Recently, the number of missing people due to senile dementia has been
increasing along with aging problem. Basically, finding missing old people
is conducted by humans. However, it takes payroll cost and much time. It
is assumed that it can be conducted automatically using security camera
and QR code on missing people. The purpose of our study is to restore and
rectify blurred and distorted QR code to develop this system.
Our proposed method consists of blind deconvolution, finding 4 lines on
the QR code, rectification using projective transformation and version estimation.
We conducted experiments in order to determine the effectiveness of our
proposed method. As a result, joint restoration and rectification worked
well when the versions of QR codes were small. For higher versions, the
decoding became more challenging. It was presumed that we needed to
improve restoration method if we deal with QR code of higher version.

Recently, the number of missing people due to senile dementia has been
increasing along with aging problem. Basically, finding missing old people
is conducted by humans. However, it takes payroll cost and much time. It
is assumed that it can be conducted automatically using security camera
and QR code on missing people. The purpose of our study is to restore and
rectify blurred and distorted QR code to develop this system.
Our proposed method consists of blind deconvolution, finding 4 lines on
the QR code, rectification using projective transformation and version estimation.
We conducted experiments in order to determine the effectiveness of our
proposed method. As a result, joint restoration and rectification worked
well when the versions of QR codes were small. For higher versions, the
decoding became more challenging. It was presumed that we needed to
improve restoration method if we deal with QR code of higher version.

[1] 平 成 29 年 版 高 齢 社 会 白 書（ 全 体 版 ） — 内
閣 府 (http://www8.cao.go.jp/kourei/whitepaper/w2017/zenbun/29pdf
index.html) (2018/1/11 Access)
[2] 平 成 28 年 に お け る 行 方 不 明 者 の 状 況 — 警 察 庁
(https://www.npa.go.jp/safetylife/seianki/fumei/H28yukuehumeisya.pdf)
(2018/1/11 Access)
[3] 防犯カメラ新たに１００台 認知症の徘徊高齢者対策にも 大阪・
淀川３区 (http://www.sankei.com/west/news/150306/wst1503060026-
n1.html)(2018/1/11 Access)
[4] ＱＲシールで徘徊高齢者の身元確認 全国初、埼玉・入間市が無
料 交 付 (http://www.sankei.com/life/news/161118/lif1611180022-
n1.html)(2018/1/11 Access)
[5] D. Munoz-Mejias, I. Gonzalez-Diaz and F. Diaz-de-Maria, ”A lowcomplexity
pre-processing system for restoring low-quality QR code images,”
in IEEE Transactions on Consumer Electronics, vol. 57, 2011.
[6] L. Li, W. Lin, X. Wang, G. Yang, K. Bahrami and A. C. Kot, ”NoReference
Image Blur Assessment Based on Discrete Orthogonal Moments,”
in IEEE Transactions on Cybernetics, vol. 46, pp. 39-50, 2016.
[7] C. C. Lee and W. L. Hwang, ”Mixture of Gaussian Blur Kernel Representation
for Blind Image Restoration,” in IEEE Transactions on Computational
Imaging, vol. 3, pp. 783-797, 2017.
[8] F. Wang, H. B. Zhang, M. Cao, R. Nishi and A. Takaoka, ”Image blurring
of thick specimens due to MeV transmission electron scattering: a
Monte Carlo study,” in Microscopy, vol. 60, pp. 315-320, 2011.
[9] A. K. Booer, J. Chambers and I. M. Mason, ”Numerical holographic
reconstruction by a ’projective transform’,” in Electronics Letters, vol.
13, pp. 569-570, 1977.
[10] ”Information technology Automatic identification and data capture
techniques Barcode symbology QR Code,” ISO/IEC 18004 International
Standard, June 2000.
[11] D. A. Brannan, M. F. Esplen and J. J. Gray, Geometry, Chapters. 3-4,
Cambridge Univ. Press, Cambridge, UK, 1999.
[12] T. C. Chen, ”QR Codes with High Visual Comprehensibility via Lossless
Logo Embedding,” National Taiwan University of Science and Technology,
Master’s thesis, July 2017.