Pattern inspection method and apparatus
First Claim
1. A pattern inspection method comprising:
- magnifying and taking a color image including a plurality of pixels;
generating a first color information of each of the plurality of pixels, wherein the first color information includes three color coordinate components, red (R), green (G), and blue (B), of an RGB color space;
converting the first color information of each of the plurality of pixels into a second color information including three color coordinate components, hue (H), saturation (S), and brightness (B) of an HSB color space;
generating a gray-scale image in accordance with the brightness (B);
generating a binary image from the gray-scale image by regarding one of the plurality of pixels having a brightness (B) of less than a predetermined threshold as black pixel and another one of the plurality of pixels having a brightness (B) of more than the predetermined threshold as a white pixel;
detecting an inspection object from the binary image by obtaining coordinate data of at least two of the plurality of pixels overlapped by the inspection object; and
judging the inspection object by comparing a reference saturation (S) of a preset non-defective reference color information with a saturation (S) of the at least two of the plurality of pixels.
0 Assignments
0 Petitions
Accused Products
Abstract
A color image of an inspection object is taken by an imaging means capable of taking a color image to obtain color information of an RGB color space. A gray-scale image of a color component of the RGB color space or another color space is generated, and the inspection object is detected by a pattern recognition technique. Alternatively, a binary image is generated from the generated gray-scale image, and the inspection object is detected by performing pattern recognition on the binary image. Color data of a pixel occupied by the detected inspection object is compared with color data of a non-defective inspection object which is previously prepared to judge whether or not the inspection object is defective. In addition, this judgment result is reflected in another manufacturing step through a network and product quality is improved.
-
Citations
10 Claims
-
1. A pattern inspection method comprising:
-
magnifying and taking a color image including a plurality of pixels; generating a first color information of each of the plurality of pixels, wherein the first color information includes three color coordinate components, red (R), green (G), and blue (B), of an RGB color space; converting the first color information of each of the plurality of pixels into a second color information including three color coordinate components, hue (H), saturation (S), and brightness (B) of an HSB color space; generating a gray-scale image in accordance with the brightness (B); generating a binary image from the gray-scale image by regarding one of the plurality of pixels having a brightness (B) of less than a predetermined threshold as black pixel and another one of the plurality of pixels having a brightness (B) of more than the predetermined threshold as a white pixel; detecting an inspection object from the binary image by obtaining coordinate data of at least two of the plurality of pixels overlapped by the inspection object; and judging the inspection object by comparing a reference saturation (S) of a preset non-defective reference color information with a saturation (S) of the at least two of the plurality of pixels. - View Dependent Claims (2)
-
-
3. A pattern inspection method comprising:
-
magnifying and taking a color image including a plurality of pixels; generating a first color information of each of the plurality of pixels, wherein the first color information includes three color coordinate components, red (R), green (G), and blue (B), of an RGB color space; converting the first color information of each of the plurality of pixels into a second color information including three color coordinate components, hue (H), saturation (S), and brightness (B) of an HSB color space; generating a gray-scale image in accordance with the brightness (B); generating a binary image from the gray-scale image by regarding one of the plurality of pixels having a brightness (B) of less than a predetermined threshold as black pixel and another one of the plurality of pixels having a brightness (B) of more than the predetermined threshold as a white pixel; detecting an inspection object from the binary image by obtaining coordinate data of at least two of the plurality of pixels overlapped by the inspection object; calculating a mean value of the saturation (S) of at least two of the plurality of pixels overlapped by the inspection object, and comparing the mean value of the saturation (S) in each inspection object with a preset saturation (S), and judging the inspection object. - View Dependent Claims (4)
-
-
5. A pattern inspection method comprising:
-
magnifying and taking a color image including a plurality of pixels; generating a first color information of each of the plurality of pixels, wherein the first color information includes three color coordinate components, red (R), green (G), and blue (B), of an RGB color space; converting the first color information of each of the plurality of pixels into a second color information including three color coordinate components, hue (H), saturation (S), and brightness (B) of an HSB color space; taking brightness (B) which is suitable to specify a position of an inspection object from the second color information; specifying the position of the inspection object based on a characteristic amount of an image obtained using the brightness (B); and judging the inspection object by comparing a reference saturation (S) of preset non-defective reference color information with a saturation (S) of the specified position. - View Dependent Claims (6)
-
-
7. A pattern inspection method comprising:
-
magnifying and taking a color image including a plurality of pixels; generating a first color information of each of the plurality of pixels, wherein the first color information includes three color coordinate components, red (R), green (G), and blue (B), of an RGB color space; converting the first color information of each of the plurality of pixels into a second color information including three color coordinate components, hue (H), saturation (S), and brightness (B) of an HSB color space; taking brightness (B) which is suitable to specify a position of an inspection object from the second color information; specifying the position of the inspection object based on a characteristic amount of an image obtained using the brightness (B); calculating a mean value of the saturation (S) of at least two of the plurality of pixels overlapped by the object; and comparing the mean value of the saturation (S) in each inspection object with a preset saturation (S), and judging the inspection object. - View Dependent Claims (8)
-
-
9. A method for manufacturing semiconductor device comprising:
-
forming an inspection object over a substrate; after forming the inspection object over the substrate, magnifying and taking a color image including a plurality of pixels; generating a first color information of each of the plurality of pixels, wherein the first color information includes three color coordinate components, red (R), green (G), and blue (B), of an RGB color space; converting the first color information of each of the plurality of pixels into a second color information including three color coordinate components, hue (H), saturation (S), and brightness (B) of an HSB color space; taking brightness (B) which is suitable to specify a position of the inspection object from the second color information; specifying the position of the inspection object based on a characteristic amount of an image obtained using the brightness (B); and judging the inspection object by comparing a reference saturation (S) of preset non-defective reference color information with a saturation (S) of the specified position. - View Dependent Claims (10)
-
Specification