eprintid: 16577
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/65/77
datestamp: 2023-12-19 03:23:05
lastmod: 2023-12-19 03:23:05
status_changed: 2023-12-19 03:06:30
type: article
metadata_visibility: show
creators_name: Ishiyama, S.
creators_name: Lu, H.
creators_name: Soomro, A.A.
creators_name: Mokhtar, A.A.
title: Single image reflection removal using meta-learning
ispublished: pub
keywords: Deep learning; Image segmentation; Iterative methods; Learning systems; Object detection, Deep learning; Learning models; Metalearning; Reflection removals; Single image reflection removal; Single images; Small training; Small training data; Training data; Window glass, Image quality
note: cited By 0
abstract: In recent years, reflection is a kind of noise in images that is frequently generated by reflections from windows, glasses, and so on, when you take pictures or movies. The reflection does not only degrade the image quality but also affects computer vision tasks, such as the accuracy of object detection and segmentation. In the task of single image reflection removal (SIRR), deep learning models play a key role for solving the problems of various patterns and the versatility. The challenge of SIRR is the influence of image quality and low precision of the method. We propose a deep learning model for the task of SIRR. The assumed scenes of reflection are varying, and there is little training data because it is difficult to obtain true values. We focus on the latter and propose an SIRR based on meta-learning. We adopt model agnostic meta-learning (MAML), and we propose an SIRR using a deep learning model with MAML, both of which are methods of meta-learning. The deep learning model includes the iterative boost convolutional long short-term memory network, which is adopted as the deep learning model. Experimental results show that the proposed method improves accuracy compared with conventional state-of-the-art methods. © 2022 SPIE and IS&T.
date: 2022
publisher: SPIE
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85142252412&doi=10.1117%2f1.JEI.31.4.041209&partnerID=40&md5=9a666cdad5b124a2109c5fd3926806f5
id_number: 10.1117/1.JEI.31.4.041209
full_text_status: none
publication: Journal of Electronic Imaging
volume: 31
number: 4
refereed: TRUE
issn: 10179909
citation:   Ishiyama, S. and Lu, H. and Soomro, A.A. and Mokhtar, A.A.  (2022) Single image reflection removal using meta-learning.  Journal of Electronic Imaging, 31 (4).   ISSN 10179909