The
global motion occurring due to the heart beat makes great disturbance to obtain
the visual alignment among the vessel structure shown in the Coronary Cine
Angiogram (CCA) frames. According to this paper introduces a Hierarchical
Region based Template Matching (HRTM) technique to reduce the global
motion from the CCA to maintain the visual alignment among the Coronary
Arteries in the frames. This proposed motion reduction technique is
efficient and it reconstructs the CCA by reducing the background motion as desired.
There are mainly four steps available in their proposed Hierarchical
Region based Template Matching (HRTM) motion reduction technique: pre-processing,
motion estimation, frame alignment and motion eliminated video creation. The
objective of the pre-processing stage is to apply possible image enhancement
techniques to obtain the required visual quality of the vessel structures recorded
in CCAs. A median filter with kernel size 3×3 was applied to the CCA frames
as a noise removal technique. Motion estimation process of the proposed method
is based on template matching image processing technique and mainly consists of
two phases namely; (i) Template selection and (ii) applying HRTM. Template
selection is done as an interactive activity using the first frame of the input
CCA to be processed. The second phase of the motion reduction process is the HRTM.
It is an iterative process and runs up to the last frame of the CCA to be processed.
The objective of the HRTM method is to efficiently compute the frame
translation vectors of the CCA to be processed. When compared to the image registration
algorithms, template matching is simpler and it is not based on a complex mathematical
model. Image registration techniques do not provide reliable results always for
CCAs. Experimental results of this proposed method have clearly shown how to
minimize the long visual gaps of the vessel structure among the frames using
template matching technique.
W.S.WAJIRAMALI
No comments:
Post a Comment