Open AccessUnsupervised anomaly detection of MEMS in low illumination based on polarimetric Support Vector Data Description
Author(s) -
Yaokang Huang,
Mei Sang,
Lun Xing,
Haofeng Hu,
Tiegen Liu
Publication year - 2021
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.438564
Subject(s) - polarimetry , anomaly detection , artificial intelligence , computer science , polarization (electrochemistry) , pixel , computer vision , optics , support vector machine , anomaly (physics) , remote sensing , physics , geology , scattering , chemistry , condensed matter physics
Low illuminated images make it challenging to conduct anomaly detection on material surface. Adding polarimetric information helps expand pixel range and recover background structure of network inputs. In this letter, an anomaly detection method in low illumination is proposed which utilizes polarization imaging and patch-wise Support Vector Data Description (SVDD) model. Polarimetric information of Micro Electromechanical System (MEMS) surface is captured by a division-of-focal- plane (DoFP) polarization camera and used to enhance low illuminated images. The enhanced images without defects serve as training sets of model to make it available for anomaly detection. The proposed method can generate heatmaps to locate defects correctly. It reaches 0.996 anomaly scores, which is 22.4% higher than that of low illuminated images and even higher than normal illuminated images.