Analyzing the efficiency of allocation of segment boundaries using neural networks
A. V. Kugaevskikh1,2,3, A. A. Sogreshilin4
1Novosibirsk State Technical University, Novosibirsk, Russia
2Novosibirsk State University
3Institute of Automation and Electrometry, Siberian Branch, Russian Academy of Sciences
4Novosibirsk State University, Novosibirsk, Russia
Keywords: выделение краёв, фильтр Габора, косинусная мера, нейронные сети, вейвлет сомбреро, гиперболический тангенс, edge selection, Gabor filter, cosine measure, neural networks, wavelet sombrero, hyperbolic tangent
Abstract
This paper describes a neural network architecture of edge detection. Different filters for first-layer neurons are compared. Neural network learning based on a cosine measure algorithm shows much worse results than an error backpropagation algorithm. Optimal parameters for first-layer neuron operation are given. The proposed architecture fulfills the stated tasks on edge selection.
|
