High Power Laser Science and Engineering, (2019), Vol. 7, e66, 6 pages.
© The Author(s) 2019. This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/
licenses/by/4.0/), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited.
doi:10.1017/hpl.2019.52
Detection of laser-induced optical defects based on
image segmentation
Xinkun Chu
1
, Hao Zhang
1
, Zhiyu Tian
1
, Qing Zhang
1
, Fang Wang
2
, Jing Chen
2
, and Yuanchao Geng
2
1
Institute of Computer Application, China Academy of Engineering Physics, Mianyang 621900, China
2
Research Center of Laser Fusion, China Academy of Engineering Physics, Mianyang 621900, China
(Received 25 June 2019; revised 20 October 2019; accepted 9 November 2019)
Abstract
A number of vision-based methods for detecting laser-induced defects on optical components have been implemented
to replace the time-consuming manual inspection. While deep-learning-based methods have achieved state-of-the-art
performances in many visual recognition tasks, their success often hinges on the availability of a large number of labeled
training sets. In this paper, we propose a surface defect detection method based on image segmentation with a U-shaped
convolutional network (U-Net). The designed network was trained on paired sets of online and offline images of optics
from a large laser facility. We show in our experimental evaluation that our approach can accurately locate laser-induced
defects on the optics in real time. The main advantage of the proposed method is that the network can be trained end to
end on small samples, without the requirement for manual labeling or manual feature extraction. The approach can be
applied to the daily inspection and maintenance of optical components in large laser facilities.
Keywords: deep learning; defect detection; laser-induced defects
1. Introduction
Defects on the surface of optics are among the earliest
indications of degradation which are critical for the main-
tenance of optical systems. Early detection of the defects
allows preventive measures to be taken to prevent the defects
from growing to an unrepairable size. Large laser facilities,
such as the National Ignition Facility (NIF)
[1]
and the Laser
Megajoule (LMJ)
[2]
, routinely operate at high ultraviolet
fluences above the damage threshold of optical components.
The laser-induced defects on optics, once initiated, will grow
rapidly in subsequent exposure to high fluence, until to the
point at which the entire optical component needs to be
replaced. Therefore, it is critical for sustainable operation to
detect and monitor defects in the early stage.
Various image processing techniques, such as the thresh-
old method, Otsu’s method and Fourier transform
[3–5]
, have
been implemented for defect detection to replace the time-
consuming and error-prone manual inspection. Scientists
at the Lawrence Livermore National Laboratory (LLNL)
have conducted a lot of valuable researches in the field of
damage online inspection. Using linescan phase-differential
imaging, LLNL developed a process for rapid detection
of phase defects in the bulk or surface of large-aperture
Correspondence to: Y. Geng, No. 64 Mianshan Road, Mianyang 621900,
China. Email: gengyuanchao@caep.cn
optics
[6]
. A threshold is set on the brightest pixel value to
select candidates for further assessment of their fratricidal
threat. LLNL also designed the local area signal-to-noise
ratio (LASNR) algorithm
[7]
for accurate and rapid inspection
of the optics from the NIF. The algorithm estimates the
strength of signal within an object versus the noise in its
local neighborhood. However, the accuracy and robustness
of these image processing techniques are largely affected by
varying situations like illumination conditions, shading and
noises.
Machine-learning-based models outperform the image
processing techniques in accuracy and robustness, and
have been successfully applied in computer vision tasks
such as object detection and classification. LLNL extracted
various features from each damage site and employed
ensemble of decision trees to identify false damage sites
from hardware reflections
[8]
. Harbin Institute of Technology
(HIT) developed the final optics damage inspection (FODI)
system for the laser facility at the China Academy of
Engineering Physics (CAEP)
[9, 10]
. HIT manually extracted
features associated with each damage site, and then used
extreme learning machine to distinguish true and false
damage sites and predict the damage size. The success of
the machine learning models above relies on the manually
custom-built features based on the experience of domain
experts. Nathan et al.
[11]
built convolutional neural network
1