Abstract:
The Discrete Cosine Transform ( DCT) is commonly used
for the compression of images due to its property of high power
compaction. Multiplication is a key fundamental stage in the
computation of Discrete Cosine Transform (DCT) of an image.
In this paper, a novel low-power, high-speed run-time
configurable image compression technique based on 2DDiscrete Cosine Transform (DCT) and conventional carry lookahead adder is proposed. In the proposed implementation of
2D-DCT using configurable booth multiplier, tuning of
accuracy and the size of the compressed image is realized by
masking the carry propagation of configurable adder at runtime. We also calculated the various performance metrics such
as Mean Square Error (MSE) and Peak Signal to Noise Ratio
(PSNR) of conventional multiplier based 2D-DCT and
proposed designs
