TITLE:
Fuzzy Logic Recursive Gaussian Denoising of Color Video Sequences via Shot Change Detection
AUTHORS:
V. Sasikala, N. UmaMaheswari, R. Venkatesh
KEYWORDS:
Keyframe Restoration, Between Frame Restoration, Motion Detection
JOURNAL NAME:
Circuits and Systems,
Vol.7 No.8,
June
15,
2016
ABSTRACT: A new technique using
fuzzy in a recursive fashion is presented to deal with the Gaussian noise. In
this technique, the keyframes and between frames are identified initially and
the keyframe is denoised efficiently. This frame is compared with the between
frames to remove noise. To do so the frames are partitioned into blocks; the
motion vector is calculated; also the difference is measured using the
dissimilarity function. If the blocks have no motion vectors in the block, the
block of value is copied to the between frames otherwise the difference between
the blocks is calculated and this value is filtered with temporal filtering.
The blocks are processed in overlapping manner to avoid the blocking effect and
also to reduce the additional edges created while processing. The simulation
results show that the peak signal to noise ratio of the new technique is
improved up to 1 dB and also the execution time is greatly reduced.