1. A method of image processing, said method comprising:
classifying each of a plurality of pixels of an image according to a predetermined segmentation of a color space; and
performing an exposure control operation based on a result of said classifying each of a plurality of pixels, wherein the image is based on a raw image captured by a sensor, and wherein the predetermined segmentation of the color space is based on a plurality of predicted responses of the sensor.
2. The method of image processing according to claim 1, wherein the predetermined segmentation of the color space is based on a plurality of predicted responses of the sensor to human skin surfaces.
3. The method of image processing according to claim 1, wherein said classifying each of a plurality of pixels according to a predetermined segmentation includes assigning each of the plurality of pixels, according to a relation between the predetermined segmentation and a color value of the pixel, to one among a first pixel class and a second pixel class, and
wherein said performing an exposure control operation includes assigning each of a plurality of blocks of the image to one among a first block class and a second block class according to a relation between (A) the number of pixels in the block that are assigned to the first pixel class and (B) a threshold value, and
wherein said performing an exposure control operation includes calculating an exposure control factor based on an average luminance value of the blocks assigned to the first block class.
4. The method of image processing according to claim 1, wherein said performing an exposure control operation includes calculating an exposure control factor based on a result of said classifying each of a plurality of pixels and changing, according to the exposure control factor, a luminance value of each of a plurality of pixels of the image.
5. The method of image processing according to claim 1, wherein said performing an exposure control operation includes:
according to a result of said classifying each of a plurality of pixels, assigning each of a plurality of blocks of the image to one among a plurality of block classes; and
based on an average luminance value of the blocks of one of the block classes, calculating an exposure control factor.
6. The method of image processing according to claim 5, wherein said performing an exposure control operation includes changing, according to the exposure control factor, a luminance value of each of a plurality of pixels of the image.
7. The method of image processing according to claim 1, wherein said classifying each of a plurality of pixels of the image includes calculating values of elements of a pixel classification map, and
wherein said method includes performing a noise reduction operation on the pixel classification map, and
wherein said performing an exposure control operation is based on the noise-reduced pixel classification map.
8. A data storage medium having machine-executable instructions describing the method of image processing according to claim 1.
9. An apparatus comprising:
a sensor configured to capture a raw image;
a pixel classifier configured to classify, according to a predetermined segmentation of a color space, pixels of an image based on the raw image; and
an exposure controller configured to perform, based on the pixel classifications, an exposure control operation,
wherein the predetermined segmentation of a color space is based on a plurality of predicted responses of the sensor.
10. The apparatus according to claim 9, wherein the predetermined segmentation of the color space is based on a plurality of predicted responses of the sensor to human skin surfaces.
11. The apparatus according to claim 9, wherein said pixel classifier is configured to assign each of the plurality of pixels, according to a relation between the predetermined segmentation and a color value of the pixel, to one among a first pixel class and a second pixel class, and
wherein said exposure controller is configured to assign each of a plurality of blocks of the image to one among a first block class and a second block class according to a relation between (A) the number of pixels in the block that are assigned to the first pixel class and (B) a threshold value, and
wherein said exposure controller is configured to calculate an exposure control factor based on an average luminance value of the blocks assigned to the first block class.
12. The apparatus according to claim 9, wherein said exposure controller is configured to calculate an exposure control factor based on the pixel classifications and to change, according to the exposure control factor, a luminance value of each of a plurality of pixels of the image.
13. The apparatus according to claim 9, wherein said exposure controller includes an image block classifier configured to assign, according to the pixel classifications, each of a plurality of blocks of the image to one among a plurality of block classes, and
wherein said exposure controller includes a calculator configured to calculate, based on an average luminance value of the blocks of one of the block classes, an exposure control factor.
14. The apparatus according to claim 13, wherein said exposure controller is configured to change, according to the exposure control factor, a luminance value of each of a plurality of pixels of the image.
15. The apparatus according to claim 9, wherein said pixel classifier is configured to calculate values of elements of a pixel classification map, and
wherein said apparatus is configured to perform a noise reduction operation on the pixel classification map, and
wherein said exposure controller is configured to perform the exposure control operation based on the noise-reduced pixel classification map.
16. The apparatus of claim 9, wherein the apparatus comprises a camera.
17. The apparatus of claim 9, wherein the apparatus comprises a wireless communications device.
18. An image processing system, comprising:
means for classifying each of a plurality of pixels of an image according to a predetermined segmentation of a color space; and
means for performing an exposure control operation based on a result of said classifying each of a plurality of pixels, wherein the image is based on a raw image captured by a sensor, and wherein the predetermined segmentation of the color space is based on a plurality of predicted responses of the sensor.
19. The image processing system of claim 18, wherein the predetermined segmentation of the color space is based on a plurality of predicted responses of the sensor to human skin surfaces.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
What is claimed is:
1. Pattern inspection equipment comprising:
a measured data generation unit for generating measured data from patterns that have been delineated on a sample according to design data; and
a reference data generation unit for generating reference data used to inspect the patterns, the reference data generation unit having:
a multi-valued pattern development circuit for developing the design data into gradational data expressed in multiple gradation levels;
a fine adjustment circuit for finely adjusting pattern edges in the multi-level gradational data; and
a fault decision circuit for comparing the measured data with the reference data.
2. The pattern inspection equipment of claim 1, wherein the fine adjustment circuit is a size modification circuit for shifting the side of patterns constructed with the gradational data according to a maximum value detected in a specified area in the gradational data.
