US 7,024,041 B2Granted

Pattern inspection apparatus and method

AssigneeDainippon Screen Mfg. Co., Ltd.

InventorYasushi Sasa

Life of this patent

Estimating the term…

Loading patent…

Abstract

A marginal distribution feature extraction unit 20 sequentially focuses on each pixel in a reference image and the corresponding pixel in an inspection image, and computes a marginal distribution feature value indicative of the spatial variation in pixel values in the focus pixel neighborhood in both images. Based on this marginal distribution feature value, a tolerance image generation selection unit 26 sets a tolerance range for the reference image or inspection image focus pixel with the less spatial variation. A target image selection unit 30 selects the image comprising pixels from both images for which a tolerance range is not set as a target image. Referencing the set tolerance ranges, a comparison operator 34 compares each pixel in the target image and tolerance image, and outputs a difference Sub representing how far the pixel values of the target image are from the respective tolerance range. A defect determination circuit 38 then outputs data indicating the pixels corresponding to a defect based on a difference map containing these difference Sub values.

Claims10

Dependent claims

A pattern inspection apparatus for generating a difference map representing differences between an inspection image and a reference image by comparing the inspection image and the reference image pixel by pixel, and detecting defects in an inspected object based on the difference map, the inspection image being a multivalued image obtained by photographing the inspected object with a specific pattern formed thereon and the reference image being a multivalued image representing the specific pattern as a reference standard, the pattern inspection apparatus comprising:

a marginal distribution feature value calculation unit for sequentially focusing on each pixel in the inspection image and a pixel at a corresponding position in the reference image, and calculating a first marginal distribution feature value indicative of spatial variation in pixel values in a neighborhood of the focus pixel in the inspection image, and a second marginal distribution feature value indicative of spatial variation in pixel values in a neighborhood of the focus pixel in the reference image;
a selection unit for selecting the inspection image focus pixel or the reference image focus pixel having less spatial variation in neighborhood pixel values as a tolerance pixel based on the first and second marginal distribution feature values, and selecting the other focus pixel as a target pixel;
a tolerance range calculation unit for calculating as a tolerance range a range of pixel values to be used as a value of the tolerance pixel allowing error in a coincidence evaluation of the inspection image focus pixel and reference image focus pixel;
and
a comparison unit for calculating a difference value indicative of a difference between the target pixel and tolerance pixel by comparing the target pixel with the tolerance pixel within the tolerance range, and storing the difference value to a specific memory;
the difference map being created by writing the difference values to the specific memory.

3 more elements

A pattern inspection method for generating a difference map representing differences between an inspection image and a reference image by comparing the inspection image and the reference image pixel by pixel, and detecting defects in an inspected object based on the difference map, the inspection image being a multivalued image obtained by photographing the inspected object with a specific pattern formed thereon and the reference image being a multivalued image representing the specific pattern as a reference standard, the pattern inspection method comprising:

a marginal distribution feature value calculation step of sequentially focusing on each pixel in the inspection image and a pixel at a corresponding position in the reference image, and calculating a first marginal distribution feature value indicative of spatial variation in pixel values in a neighborhood of the focus pixel in the inspection image, and a second marginal distribution feature value indicative of spatial variation in pixel values in a neighborhood of the focus pixel in the reference image;
a selection step of selecting the inspection image focus pixel or the reference image focus pixel having less spatial variation in neighborhood pixel values as a tolerance pixel based on the first and second marginal distribution feature values, and selecting the other focus pixel as a target pixel;
a tolerance range calculation step of calculating as a tolerance range a range of pixel values to be used as a value of the tolerance pixels allowing error in a coincidence evaluation of the inspection image focus pixel and reference image focus pixel;
and
a comparison step of calculating a difference value indicative of a difference between the target pixel and tolerance pixel by comparing the target pixel with the tolerance pixel within the tolerance, and storing the difference value to a specific memory;
the difference map being created by writing the difference values to the specific memory.

3 more elements

Dependencies are inferred from the claim text.

Facts

Application: 10/216,320Filed 12 Aug 2002
Priority: JP 2001-24535413 Aug 2001
Published: US 2003/0031356 A113 Feb 2003
Granted: 4 Apr 2006
Term ends: Not estimatedThe source records don’t support an estimate.

Classification8 codes

G06T 7/001
Industrial image inspection: using an image reference approach
G01N 21/95607
Inspecting patterns on the surface of objects: using a comparative method
G06F 18/28
Analysing: determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
G06T 2207/30141
Industrial image inspection: printed circuit board [PCB]