Analyzing the Efficiency of Segment Boundary Detection Using Neural Networks

A. V. Kugaevskikh; A. A. Sogreshilin

doi:10.3103/S8756699019040137

Analyzing the Efficiency of Segment Boundary Detection Using Neural Networks

Результат исследования: Научные публикации в периодических изданиях › статья

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	https://doi.org/10.3103/S8756699019040137
Состояние	Опубликовано - 1 июл 2019

Доступ к документу

10.3103/S8756699019040137

Link to publication in Scopus

Fingerprint Подробные сведения о темах исследования «Analyzing the Efficiency of Segment Boundary Detection Using Neural Networks». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать

Kugaevskikh, A. V., & Sogreshilin, A. A. (2019). Analyzing the Efficiency of Segment Boundary Detection Using Neural Networks. Optoelectronics, Instrumentation and Data Processing, 55(4), 414-422. https://doi.org/10.3103/S8756699019040137

@article{e3a2d16b7e9945fabb78cc06dc0158c8,

title = "Analyzing the Efficiency of Segment Boundary Detection Using Neural Networks",

abstract = "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.",

keywords = "cosine measure, edge selection, Gabor filter, hyperbolic tangent, Mexican hat wavelet, neural networks",

author = "Kugaevskikh, {A. V.} and Sogreshilin, {A. A.}",

year = "2019",

month = jul,

day = "1",

doi = "10.3103/S8756699019040137",

language = "English",

volume = "55",

pages = "414--422",

journal = "Optoelectronics, Instrumentation and Data Processing",

issn = "8756-6990",

publisher = "Allerton Press Inc.",

number = "4",

}

TY - JOUR

T1 - Analyzing the Efficiency of Segment Boundary Detection Using Neural Networks

AU - Kugaevskikh, A. V.

AU - Sogreshilin, A. A.

PY - 2019/7/1

Y1 - 2019/7/1

N2 - 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.

AB - 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.

KW - cosine measure

KW - edge selection

KW - Gabor filter

KW - hyperbolic tangent

KW - Mexican hat wavelet

KW - neural networks

UR - http://www.scopus.com/inward/record.url?scp=85073225128&partnerID=8YFLogxK

U2 - 10.3103/S8756699019040137

DO - 10.3103/S8756699019040137

M3 - Article

AN - SCOPUS:85073225128

VL - 55

SP - 414

EP - 422

JO - Optoelectronics, Instrumentation and Data Processing

JF - Optoelectronics, Instrumentation and Data Processing

SN - 8756-6990

IS - 4

ER -