Image Processing Program, Image Processing Device, and Image Processing Method

Patent metadata

Field	Value
Publication number	US-2024404043-A1
Application number	US-202418797711-A
Country	US
Kind code	A1
Filing date	Aug 8, 2024
Priority date	Jun 13, 2019
Publication date	Dec 5, 2024
Grant date	—

Abstract

The purpose of the present invention is to provide a computer program for achieving die-to-database inspection at high speed and with few false reports, and a semiconductor inspection device using the same. To achieve this purpose, the present invention proposes: a computer program comprising an encoder layer that is configured to determine the features of a design data image, and a decoder layer that is configured to generate, on the basis of a variation in an image (inspection target image) obtained by photographing an inspection target pattern, a statistic pertaining to the brightness values of pixels from feature values output by the encoder layer, wherein die-to-database inspection with few false reports can be achieved by comparing the inspection target image and the statistic obtained from the decoder layer and pertaining to the brightness values, and thereby detecting a defect region in the image; and a semiconductor inspection device using the same.

First claim

1 . An image processing program for performing an inspection on a sample by using reference data of the sample and input data pertaining to the sample, which is stored in a storage medium the image processing program causing a processor to implement:
receiving the reference data; calculating a statistic indicating probability distribution of a value that is able to be taken by the input data on the basis of the reference data, depending on the input data.

2 . The image processing program according to claim 1 , wherein the reference data is design data image and the input data is photographed image corresponding to the design data image,
further causing a processor to implement: calculating a feature value pertaining to the sample on the basis of the design data image, depending on the photographed image; and calculating the statistic is calculating indicating probability distribution of a value that is able to be taken by the input data on the basis of the feature value.

3 . The image processing program according to claim 2 , further causing a processor to implement:
the feature value is design information indicating to which of the wiring portion and a space portion each pixel on the design data image belongs, and design information including peripheral regions such as the vicinity of an edge and the vicinity of a corner of the wiring.

4 . The image processing program according to claim 2 , wherein statistic defines probability distribution of a brightness value that can be taken by each pixel on the corresponding photographed image.

5 . The image processing program according to claim 2 , further causing a processor to implement:
evaluating the sample on the basis of a region of the probability distribution.

6 . The image processing program according to claim 2 , wherein calculating the statistic using parameters which are adjusted by model creation processing.

7 . The image processing program according to claim 6 , further causing a processor to implement:
determining threshold-value range of the brightness value of each pixel for each pixel on the basis of the statistic.

8 . The image processing program according to claim 7 , further causing a processor to implement:
determining whether or not the brightness value of the photographed image is within the threshold-value range for each pixel by using the determined threshold-value range and the photographed image.

9 . The image processing program according to claim 8 , further causing a processor to implement:
displaying pixel on the screen as a defective region, if there is a pixel having a brightness value out of the threshold-value range.

10 . An image processing device for performing an inspection on a sample by using reference data of the sample and input data pertaining to the sample, the image processing device comprising:
receiving unit to receive the reference data; calculating unit to calculate a statistic indicating probability distribution of a value that is able to be taken by the input data on the basis of the reference data, depending on the input data.

11 . The image processing device according to claim 10 , wherein the reference data is design data image and the input data is photographed image corresponding to the design data image, further comprising:
calculating a feature value unit to pertain to the sample on the basis of the design data image, depending on the photographed image; and wherein the calculating the feature value unit to calculate the statistic is calculating indicating probability distribution of a value that is able to be taken by the input data on the basis of the feature value.

12 . The image processing device according to claim 11 , wherein the feature value is design information indicating to which of the wiring portion and a space portion each pixel on the design data image belongs, and design information including peripheral regions such as the vicinity of an edge and the vicinity of a corner of the wiring.

13 . The image processing device according to claim 11 , wherein statistic defines probability distribution of a brightness value that can be taken by each pixel on the corresponding photographed image.

14 . The image processing device according to claim 10 , further comprising:
evaluating unit to evaluate the sample on the basis of a region of the probability distribution.

15 . An image processing method for performing an inspection on a sample by using reference data of the sample and input data pertaining to the sample, the image processing method comprising steps of:
receiving the reference data; calculating a statistic indicating probability distribution of a value that is able to be taken by the input data on the basis of the feature value, depending on the input data.

16 . The image processing method according to claim 15 , wherein the reference data is design data image and the input data is photographed image corresponding to the design data image,
further comprising steps of: calculating a feature value pertaining to the sample on the basis of the design data image, depending on the photographed image; and calculating the statistic is calculating indicating probability distribution of a value that is able to be taken by the input data on the basis of the feature value.

17 . The image processing method according to claim 16 , further comprising steps of:
the feature value is design information indicating to which of the wiring portion and a space portion each pixel on the design data image belongs, and design information including peripheral regions such as the vicinity of an edge and the vicinity of a corner of the wiring.

18 . The image processing method according to claim 16 , wherein statistic defines probability distribution of a brightness value that can be taken by each pixel on the corresponding photographed image.

19 . The image processing method according to claim 15 , further comprising steps of:
evaluating the sample on the basis of a region of the probability distribution.

20 . A defect detection system for detecting a defect of a sample by using design data of the sample and input data which is related inspection, the defect detection system comprising:
means for receiving the design data; means for calculating a statistic indicating probability distribution of a value that is able to be taken by the input data on the basis of the design data; evaluating the sample on the basis of a region of the probability distribution.

Assignees

• Hitachi High Tech Corp

Inventors

• Ouchi Masanori
• Shinoda Shinichi
• Toyoda Yasutaka
• Yumiba Ryou
• Shindo Hiroyuki

Classifications

• G06T2207/30141

  Printed circuit board [PCB] · CPC title

• G06T2207/30148

  Semiconductor; IC; Wafer · CPC title

• G06V10/476

  using statistical shape modelling, e.g. point distribution models · CPC title

• G06T9/005

  Statistical coding, e.g. Huffman, run length coding · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title