Abstract:
|
In this paper, a new method to compute the image
histogram is presented, along with the image maximum
and minimum values. It is intended for highly paral-
lel architectures such as the ones found in Focal Plane
Processors (FPP). This new approach exploits this par-
allelism relying on the privatization technique to avoid
the memory collision problem, while the bin frequency
is obtained through image bitwise manipulation. Unlike
traditional privatization techniques, our method exhibits
a trade-o between processing time and bin size. That
is, it can be adapted as a power-of-two bin size histogram
and the computation time decreases exponentially as the
bin size is reduced on each power of two, allowing high
computational
exibility. |