Reduced complexity and blur technique for an electronic lighting system
View Patent ↗Digital blurring of an image is carried out by blurring using a linear or piecewise continuous blurring function. The blurring function blurs a rectangular portion of an image so that the blurring can be embodied by vertical blurring followed by halls on pull blow. Blurring is done by getting on portion of the line of pixels, adding and dividing by the number of pixels. All the columns are blurred, followed by all of the rows being blurred. The columns and rows can be blurred at the same time to maximize the number of cache hits.
1. A method, comprising:
using a processor that is programmed for carrying out a blur on an image using a blurring kernel, where said processor is programmed for using said blurring kernel at different areas across an image from one edge to another edge; and
using values to blur edge pixels of the image based on areas that are not part of the image.
2. A method as in claim 1 , wherein said blurring kernel has a single weighting value for all values within the kernel.
3. A method as in claim 1 , wherein said blurring kernel has first and second weighting values for all values in the kernel.
4. A method as in claim 1 , wherein said blur is carried out on a rectangular portion of the image.
5. A method as in claim 4 , wherein said rectangular portion is a square portion.
6. A method as in claim 4 , wherein said carrying out a blur comprises first blurring in a first direction, and second blurring in a second orthogonal direction.
7. A method as, in claim 6 , wherein said first blurring and said second blurring are carried out serially, with said first blurring being carried out and then said second blurring being carried out.
8. A method as in claim 6 , wherein said first blurring and said second blurring are carried out substantially simultaneously.
9. A method as in claim 7 , wherein said first blurring, which is carried out first, is carried out in a vertical direction.
10. A method, comprising:
obtaining an image;
using a processor that is programmed for digitally blurring the image using a rectangular blurring area to blur the image by using the program in the processor for moving a blurring kernel across the image where said blurring kernel blurs different areas of the image at different times by summing the image within the kernel at said different areas; and
said processor-programmed for using a value other than from the image to blur edge areas of the image.
11. A method as in claim 10 , wherein said rectangular blurring area is carried out in two separate passes.
12. A method as in claim 10 , wherein said rectangular blurring area is blurred by using a vertical pass for vertical blurring and a horizontal pass for horizontal blurring.
13. A method as in claim 10 , wherein said digitally blurring comprises using a noncontinuous blurring kernel to blur pixels of the image.
14. A method as in claim 13 , wherein said noncontinuous blurring kernel is a blurring kernel which has a single weighting value for each value within the kernel.
15. A method as in claim 13 , wherein said noncontinuous blurring kernel is a blurring kernel which has two separate weighting values for different values within the kernel.
16. A method as in claim 10 , wherein said rectangular blurring area is blurred in two orthogonal directions which are calculated substantially simultaneously.
17. A method as in claim 13 further comprising taking steps which improve a number of cache hits during said blurring.
18. A method, comprising:
obtaining an image; and using a processor which is programmed for digitally blurring the image using a rectangular blurring area to blur the image, said processor programmed for taking steps which improve a number of cache hits during said blurring, and wherein said taking steps comprises adjusting an order of pixel processing to improve a number of cache hits.
19. A method, comprising:
obtaining an image; and using a processor which is programmed for blurring the image by shifting a blurring window across the image, where said blurring window is programmed to change values of some, but not all, pixels within the window during each said shifting, said processor programmed for maintaining a sum of pixels in a cache memory, and using said sum for a subsequent shifting.
20. A method as in claim 19 , wherein said blurring comprises changing the values of only two pixels during each said shifting.
21. A method as in claim 20 , wherein said two pixels comprise edge pixels on both sides of the window.
22. A method as in claim 19 , wherein said blurring comprises changing the values of only four pixels during each shifting.
23. A method as in claim 19 , wherein said shifting comprises first shifting across the image in a first direction, and second shifting across the image in a second direction, substantially orthogonal to said first direction.
24. A method as in claim 19 , wherein said blurring comprises blurring a substantially rectangular area.
25. A method as in claim 1 , wherein said area that is not part of the image is a value indicative of black.
26. A method as in claim 1 , further comprising arranging pixels in cache memory in a way that improves a number of cache hits during said blur.
27. A method as in claim 10 , wherein said value other than from the image is a value indicative of black.
28. A method as in claim 18 , wherein said digitally blurring comprises moving a kernel across the image where said blurring kernel blurs different areas of the image at different times by summing the part of the image which in the kernel at said different areas.
29. A method as in claim 18 , wherein said blurring comprises using a value other than within the image at to blur edges of the image.
30. A method as in claim 29 , wherein said value is a value indicative of black.