DocumentCode :
1649218
Title :
Saliency map model based on the edge images of natural scenes
Author :
An, Kwang-Hwan ; Lee, Minho ; Shin, Jang-Kyoo
Author_Institution :
Sch. of Electron. & Electr. Eng., Kyungpook Nat. Univ., Taegu, South Korea
Volume :
1
fYear :
2002
fDate :
6/24/1905 12:00:00 AM
Firstpage :
1023
Lastpage :
1027
Abstract :
In this paper, we propose a new saliency map model to find a saliency point based on an edge image rather than a complex natural scene. We use independent component analysis to find a filter that can generate a saliency point from edge information with a gray scale. Computer experimental results show that the proposed saliency map model successfully generates the saliency points, of which the results are very considerable
Keywords :
edge detection; filtering theory; neural nets; ICA; edge images; filter; gray scale; independent component analysis; natural scenes; neural nets; saliency map model; Computer vision; Detectors; Electronic mail; Humans; Intelligent sensors; Layout; Machine vision; Retina; Signal processing; Visual system;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
ISSN :
1098-7576
Print_ISBN :
0-7803-7278-6
Type :
conf
DOI :
10.1109/IJCNN.2002.1005616
Filename :
1005616
Link To Document :
بازگشت