1. An apparatus to be used to illuminate an object having an essentially flat surface along a first dimension that extends along a first direction, the apparatus for providing light that is directed onto the flat surface in a direction that has at least some component in the first direction, the apparatus comprising:
a light source that forms a plurality of initial light rays that are directable along a direction essentially perpendicular to the first direction; and
a guidance member positioned proximate the light source that intercepts and redirects the initial light rays such that redirected rays exit the guidance member along paths that form angles with respect to the initial rays and which have a lateral component aligned with the first direction and so that the redirected rays subtend an illuminated portion of the flat surface.
2. The apparatus of claim 1 wherein the light source is positioned such that the initial rays are essentially perpendicular to the flat surface.
3. The apparatus of claim 1 wherein the guidance member redirects the rays such that the redirected rays are essentially parallel to each other.
4. The apparatus of claim 1 wherein the light source is a line light source having a line surface from which light emanates, the source positioned such that the line surface is parallel to the flat surface and extends in the first direction.
5. The apparatus of claim 1 also for collecting images of the illuminated portion of the flat surface and further including a camera having a field of view and positioned such that the field of view includes at least a segment of the illuminated portion of the flat surface.
6. The apparatus of claim 1 wherein the flat surface has a second dimension perpendicular to the first dimension and wherein the source is positioned such that the initial rays are angled so as to have a longitudinal component aligned with the second direction.
7. The apparatus of claim 1 wherein the guidance member is a prismatic film.
8. The apparatus of claim 7 wherein the source is a line source having a line surface from which light emanates, the source positioned such that the line surface is essentially parallel to the flat surface of the object and extends in the first direction.
9. The apparatus of claim 8 wherein the object is a sheet of material wrapped around a role such that the first dimension is along the width of the roll and a second dimension is perpendicular to the first dimension and, wherein, the source is positioned essentially parallel to the first dimension.
10. The apparatus of claim 9 wherein the light source has a length dimension along its length that is essentially identical to the first dimension and wherein the light source and guidance member are offsetable with respect to the flat surface along the first direction such that the redirected rays subtend the flat surface along essentially the entire first dimension.
11. The apparatus of claim 9 wherein the initial rays have a longitudinal component in the second direction.
12. The apparatus of claim 11 also for collecting images of the illuminated portion of the flat surface and further including a camera having a field of view and positioned such that the field of view includes at least a segment of the illuminated portion of the flat surface.
13. The apparatus of claim 1 wherein the guidance member is positioned at least in part between the source and the flat surface.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. An image processing method comprising:
a clipping step of clipping a plurality of partial images from an image based on a predetermined criterion,
a first calculating step of calculating difference values of pixel values between a target pixel and surrounding pixels surrounding the target pixel in the partial image clipped in the clipping step, a deciding step of deciding parameter values for each of the surrounding pixels based on identification information that identifies the partial image from among the plurality of the partial images clipped in the clipping step and the difference values,
a second calculating step of calculating a feature amount corresponding to the target pixel using the parameter values decided in the deciding step, and
an obtaining step of obtaining feature amounts for each of the partial images by calculating the feature amount in the first calculating step, the deciding step, and the second calculating step, using each pixel in the partial images as the target pixels.
2. An image processing method comprising:
a clipping step of clipping a partial image from an image,
a first calculating step of calculating difference values of pixel values between a target pixel and surrounding pixels surrounding the target pixel in the partial image,
a deciding step of deciding parameter values for each of the surrounding pixels based on types of features to be detected and the difference values,
a second calculating step of calculating a feature amount corresponding to the target pixel using the parameter values decided in the deciding step, and
an obtaining step of obtaining a feature amount of the partial image by calculating the feature amount in the first calculating step, the deciding step, and the second calculating step, using each pixel in the partial image as the target pixels.
3. The method according to claim 1, wherein the relative position relationship between the surrounding pixels and the target pixel is further used in the deciding step in order to decide the parameter values for the surrounding pixels.
4. The method according to claim 2, wherein
in the clipping step, a plurality of partial images are clipped from the image based on a predetermined criterion, and
in the deciding step, parameter values for respective surrouding pixels are decided further using identification information that shows which of the plurality of the partial images clipped in the clipping step that partial image is.
5. The method according to claim 1, further comprising:
a quantizing step of obtaining a quantization value by quantizing the difference values in a predetermined quantization level,
wherein in the deciding step, the quantization value is used for deciding the parameter values for the surrounding pixels.
6. The method according to claim 5, wherein in the quantizing step, the difference values are quantized in two quantization levels.
7. The method according to claim 1, wherein the parameter values are powers of two.
8. The method according to claim 1, wherein in the obtaining step, the result of adding all the parameter values decided in the deciding step for one target pixel is set as the feature amount for the target pixel.
9. A pattern detection method that detects a detection target pattern from an image based on the feature amount of the processing region image obtained using the image processing method according to claim 1.
10. A pattern recognition method that determines which pattern that is registered in advance the image corresponds to based on the feature amount of the processing region image obtained by using the image processing method according to claim 1.
11. An image processing device comprising:
a clipping unit that clips a plurality of partial images from an image based on a predetermined criterion,
a first calculating unit that calculates difference values of pixel values between a target pixel and surrounding pixels surrounding the target pixel in the partial image clipped by the clipping means,
a deciding unit that decides parameter values for each of the surrounding pixels based on identification information that identifies the partial image from among the plurality of the partial images clipped by the clipping means and the difference values,
a second calculating unit that calculates a feature amount corresponding to the target pixel using the parameter values decided by the deciding means, and
an obtaining unit that obtains feature amounts for each of the partial images by calculating the feature amount by the first calculating means, the deciding means, and the second calculating means, using each pixel in the partial images as the target pixels.
12. An image processing device comprising:
a clipping unit that clips a partial image from an image,
a first calculating unit that calculates difference values of pixel values between a target pixel and surrounding pixels surrounding the target pixel in the partial image,
a deciding unit that decides parameter values for each of the surrounding pixels based on types of features to be detected and the difference values,
a second calculating unit that calculates a feature amount corresponding to the target pixel using the parameter values decided by the deciding means, and
an obtaining unit that obtains a feature amount of the partial image by calculating the feature amount by the first calculating means, the deciding means, and the second calculating means, using each pixel in the partial image as the target pixels.
13. A computer-readable storage medium in which is stored a program for causing a computer to execute the image processing method according to claim 1.
14. A computer-readable storage medium in which is stored a program for causing a computer to execute the pattern detection method according to claim 9.
15. A computer-readable storage medium in which is stored a program for causing a computer to execute the pattern recognition method according to claim 10.