DocumentCode :
2192269
Title :
Image data preparation for intelligent security systems
Author :
Sheraizin, S. ; Itzikowitz, S.
Author_Institution :
Comput. Sci. Dept., Coll. of Manage., Rishon Lezion, Israel
fYear :
2008
fDate :
3-5 Dec. 2008
Firstpage :
198
Lastpage :
202
Abstract :
In this paper, we present a new complex approach for image data preparation (IDP) that is optimized for robust an object of interest (OOI) detection intended for intelligent (unmanned) security systems. The objectives of the image processing are: improvement of an OOI detection as well as emphasizing the object specific features for high representative descriptors generation. Our IDP method and algorithms are based on sensation model of the human eye-brain interaction. Following this model and existing object detection algorithms the suggested IDP method takes into account the relatively large OOI dimensions and applies contrast enhancement and object edges emphasizing for these objects. The method is based on optimization criteria providing an object low false detection. The algorithms are effectively applied in an intelligent person tracking security systems. It is shown that the developed method can substantially improve object detection.
Keywords :
image enhancement; object detection; security of data; contrast enhancement; human eye-brain interaction; image data preparation; image processing; intelligent security system; object detection algorithm; Artificial intelligence; Computer security; Data security; Humans; Image edge detection; Image sensors; Intelligent systems; Interference; Object detection; Robustness; Adaptive control; Artificial intelligence; Contrast; Image objects detection; Matched filter;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electrical and Electronics Engineers in Israel, 2008. IEEEI 2008. IEEE 25th Convention of
Conference_Location :
Eilat
Print_ISBN :
978-1-4244-2481-8
Electronic_ISBN :
978-1-4244-2482-5
Type :
conf
DOI :
10.1109/EEEI.2008.4736687
Filename :
4736687
Link To Document :
بازگشت