Applied Materials Israel Limited

Elad Cohen

Eyal Neistein

Moshe Amzaleg

Lior Katz

Yuri Feigin

Rafael Bistritzer

Ariel Shkalim

Mark Geshel

Ilan Ben-Harush

Shahar Arad

Denis Simakov

Limor Martin

Shlomo Tubul

Victor Egorov

There is provided a system of examination of a semiconductor specimen, comprising a processor and memory circuitry configured to obtain, for each given candidate defect of a plurality of candidate defects in an image of the specimen, a given area of the given candidate defect in the image, obtain a reference image, perform a segmentation of at least part of the reference image, to determine, for each given candidate defect, first reference areas in the reference image matching a given reference area corresponding to the given area, select among the first reference areas, a plurality of second reference areas, obtain a plurality of corresponding second areas in the image, and use data informative of a pixel intensity of the second areas and data informative of a pixel intensity of the given area to determine whether the given candidate defect corresponds to a defect.

Detection of defects using a computationally efficient segmentation approach

A system and method for specimen examination, the system comprising a processing and memory circuitry (PMC) for: obtaining an image of at least a part of a specimen, the image acquired by an examination tool; receiving one or more characteristics of a defect of interest and a location of interest associated therewith; modifying within the image one or more pixels corresponding to the location of interest, wherein the modification is provided in accordance with a characteristic of the defect of interest, thereby planting the defect of interest into the image; processing the modified image to detect locations of potential defects of the specimen in accordance with a detection recipe; and determining whether the detected locations include the location of interest. Subject to the location of interest not being detected, modifying the detection recipe to enable detecting the planted defect of interest at the location of interest.

Detecting defects in a semiconductor specimen

A method and system for detecting defects in a specimen, the method comprising: obtaining an image comprising a plurality of pixels of a specimen part; processing the image according to a detection recipe to derive information related to potential defects in the specimen, the information comprising a first data set informative of first locations identified, in accordance with the detection recipe as locations of potential defects, and a second data set informative of second locations not identified as locations of potential defects; receiving data specifying targeted locations of interest within the part of the specimen; when the first data set is not informative of each targeted location, generating a third data set by adding to the first data set information related to the missing targeted location from the second data set, the information bearing an indication that it corresponds to a targeted location; and outputting the third data set.

Detecting targeted locations in a semiconductor specimen

There are provided a system and method of examination on a specimen, the method comprising: obtaining an inspection image of a die and generating a defect map using one or more reference images; selecting a plurality of defect candidates from the defect map; and generating for each defect candidate, a respective modified inspection image patch, comprising: extracting an image patch surrounding the defect candidate respectively from the inspection image and each reference image; and modifying the inspection image patch, comprising: estimating noise representative of intensity variations on the inspection image patch, the noise including a first type of noise representative of a polynomial relation between the inspection and reference image patches, and a second type of noise representative of a spatial anomaly in the inspection image patch, and removing at least one of the first and second types of noise from the inspection image patch based on the estimated noise.

Method of examination of a specimen and system thereof

There are provided a system and method of defect detection on a specimen, the method comprising: performing partitioning for each of one or more portions of a first die; receiving one or more noise maps indicative of noise distribution on second images captured for one or more portions of a second die; performing segmentation for each noise map in runtime, the segmentation for a given noise map including: calculating a score for each region, the given noise map aligned with the regions and each region is associated with noise data aligned therein, the score for a given region calculated at least based on the noise data associated therewith; and associating each region with one segmentation label of a predefined set of segmentation labels indicative of noise levels based on the score, thereby obtaining a set of segments each corresponding to one or more regions associated with the same segmentation label.

Method of defect detection on a specimen and system thereof

There are provided system and method of detecting defects on a specimen, the method comprising: capturing a first image from a first die and obtaining one or more second images; receiving: i) a first set of predefined first descriptors each representing a type of DOI, and ii) a second set of predefined second descriptors each representing a type of noise; generating at least one difference image based on difference between pixel values of the first image and pixel values derived from the second images; generating at least one third image, comprising: computing a value for each given pixel of at least part of the at least one difference image based on the first and second sets of predefined descriptors, and surrounding pixels centered around the given pixel; and determining presence of defect candidates based on the at least one third image and a predefined threshold.

Method of defect detection and system thereof

There are provided system and method of generating an examination recipe usable for examining a specimen, the method comprising: capturing images from dies and obtaining noise map indicative of noise distribution on the images; receiving design data representative of a plurality of design groups each having the same design pattern; calculating a group score for each given design group, the group score calculated based on the noise data associated with the given design group and a defect budget allocated for area of the given design group; providing segmentation related to the dies, comprising: associating design groups with segmentation labels indicative of different noise levels based on the group score, thereby obtaining a set of die segments each corresponding to one or more design groups associated with the same segmentation label and segmentation configuration data; and generating an examination recipe using the segmentation configuration data.

Growing community of inventors

Beer Sheva, Israel

Elad Cohen