Hardware Implementation of an a-Trimmed Adaptive Median Mean Filter

In this paper, we provide and describe a hardware implementation of an <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\alpha$</tex> -trimmed adaptive median mean filter capable of restoring images affected by both Gaussian and impulse noise without causing blurriness in the reconstructed image. The algorithm was implemented on an FPGA device and achieved real-time processing capabilities of 50 frames/second for a frame of 1024x768 pixels while utilizing 3363 LUTs, 392 FFs, and 1 DSP block.