Аннотация
This paper describes the architecture of a neural network for 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 the first-layer neuron operation are given. The proposed architecture fulfills the stated tasks on edge selection.
Язык оригинала | английский |
---|---|
Страницы (с-по) | 414-422 |
Число страниц | 9 |
Журнал | Optoelectronics, Instrumentation and Data Processing |
Том | 55 |
Номер выпуска | 4 |
DOI | |
Состояние | Опубликовано - 1 июл 2019 |