UP-Net: A multi-head architecture for reading and efficiently segmenting distorted QR codes

Semantic segmentation is essential in machine vision but susceptible to noise and distortions that often appear in real-world images. We propose UPlus-Net (UP-Net), a deep-learning architecture based on the U-Net encoder-decoder architecture. We address the limitations of U-Net by intro-ducing a mul...

Full description

Saved in:
Bibliographic Details
Main Authors: Ebrahim Parcham, Mahdi Ilbeygi, Vahid Hajipour, Ali Gharaei, Mahdi Mokhtari, Mostafa Foroutan
Format: Article
Language:English
Published: Electronics and Telecommunications Research Institute (ETRI) 2025-06-01
Series:ETRI Journal
Subjects:
Online Access:https://doi.org/10.4218/etrij.2023-0540
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849710662159171584
author Ebrahim Parcham
Mahdi Ilbeygi
Vahid Hajipour
Ali Gharaei
Mahdi Mokhtari
Mostafa Foroutan
author_facet Ebrahim Parcham
Mahdi Ilbeygi
Vahid Hajipour
Ali Gharaei
Mahdi Mokhtari
Mostafa Foroutan
author_sort Ebrahim Parcham
collection DOAJ
description Semantic segmentation is essential in machine vision but susceptible to noise and distortions that often appear in real-world images. We propose UPlus-Net (UP-Net), a deep-learning architecture based on the U-Net encoder-decoder architecture. We address the limitations of U-Net by intro-ducing a multi-head architecture in UP-Net to properly handle segmentation challenges. In addition, we evaluate UP-Net for decoding distorted quick-response (QR) codes heavily polluted by noise. Experimental results confirm that UP-Net outperforms existing QR reader mobile applications, highlighting the UP-Net ability to handle challenging images. Unlike existing methods focused solely on QR code reading or segmentation, UP-Net offers a combined solution, efficiently and accurately reading distorted QR codes while perform-ing high-quality semantic segmentation. These unique characteristics render UP-Net promising for applications demanding robust image analysis in chal-lenging environments.
format Article
id doaj-art-4f353bcb3f844802ae88f0acde78bd1f
institution DOAJ
issn 1225-6463
2233-7326
language English
publishDate 2025-06-01
publisher Electronics and Telecommunications Research Institute (ETRI)
record_format Article
series ETRI Journal
spelling doaj-art-4f353bcb3f844802ae88f0acde78bd1f2025-08-20T03:14:50ZengElectronics and Telecommunications Research Institute (ETRI)ETRI Journal1225-64632233-73262025-06-0147352754410.4218/etrij.2023-0540UP-Net: A multi-head architecture for reading and efficiently segmenting distorted QR codesEbrahim ParchamMahdi IlbeygiVahid HajipourAli Gharaei Mahdi MokhtariMostafa ForoutanSemantic segmentation is essential in machine vision but susceptible to noise and distortions that often appear in real-world images. We propose UPlus-Net (UP-Net), a deep-learning architecture based on the U-Net encoder-decoder architecture. We address the limitations of U-Net by intro-ducing a multi-head architecture in UP-Net to properly handle segmentation challenges. In addition, we evaluate UP-Net for decoding distorted quick-response (QR) codes heavily polluted by noise. Experimental results confirm that UP-Net outperforms existing QR reader mobile applications, highlighting the UP-Net ability to handle challenging images. Unlike existing methods focused solely on QR code reading or segmentation, UP-Net offers a combined solution, efficiently and accurately reading distorted QR codes while perform-ing high-quality semantic segmentation. These unique characteristics render UP-Net promising for applications demanding robust image analysis in chal-lenging environments. https://doi.org/10.4218/etrij.2023-0540image distortionmobile phonemulti-head architectureqr code readersemantic segmentation
spellingShingle Ebrahim Parcham
Mahdi Ilbeygi
Vahid Hajipour
Ali Gharaei
Mahdi Mokhtari
Mostafa Foroutan
UP-Net: A multi-head architecture for reading and efficiently segmenting distorted QR codes
ETRI Journal
image distortion
mobile phone
multi-head architecture
qr code reader
semantic segmentation
title UP-Net: A multi-head architecture for reading and efficiently segmenting distorted QR codes
title_full UP-Net: A multi-head architecture for reading and efficiently segmenting distorted QR codes
title_fullStr UP-Net: A multi-head architecture for reading and efficiently segmenting distorted QR codes
title_full_unstemmed UP-Net: A multi-head architecture for reading and efficiently segmenting distorted QR codes
title_short UP-Net: A multi-head architecture for reading and efficiently segmenting distorted QR codes
title_sort up net a multi head architecture for reading and efficiently segmenting distorted qr codes
topic image distortion
mobile phone
multi-head architecture
qr code reader
semantic segmentation
url https://doi.org/10.4218/etrij.2023-0540
work_keys_str_mv AT ebrahimparcham upnetamultiheadarchitectureforreadingandefficientlysegmentingdistortedqrcodes
AT mahdiilbeygi upnetamultiheadarchitectureforreadingandefficientlysegmentingdistortedqrcodes
AT vahidhajipour upnetamultiheadarchitectureforreadingandefficientlysegmentingdistortedqrcodes
AT aligharaei upnetamultiheadarchitectureforreadingandefficientlysegmentingdistortedqrcodes
AT mahdimokhtari upnetamultiheadarchitectureforreadingandefficientlysegmentingdistortedqrcodes
AT mostafaforoutan upnetamultiheadarchitectureforreadingandefficientlysegmentingdistortedqrcodes