Method and system for reducing artifacts in image detection
View Patent ↗An imager captures light reflecting off an object of interest and generates two or more images of the object. A controller identifies artifacts in one of the captured images and defines one or more non-interpretation regions in a binary image. The non-interpretation regions include pixels representative of the artifacts and do not include pixels representative of the object of interest. The controller performs pixel operations on the pixels in the binary image to reduce a number of artifacts in a final image.
1. A system, comprising:
an imager for capturing first and second images of an object using light reflected off the object, the first image including illuminated pixels that are part of an object of interest and the second image including illuminated pixels that are not part of the object of interest; and
a controller connected to the imager for defining and using one or more non-interpretation region based on one of the first image and second image to reduce a number of artifacts in a final image, wherein the controller is configured to:
compute a difference image between the first image and second image to remove the illuminated pixels that are not part of the object of interest, the difference image including illuminated pixels that are artifacts and the illuminated pixels that are part of the object of interest,
wherein the illuminated pixels that are artifacts in the difference image correspond to the illuminated pixels that are not part of the object of interest in the second image;
generate a binary image from the difference image;
define the one or more non-interpretation region in the binary image to include the illuminated pixels that are artifacts in the difference image and non-illuminated pixels that are in proximity to the illuminated pixels that are artifacts in the difference image,
wherein the illuminated pixels that are part of the object of interest in the difference image are excluded from the non-interpretation region; and
eliminate the illuminated pixels that are artifacts in the difference image which are included in the defined non-interpretation region.
2. The system of claim 1 , further comprising a source for emitting light towards the object.
3. The system of claim 1 , wherein the imager simultaneously captures the images of the object.
4. The system of claim 3 , wherein the images of the object comprise sub-frames.
5. The system of claim 1 , wherein the imager successively captures the images of the object.
6. The system of claim 1 , wherein the controller generates a first binary image from the first captured image.
7. The system of claim 6 , comprising a Boolean NAND operator which performs a Boolean NAND operation between the first binary image and the second binary image.
8. The system of claim 4 , wherein the controller computes a difference image between a first sub-frame image of the object and a second sub-frame image of the object.
9. The system of claim 8 , wherein the controller computes a binary image of the difference image.
10. The system of claim 9 , wherein the controller:
generates a first sub-frame binary image of one of the sub-frame images;
performs a dilation operation on one of the sub-frame images to generate a second sub-frame binary image; and
performs a Boolean logic operation with the first sub-frame binary image and the second sub-frame binary image.
11. The system of claim 10 , wherein the controller:
inverts the second sub-frame binary image; and
performs a Boolean NAND operation with the first sub-frame binary image and the inverted second sub-frame binary image.
12. The system of claim 10 , wherein the controller is configured to perform the Boolean logic operation by performing a Boolean NAND operation with the first sub-frame binary image and the second sub-frame binary image.