Summary
the 2014 International Symposium on Nonlinear Theory and its Applications
2014
Session Number:D3L-C
Session:
Number:D3L-C1
Application of Delayed CNN templates for gesture control
Andras Horvath, Tamas Roska,
pp.858-861
Publication Date:2014/9/14
Online ISSN:2188-5079
DOI:10.34385/proc.46.D3L-C1
PDF download (619.4KB)
Summary:
Spatial-temporal event detection is a crucial task and it is usually difficult to be handled effciently with current algorithms and devices. It has been shown how delayed CNN templates can be applied in machine-vision and spatial-temporal classification. We can observe similar structures, the analogy of delayed type templates in the retina as well, which performs well and effciently in image processing tasks. Delayed type templates can provide us with even more flexibilities and possibilities in new applications including frameless detection of motion features. In this article we show how cellular neural networks with delayed type templates can be used for the identification of gestures, movement. The detection is done by using continuous dynamics without cutting the input flow into frames.