%0 Journal Article
	%A Jaroslav Polec and  Petra Heribanová and  Tomáš Hirner
	%D 2013
	%J International Journal of Electronics and Communication Engineering
	%B World Academy of Science, Engineering and Technology
	%I Open Science Index 78, 2013
	%T Key Frames Extraction for Sign Language Video Analysis and Recognition
	%U https://publications.waset.org/pdf/2672
	%V 78
	%X In this paper we proposed a method for finding video
frames representing one sign in the finger alphabet. The method is
based on determining hands location, segmentation and the use of
standard video quality evaluation metrics. Metric calculation is
performed only in regions of interest. Sliding mechanism for finding
local extrema and adaptive threshold based on local averaging is used
for key frames selection. The success rate is evaluated by recall,
precision and F1 measure. The method effectiveness is compared
with metrics applied to all frames. Proposed method is fast, effective
and relatively easy to realize by simple input video preprocessing
and subsequent use of tools designed for video quality measuring.
	%P 611 - 615