ПРИМЕНЕНИЕ НЕЙРОННОЙ СЕТИ “НЕОКОГНИТРОН” ДЛЯ ОБРАБОТКИ ИЗОБРАЖЕНИЙ ИНТЕГРАЛЬНЫХ СХЕМ

Authors

  • М.Е. Ваткин
  • Р.Х. Садыхов

DOI:

https://doi.org/10.47839/ijc.1.2.120

Keywords:

Нейронная сеть, Распознавание образов

Abstract

Рассматриваются архитектура нейронной сети “неокогнитрон” в задачах поиска структурных элементов на полутоновых изображениях интегральных схем. Предлагается модифицированное правило активации нейронов инвариантное к искажениям яркости изображения. Сравнительные результаты применения нейронной сети показали преимущество использования нейросетевого подхода.

References

G. A. Carpenter, W. D. Ross. ART­EIMAGE: A neural network architecture for object recog­nition by evidence accumulation, IEEE Transac­tion on Neural Networks 6 (1995). p. 805­818.

G. A. Carpenter, S. Grossberg, G. W. Lesher. The What­and­Were Filter. A Spatial Imageping Neural Network for Object Recognition and Im­age Understanding, Computer Vision and Image Understanding 69 (1) (1998). p. 1­22.

S. Grossberg, E. Mingolla, J. Williamson. Synthetic aperture radar processing by multiple scale neural system for boundary and surface representation, Neural Networks 8 (1995). p. 1005-­1028.

G.H. Traven. A Neural Network Approach to Statistical Pattern Classif ication by “Semi­parametric” Estimation of Probability Density Function, IEEE Transactions on Neural Net­works 2 (3) (1991). p. 366­-377.

K. Fukushima. Neocognitron: A self­or­ganizing neural network model for a mecha­nism of pattern recognition unaf fected by shift in position, Biol. Cybern. 36 (1980). p. 193­-202.

K. Fukushima, S. Miyake. Neocognitron: A new algorithm for pattern recognition toler­ant of deformations and shifts in position, Pat­tern Recognition 15 (1982). p. 455­-469.

K. Fukushima, S. Miyake, T. Ito. Neocogni­tron: A neural network model for a mechanism of visual pattern recognition, IEEE Trans. Syst., Man, Cybern. SMC­13 (1983). p. 826­-834.

K. Fukushima, N. Wake. Handwritten al­phanumeric character recognition by the Neocognitron, IEEE Trans. on Neural Networks 2 (3) (1991). p. 355­-365.

Downloads

Published

2002-12-31

How to Cite

Ваткин, М., & Садыхов, Р. (2002). ПРИМЕНЕНИЕ НЕЙРОННОЙ СЕТИ “НЕОКОГНИТРОН” ДЛЯ ОБРАБОТКИ ИЗОБРАЖЕНИЙ ИНТЕГРАЛЬНЫХ СХЕМ. International Journal of Computing, 1(2), 91-94. https://doi.org/10.47839/ijc.1.2.120

Issue

2002, Volume 1, Issue 2

Section

Articles

License

International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:
•    Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
•    Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
•    Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.