Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 1

finger alphabet Related Publications

1 Key Frames Extraction for Sign Language Video Analysis and Recognition

Authors: Jaroslav Polec, Petra Heribanová, Tomáš Hirner

Abstract:

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.

Keywords: video, Quality, Sign Language, MSE, metric, key frame, MSAD, SSIM, VQM, finger alphabet

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1665