Title :
Curvature and orientation estimation by neuronal structures
Author :
Tanaka, Júlia Sawaki ; Manoel, Edson Tadeu Monteiro ; Costa, Luciano Da Fontoura
Author_Institution :
Cybern. Vision Res. Group, Sao Paulo Univ., Brazil
Abstract :
The paper presents a simple model of curvature and orientation estimation by neural networks where a pair of neurons is used to approximate the partial differential operators needed for curvature and orientation estimation. The influence of neuronal morphometry in the estimation of curvature and orientation is investigated and discussed. In addition, the biological plausibility of the model is discussed, and simulation results are presented along a sequence of increasing plausibility and sophistication. Steerable filters are considered as a means to increase the model efficiency
Keywords :
computer vision; image recognition; neural nets; computer vision; curvature estimation; neural networks; neuronal morphometry; neurons; orientation estimation; partial differential operators; simulation; Biological neural networks; Biological system modeling; Cybernetics; Design for quality; Equations; Filters; Humans; Neural networks; Neurons; Shape;
Conference_Titel :
Computer Graphics and Image Processing, 2000. Proceedings XIII Brazilian Symposium on
Conference_Location :
Gramado
Print_ISBN :
0-7695-0878-2
DOI :
10.1109/SIBGRA.2000.883893