3. The pattern inspection equipment of claim 2, wherein the size modification circuit detects an oblique side in the gradational data.
4. The pattern inspection equipment of claim 2, wherein the size modification circuit comprising:
a first pattern data reversing circuit connected to an input end of the size modification circuit, for reversing the gradational data;
a maximum detector connected to the first pattern data reversing circuit, for detecting a maximum value in a specified area;
a pattern enlarger connected to the first pattern data reversing circuit and maximum detector; and
a second pattern data reversing circuit connected to the pattern enlarger, for reversing the output of the pattern enlarger.
5. The pattern inspection equipment of claim 3, wherein the size modification circuit comprising:
a first pattern data reversing circuit connected to an input end of the size modification circuit, for reversing the gradational data;
a maximum detector connected to the first pattern data reversing circuit, for detecting a maximum value in a specified area;
an oblique side detector connected to the first pattern data reversing circuit, for detecting an oblique side;
a pattern enlarger connected to the first pattern data reversing circuit, maximum detector, and oblique side detector; and
a second pattern data reversing circuit connected to the pattern enlarger, for reversing the output of the pattern enlarger.
6. The pattern inspection equipment of claim 3, wherein the size modification circuit recognizes pattern shapes in the gradational data and separately processes vertical or horizontal sides and oblique sides in the gradational data.
7. The pattern inspection equipment of claim 2, wherein the size modification circuit isotropically enlarges and reduces size of the pattern constructed with the gradational data irrespective of pattern shapes in the gradational data.
8. The pattern inspection equipment of claim 1, wherein the fine adjustment circuit is a corner rounding circuit for rounding the corners of patterns constructed with the gradational data.
9. The pattern inspection equipment of claim 8, wherein the corner rounding circuit has at least a corner detector for converting the gradational data into binary data and detecting the corners of patterns constructed with the gradational data according to the binary data.
10. The pattern inspection equipment of claim 9, wherein the corner rounding circuit further comprises:
a corner size decision circuit for deciding the size of each of the corners according to the binary data;
a rounding data generation circuit for generating rounding data for the corners according to information provided by the corner size decision circuit; and
a rounding processor for rounding the corners according to the rounding data and the gradational data.
11. The pattern inspection equipment of claim 8, wherein the corner rounding circuit optionally changes the roundness of a given corner in the pattern constructed with the gradational data according to an external instruction and the type of the corner.
12. A method for inspecting patterns, comprising the steps of:
(a) developing design data used to delineate the patterns on a sample into gradational data expressed in multiple gradation levels;
(b) finely adjusting the edges of patterns constructed with the gradational data and generating reference data;
(c) generating measured data from the actual patterns delineated on the sample; and
(d) comparing the measured data with the reference data.
13. The method of claim 12, wherein the finely adjusting step includes a modification step of detecting a maximum value in a specified area in the gradational data and modifying sizes of patterns constructed with the gradational data accordingly.
14. The method of claim 13, wherein the modification step detects an oblique side in the pattern constructed with the gradational data.
15. The method of claim 13, wherein the modification step including the steps of:
a first reversing step of determining whether or not the gradational data must be enlarged or reduced, and if it must be reduced, reversing the gradational data;
detecting a maximum value in a specified area in the gradational data;
referring to a lookup table according to the maximum value and a given size modification quantity and determining a new value to be set to the central pixel of the specified area;
setting the new value to the central pixel of the specified area to modify a size of a pattern constructed with the gradational data; and
a second reversing step of reversing the new value if the gradational data has been reversed by the first inversion step.
16. The method of claim 14, wherein the modification step additionally includes the steps of:
detecting an inclination of an oblique side;
referring to a given lookup table according to the maximum value and a preset size modification quantity and determining a new size modification quantity;
referring to the new size modification quantity and a given threshold value, to determine a new value to be set to the central pixel including the oblique side; and
setting the new value to the central pixel including the oblique side and shifting the position of the oblique side.
17. The method of claim 13, wherein the modification step recognizes pattern shapes in the pattern constructed with the gradational data and separately processes vertical or horizontal sides and oblique sides constructed with the gradational data.
18. The method of claim 13, wherein the modification process isotropically enlarges and reduces the size of a pattern constructed with the gradational data irrespective of pattern shapes.
19. The method of claim 12, wherein the finely adjusting step includes a corner rounding step of rounding corners in the pattern constructed with the gradational data.
20. The method of claim 19, wherein the corner rounding step includes the steps of:
converting the gradational data into binary data; and
detecting corners in the pattern constructed with the gradational data according to the binary data.
21. The method of claim 20, wherein the corner rounding step additionally includes the steps of:
deciding the size of each of the corners according to the binary data;
generating rounding data for the corners according to information provided by the deciding step; and
rounding the corners according to the rounding data and gradational data.
22. The method of claim 19, wherein the corner rounding step optionally changes the roundness of a given corner in the pattern constructed with the gradational data according to an external instruction and the type of the corner.
23. A storage medium storing a program comprising the steps of:
(a) developing design data used to delineate patterns on a sample into gradational data expressed in multiple gradation levels;
(b) finely adjusting patterns in the gradational data and generating reference data;
(c) generating measured data from the actual patterns delineated on the sample; and
(d) comparing the measured data with the reference data.
24. The storage medium of claim 23, wherein the finely adjusting step detects a maximum value in a specified area in the gradational data and modifies a size of a pattern constructed with the gradational data accordingly.
25. The storage medium of claim 23, wherein the finely adjusting step rounds corners in a pattern constructed with the gradational data.