determine a size of a defect in the pseudo-color RGB image. The CNN also can classify the defect into a size category.

Abstract: A location of grid lines in an image of a laser-annealed semiconductor wafer is determined. An area covered by the grid lines can be filled using a new gray value. The new gray value can be based on a second gray scale value of a neighborhood around the area. The neighborhood is outside of the area covered by the grid lines.

Abstract: The correlation of optical images with SEM images includes acquiring a full optical image of a sample by scanning the sample with an optical inspection sub-system, storing the full optical image, identifying a location of a feature-of-interest present in the full optical image with an additional sources, acquiring an SEM image of a portion of the sample that includes the feature at the identified location with a SEM tool, acquiring an optical image portion at the location identified by the additional source, the image portions including a reference structure, correlating the image portion and the SEM image based on the presence of the feature-of-interest and the reference structure in both the image portions and the SEM image, and transferring a location of the feature-of-interest in the SEM image into the coordinate system of the image portion of the full optical image to form a corrected optical image.

Abstract: A system has detectors configured to receive a beam of light reflected from a wafer. For example, three detectors may be used. Each of the detectors is a different channel. Images from the detectors are combined into a pseudo-color RGB image. A convolutional neural network unit (CNN) can receive the pseudo-color RGB image and determine a size of a defect in the pseudo-color RGB image. The CNN also can classify the defect into a size category.

Abstract: The present disclosure describes methods, systems, and articles of manufacture for performing a defect inspection of a die image using adaptive care areas (ACAs). The use of ACAs solve the problem of handling rotations of components that require rotating care areas; handling the situation where each care area requires its own rotation, translation, or affine transformation; and the situation of decoupling intensity differences caused by defects or process variation from intensity differences caused by size variations.

Abstract: A system for defect detection and analysis is provided. The system may include an inspection sub-system and a controller including a memory and one or more processors. The inspection sub-system may include an illumination source and one or more detectors configured to acquire control patch images of defects of a control specimen along one or more detector channels. The one or more processors may be configured to train a defect classifier using the control patch images and known parameters associated with the defects of the control specimen. The inspection sub-system may be further configured to acquire patch images of identified defects on an additional specimen. The one or more processors may be configured to determine parameters of the identified defects using the defect classifier.

Abstract: A system for defect detection and analysis is provided. The system may include an inspection sub-system and a controller including a memory and one or more processors. The inspection sub-system may include an illumination source and one or more detectors configured to acquire control patch images of defects of a control specimen along one or more detector channels. The one or more processors may be configured to train a defect classifier using the control patch images and known parameters associated with the defects of the control specimen. The inspection sub-system may be further configured to acquire patch images of identified defects on an additional specimen. The one or more processors may be configured to determine parameters of the identified defects using the defect classifier.

Abstract: A die-die inspection image can be aligned using a method or system configured to receive a reference image and a test image, determine a global offset and rotation angle from local sections on the reference image and test image, and perform a rough alignment de-skew of the test image prior to performing a fine alignment.

Abstract: Methods and systems for determining parameter(s) of a process to be performed on a specimen are provided. One system includes one or more computer subsystems configured for determining an area of a defect detected on a specimen. The computer subsystem(s) are also configured for correlating the area of the defect with information for a design for the specimen and determining a spatial relationship between the area of the defect and the information for the design based on results of the correlating. In addition, the computer subsystem(s) are configured for automatically generating a region of interest to be measured during a process performed for the specimen with a measurement subsystem based on the spatial relationship.

Abstract: The correlation of optical images with SEM images includes acquiring a full optical image of a sample by scanning the sample with an optical inspection sub-system, storing the full optical image, identifying a location of a feature-of-interest present in the full optical image with an additional sources, acquiring an SEM image of a portion of the sample that includes the feature at the identified location with a SEM tool, acquiring an optical image portion at the location identified by the additional source, the image portions including a reference structure, correlating the image portion and the SEM image based on the presence of the feature-of-interest and the reference structure in both the image portions and the SEM image, and transferring a location of the feature-of-interest in the SEM image into the coordinate system of the image portion of the full optical image to form a corrected optical image.

