Noise enhanced histograms
AssigneeImagination Technologies Limited
InventorTim Lee
Life of this patent
Estimating the term…
Abstract
Apparatus for binning an input value into one of a plurality of bins which collectively represent a histogram of input values, each of the plurality of bins representing a corresponding range of input values, the apparatus comprising: an input for receiving an input value; a noise source configured to generate an error value according to a predetermined noise distribution; and a binning controller configured to mix the received input value with the error value so as to generate a modified input value and to allocate the modified input value to the bin corresponding to that modified input value.
Claims19
Apparatus for binning an input value into one of a plurality of bins for use by one or more processing algorithms, each of the plurality of bins representing at least one corresponding value, the apparatus comprising:
- a binning controller configured to mix an input value with an error value so as to generate a modified input value and to allocate the modified input value to the bin corresponding to that modified input value, wherein the error value is generated according to a predetermined noise distribution having a variance which is substantially equal to the average width of the bins or the width of the largest bin.
A non-transitory machine-readable storage medium having encoded thereon machine-readable code which when executed causes the generation of an apparatus for binning an input value into one of a plurality of bins for use by one or more processing algorithms, each of the plurality of bins representing at least one corresponding value, the apparatus comprising:
- a binning controller configured to mix an input value with an error value so as to generate a modified input value and to allocate the modified input value to the bin corresponding to that modified input value, wherein the error value is generated according to a predetermined noise distribution having a variance which is substantially equal to the average width of the bins or the width of the largest bin.
A method for binning an input value into one of a plurality of bins for use by one or more processing algorithms, each of the plurality of bins representing at least one corresponding value, the method comprising:
- mixing an input value with an error value so as to generate a modified input value;
- and
- allocating the modified input value to the bin corresponding to that modified input value;
- wherein the error value is generated according to a predetermined noise distribution having a variance which is substantially equal to the average width of the bins or the width of the largest bin.
Dependencies are inferred from the claim text.