Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Ataturk University -...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
addClaim

Mask R-CNN ile Çoklu Barkod Tespiti

Authors: Oral, Emin Argun; Polat, Enes; Mohammed, Hussein Mahmood Abdo; Kumbasar, Nida; Ömeroğlu, Aslı Nur; Özbek, İbrahim Yücel;

Mask R-CNN ile Çoklu Barkod Tespiti

Abstract

Günümüzde kullanılan birçok ürünün kendileriyleilişkili benzersiz kodu veya kimliği vardır. Bu özel kimlik barkodolarak adlandırılır. Barkodlar çeşitli endüstriyel ortamlardaotomasyona olan yüksek talep nedeniyle son yıllarda kapsamlıaraştırmalara konu olmuştur. Birçok ticari uygulamadakullanılan ürün ile ilgili tüm detayların öğrenilebildiğibarkodların hızlı ve doğru okuması oldukça önemlidir. Buçalışmada 1B barkodların görüntüdeki bölgelerini tespit etmekamacıyla, Mask R-CNN algoritması kullanılmıştır. Mask R-CNNile görüntüdeki barkodlar tespit edilmiş, her barkodun sınırlayıcıkutu konumunun yanı sıra, sınırlayıcı kutudaki bu sınıfa karşılıkgelen piksel bilgileri de görselleştirilmiştir. Farklı ortamışıklarında ve farklı açılarla çekilmiş çeşitli ürünler üzerindekirenkli barkodlar toplanarak 1114 görüntüden oluşan yeni birveri seti hazırlanmıştır. Bu veri seti kullanılarak Mask R-CNN ilebaşlangıç çalışması olarak %74.41 doğruluk oranı elde edilmiştir.

Almost all products on the market today have aunique code or ID associated with them. This specialidentification is called a barcode. Barcodes have been the subjectof extensive research in recent years due to the high demand forautomation in various industrial environments. Fast andaccurate reading of barcodes, where all details about the productused in many commercial applications can be learned, is veryimportant. In this study, Mask R-CNN algorithm was used todetermine the regions of the 1B barcodes in the image. In theMask R-CNN, barcodes in the image have been detected, as wellas the bounding box position of each barcode, as well as the pixelinformation corresponding to this class in the bounding box.Colored barcodes on various products taken at different ambientlights and at different angles were collected and a data set of 1114images was prepared. Using this dataset, 74.41 % accuracy wasachieved with Mask R-CNN

Country
Turkey
Related Organizations
  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green