Abstract: The correlation of optical images with SEM images includes acquiring a full optical image of a sample by scanning the sample with an optical inspection sub-system, storing the full optical image, identifying a location of a feature-of-interest present in the full optical image with an additional sources, acquiring an SEM image of a portion of the sample that includes the feature at the identified location with a SEM tool, acquiring an optical image portion at the location identified by the additional source, the image portions including a reference structure, correlating the image portion and the SEM image based on the presence of the feature-of-interest and the reference structure in both the image portions and the SEM image, and transferring a location of the feature-of-interest in the SEM image into the coordinate system of the image portion of the full optical image to form a corrected optical image.

Abstract: A die-die inspection image can be aligned using a method or system configured to receive a reference image and a test image, determine a global offset and rotation angle from local sections on the reference image and test image, and perform a rough alignment de-skew of the test image prior to performing a fine alignment.

Abstract: The present disclosure describes methods, systems, and articles of manufacture for performing a defect inspection of a die image using adaptive care areas (ACAs). The use of ACAs solve the problem of handling rotations of components that require rotating care areas; handling the situation where each care area requires its own rotation, translation, or affine transformation; and the situation of decoupling intensity differences caused by defects or process variation from intensity differences caused by size variations.

Abstract: Methods and systems for determining parameter(s) of a process to be performed on a specimen are provided. One system includes one or more computer subsystems configured for determining an area of a defect detected on a specimen. The computer subsystem(s) are also configured for correlating the area of the defect with information for a design for the specimen and determining a spatial relationship between the area of the defect and the information for the design based on results of the correlating. In addition, the computer subsystem(s) are configured for automatically generating a region of interest to be measured during a process performed for the specimen with a measurement subsystem based on the spatial relationship.

Abstract: Various embodiments for detecting defects on a wafer are provided. Some embodiments include matching a template image, in which at least some pixels are associated with regions in the device having different characteristics, to output of an electron beam inspection system and applying defect detection parameters to pixels in the output based on the regions that the pixels in the output are located within to thereby detect defects on the wafer.

Abstract: Various embodiments for classifying defects detected on a wafer are provided. One method includes acquiring an electron beam image generated by a defect review tool for a location of a defect detected on a wafer by a wafer inspection tool. The method also includes determining a classification of the defect based on at least the electron beam image and without input from a user. The method may also include feeding back the classification results to the wafer inspection tool and optimizing the parameters of the tool to maximize sensitivity to the defects of interest.

Abstract: Various embodiments for classifying defects detected on a wafer are provided. One method includes acquiring an electron beam image generated by a defect review tool for a location of a defect detected on a wafer by a wafer inspection tool. The method also includes determining a classification of the defect based on at least the electron beam image and without input from a user. The method may also include feeding back the classification results to the wafer inspection tool and optimizing the parameters of the tool to maximize sensitivity to the defects of interest.

Abstract: The correlation of optical images with SEM images includes acquiring a full optical image of a sample by scanning the sample with an optical inspection sub-system, storing the full optical image, identifying a location of a feature-of-interest present in the full optical image with an additional sources, acquiring an SEM image of a portion of the sample that includes the feature at the identified location with a SEM tool, acquiring an optical image portion at the location identified by the additional source, the image portions including a reference structure, correlating the image portion and the SEM image based on the presence of the feature-of-interest and the reference structure in both the image portions and the SEM image, and transferring a location of the feature-of-interest in the SEM image into the coordinate system of the image portion of the full optical image to form a corrected optical image.

Abstract: One embodiment relates to an apparatus for automated inspection of a semiconductor substrate. Processor-executable code is configured to control the stage electronics to move the substrate using a continuous motion in a substrate-translation direction and is configured to control the beam to scan it across the surface of the substrate and collect corresponding image data, scan lines of the scan being along a scan-line direction perpendicular to the substrate-translation direction. Processor-executable code is also configured to select from the image data two cells of the repeating pattern on the surface of the substrate, the two cells being displaced from each other by one or multiple cell heights in the scan-line direction. Finally, processor-executable code is configured to generate a difference image by subtracting image data from said two cells on a pixel-by-pixel basis. Other embodiments, aspects and features are also disclosed.

Abstract: A method for monitoring the stability of an inspection or processing of a substrate, a substrate inspection system and a processor readable medium are disclosed. One or more images of one or more portions of the substrate may be obtained from an inspection tool. Image quality information may be extracted from the one or more images. The image quality information may be analyzed to monitor stability of the inspection tool and/or to determine variation of a process performed on the substrate.