Chasing excellence: from deep machine learning to artificial intelligence in Maker-Ray AOI systems. Part 2

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

In the first part of the article, published in «ELECTRONICS: Science, Technology, Business» No. 10/2023 journal, the effectiveness of the use of artificial intelligence (AI) was substantiated as the next step in the development of machine learning algorithms in image analysis. The second part discusses the theory and practice of building a virtual model for the operation of artificial intelligence used in Maker-Ray optical inspection systems.

Full Text

Restricted Access

About the authors

I. Rozhkov

ООО «Новые Технологии»

Author for correspondence.
Email: rozhkov@nt-smt.ru

генеральный директор, управляющий партнер

Russian Federation

A. Garanin

ООО «Новые Технологии»

Email: garanin@nt-smt.ru

технический директор, управляющий партнер

Russian Federation

D. Podolsky

ООО «Новые Технологии»

Email: podolsky@nt-smt.ru

ведущий менеджер по продуктам

Russian Federation

Supplementary files

Supplementary Files
Action
1. JATS XML
2. Photo 1

Download (52KB)
3. Fig. 1. General model of AI training

Download (512KB)
4. Fig. 2. Statistical results of measuring the number of red pixels R: a - number of red pixels R on the red line; b - number of red pixels R in the other area

Download (19KB)
5. Fig. 3. Algorithm of applying fragmentation and pixel transformation function

Download (33KB)
6. Fig. 4. Illustration of the description of the transformation function f(x, y)

Download (901KB)
7. Fig. 5. Methodology for increasing the informativeness of images

Download (791KB)
8. Fig. 6. Formation of image classes

Download (18KB)
9. Fig. 7. Dropout method

Download (20KB)

Copyright (c) 2024 Rozhkov I., Garanin A., Podolsky D.

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies