Conversion of a sub-pixel format data to another sub-pixel data format

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.