Automatic design of machine vision lens based on improved genetic algorithm and damped least squares

Jifeng Sun; Xiaotong Li

doi:10.1117/12.2600897

9 October 2021 Automatic design of machine vision lens based on improved genetic algorithm and damped least squares

Jifeng Sun, Xiaotong Li

Proceedings Volume 11895, Optical Design and Testing XI; 118950X (2021) https://doi.org/10.1117/12.2600897
Event: SPIE/COS Photonics Asia, 2021, Nantong, JS, China

Conference Poster

Abstract

As the most widely used optimization method in optical system design, the damped least squares (DLS) method performs well in convergence speed. However, the fatal flaw of DLS method is that it is easy to get caught into local minima. Thus, some intelligent algorithms are adopted in optical system designing for global optimization. Genetic algorithm (GA) has the unique advantages of wide scope of application and powerful global search capability. In this paper, we proposed a new optimization method for optical system design, which is based on an improved genetic algorithm and combined with the damped least squares method. Besides, a machine vision lens is designed by the proposed method, which verified the effectiveness of the method.

Citation Download Citation

Jifeng Sun and Xiaotong Li "Automatic design of machine vision lens based on improved genetic algorithm and damped least squares", Proc. SPIE 11895, Optical Design and Testing XI, 118950X (9 October 2021); https://doi.org/10.1117/12.2600897

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available