Open AccessFPGA Implementation of a Novel Gaussian Filter Using Power Optimized Approximate Adders
Author(s) -
Jamshid M Basheer,
Murugesh
Publication year - 2018
Publication title -
indonesian journal of electrical engineering and computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.241
H-Index - 17
eISSN - 2502-4760
pISSN - 2502-4752
DOI - 10.11591/ijeecs.v11.i3.pp1048-1059
Subject(s) - gaussian filter , gaussian blur , adder , field programmable gate array , computer science , pixel , gaussian , smoothing , filter (signal processing) , gaussian noise , algorithm , median filter , computer hardware , electronic engineering , artificial intelligence , image processing , computer vision , image (mathematics) , engineering , image restoration , telecommunications , physics , quantum mechanics , latency (audio)
Smoothing filters are essential for noise removal and image restoration. Gaussian filters are used in many digital image and video processing systems. Hence the hardware implementation of the Gaussian filter becomes a reliable solution for real time image processing applications. This paper discusses the implementation of a novel Gaussian smoothing filter with low power approximate adders in Field Programmable Gate Array (FPGA). The proposed Gaussian filter is applied to restore the noisy images in the proposed system. Original test images with 512x512 pixels were taken and divided in to 4x4 blocks with 256x256 pixels. The proposed technique has been applied and the performance metrics were measured for various simulation criteria. The proposed algorithm is also implemented using approximate adders, since approximate adders had been recognized as a reliable alternate for error tolerant applications in circuit based metrics such as power, area and delay where the accuracy may be considered for trade off.