Conversion of a sub-pixel format data to another sub-pixel data format
First Claim
1. A method of limiting filter kernel divisors in a filter kernel to a value designed to simplify hardware implementations, comprising:
- calculating areas for filter coefficients using floating point arithmetic;
dividing each said filter coefficient by a total area of a rendering area to produce a first product;
multiplying each said first product by a divisor to produce a filter sum;
completing a binary search to find a round off point for said filter sum; and
converting said filter coefficients to integers using said round off point.
6 Assignments
0 Petitions
Accused Products
Abstract
A method of producing a plurality of filter kernels comprised of filter coefficients for use in a sub-pixel rendering operation comprises calculating a plurality of filter coefficients for each filter kernel by dividing a spatial area of an input image that is overlapped by a portion of a spatial rendering area by a total area of the spatial rendering area using floating point arithmetic. The method further comprises multiplying each filter coefficient by a divisor to produce a filter product such that a sum of all filter products produces a filter sum that equals the divisor. Then a binary search operation is performed to find a round off point for the filter sum such that when each filter coefficient is converted to an integer, a sum of the filter coefficients equals the divisor. The filter coefficients are then converted to integers using the round off point.
221 Citations
10 Claims
-
1. A method of limiting filter kernel divisors in a filter kernel to a value designed to simplify hardware implementations, comprising:
-
calculating areas for filter coefficients using floating point arithmetic; dividing each said filter coefficient by a total area of a rendering area to produce a first product; multiplying each said first product by a divisor to produce a filter sum; completing a binary search to find a round off point for said filter sum; and converting said filter coefficients to integers using said round off point. - View Dependent Claims (2, 3, 4)
-
-
5. A method of producing a plurality of filter kernels for use in a sub-pixel rendering operation, said sub-pixel rendering operation converting input image data specified in a first sub-pixel format and indicating an input image to output image data specified in a second sub-pixel format, the method comprising:
-
calculating a plurality of filter coefficients for each filter kernel by dividing a spatial area of said input image that is overlapped by a portion of a spatial rendering area by a total area of the spatial rendering area using floating point arithmetic;
each of said filter coefficients being an element of the filter kernel;multiplying each said filter coefficient by a divisor to produce a filter kernel element product such that a sum of all filter kernel element products produces a filter sum that equals the divisor; performing a binary search operation to find a round off point for said filter sum such that when each filter coefficient is converted to an integer, a sum of the filter coefficients equals said divisor; and converting said filter coefficients to integers using said round off point. - View Dependent Claims (6, 7, 8, 9, 10)
-
Specification