DocumentCode :
3429487
Title :
Directed spreading activation in multiple layers for low-level feature extraction
Author :
Valan, A. Arul ; Yegnanarayana, B.
Author_Institution :
Dept. of Comput. Sci. & Eng., Indian Inst. of Technol., Madras, India
fYear :
1992
fDate :
16-20 Nov 1992
Firstpage :
563
Abstract :
Spreading activation neural networks have been proposed in literature. The paper proposes a directed spreading activation neural network model which performs a large number of early vision tasks. It is shown how directed two-dimensional (2D) diffusion followed by detection of local maxima can effectively perform feature extraction, feature centroid determination and feature clustering all on multiple scales in a purely data-driven manner. The feature map, which is the result of this directed spreading activation process can be used in learning and recognition of 2D object shapes from their binary patterns invariant to affine transformations
Keywords :
feature extraction; neural nets; 2D object shapes; affine transformations; binary patterns; directed 2D diffusion; directed spreading activation; early vision tasks; feature centroid determination; feature clustering; feature extraction; feature map; learning; local maxima; Computer science; Computer vision; Detectors; Feature extraction; Humans; Intelligent networks; Neurons; Pattern recognition; Retina; Shape;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Singapore ICCS/ISITA '92. 'Communications on the Move'
Print_ISBN :
0-7803-0803-4
Type :
conf
DOI :
10.1109/ICCS.1992.254888
Filename :
254888
Link To Document :
بازگشت