Please use this identifier to cite or link to this item:
Title: Super precision spectral encoding for laser imaging via machine learning
Authors: Liu, Yunke
Keywords: Engineering::Electrical and electronic engineering::Optics, optoelectronics, photonics
Issue Date: 2021
Publisher: Nanyang Technological University
Source: Liu, Y. (2021). Super precision spectral encoding for laser imaging via machine learning. Master's thesis, Nanyang Technological University, Singapore.
Abstract: Laser Imaging is an important technology nowadays, which involves using of cameras based on CCDs. However, all the colors are associated with distinct emission wavelength of laser, and CCDs not be capable of distinguishing them, rendering the RGB images captured by such cameras may not show adequate information about the laser emission wavelength. Machine Learning is a useful tool, which enables to build a model between the colors and wavelength, provided with adequate amount of data. In our work, a neural network containing residual units is used to build the model between RGB values of laser images in small blocks and the corresponding laser emission wavelength, is trained, and is used on images containing liquid crystal droplets, to make predictions of emission wavelength in every part of these images.
Schools: School of Electrical and Electronic Engineering 
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
  Restricted Access
3.04 MBAdobe PDFView/Open

Page view(s)

Updated on Sep 26, 2023


Updated on Sep 26, 2023

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.