Application of Distributed Arithmetic in Image and ECG Signal Processing
Anu Mary Sunny, Naveen Varghese Jacob · 2017 International Conference on Current Trends in Computer, Electrical, Electronics and Communication (CTCEEC) · 2017
The core of many DSP applications involve convolution which was previously implemented by Multiply and Accumulate operations or MAC. It requires a number of multipliers and accumulators. The use of multipliers and accumulators result in faster execution but it also results in an increase in cost. Also the number of multipliers and adders are limited. Hence a new technique known as Distributed Arithmetic (DA) was proposed. It is basically a multiplier-less concept utilizing Lookup Table (LUT). It is used when one of the operand is fixed. The input enters into a serial register which is used to access the LUT. To get the address from the LUT we consider the bit positions and get the values of inputs by that bit position. The output from the lookup table is shifted accordingly and the shifted results are added together to form the final result. Hence it basically involves accessing the lookup table, shift and add operation. After implementing the DA logic and comparing it with the convolution scheme, we apply this concept in Discrete Wavelet Transform (DWT) of an image and ECG signal by using Haar filter coefficient.