Reducing the Computational Complexity Of A 2d Gaussian Filter for Image Processing (An Overview)
D.Joseph Pushpa Raj, Poonam Singal · International journal of advance research, ideas and innovations in technology · 2017
The 2D Gaussian filter is one of the very useful techniques in image processing, this technique is very useful especially in image smoothing. Basically, the implementation of 2D Gaussian filter needs heavy computational resources, When this type of technique comes down to real time applications, efficiency in the implementation is vital. An obstacle for this is floating-point math representation, as it requires a heavy amount of computational power to achieve real-time image processing. On the other hand, a fixed-point approach is more satisfactory. By using fixed-point arithmetic, we increase the speed as well as efficiency in many ways. We also reduce the area of hardware by reducing the LUTs.