Quick response barcode deblurring via doubly convolutional neural network

Various image preprocessing applications for two dimensional (2D) barcode involve reversing the degradation operations (e.g. deblurring). Most of the previously proposed deblurring approaches focus on the construction of suitable deconvolution models, which have shown significant performance at labo...

Full description

Saved in:
Bibliographic Details
Published in:Multimedia tools and applications 2019-01, Vol.78 (1), p.897-912
Main Authors: Pu, Haitao, Fan, Mingqu, Yang, Jinliang, Lian, Jian
Format: Article
Language:English
Subjects:
Artificial neural networks
Bar codes
Computer Communication Networks
Computer Science
Data Structures and Information Theory
Machine learning
Multimedia Information Systems
Neural networks
Preprocessing
Quick Response
Special Purpose and Application-Based Systems
Two dimensional models
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Various image preprocessing applications for two dimensional (2D) barcode involve reversing the degradation operations (e.g. deblurring). Most of the previously proposed deblurring approaches focus on the construction of suitable deconvolution models, which have shown significant performance at laboratory level. However, the model-based image deblurring solutions might not work well in practical scenarios. To deal with this problem, we propose a convolutional neural network (CNN) based framework to tackle the parameter-free situation for 2D barcode deblurring. The proposed solution leverages the deep learning technique to bridge the gap between traditional model-based methods and requirement of reversing the blurry 2D barcode images. Experiments on practically blurred quick response (QR) barcode images demonstrate that the proposed approach achieves the superior performance in comparison with state-of-the-art model-based image deblurring approaches.
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-018-5802-2