In this work, an embedded system based product defect
detection system has been developed for the metal industry. As a test product,
sheet metal plates which are used very often in the metal industry containing
circular holes have been used. The geometrical information about the holes on
the plates have been obtained using Hough circular transformation. Detection of
defective products was made by comparison using the reference image. As an
embedded system Raspberry Pi Model 3 B+ have been used. Performance analysis of
the developed system have been carried out on a special image sets having
different resolutions which are obtained for the study. Based on the
experimental results it has been shown that the developed system reached 96,29%
accuracy rate for the image set with 10MP resolution.
Bu
çalışmada, metal sektöründe kullanılmak üzere gömülü sistem tabanlı bir hatalı
ürün tespit sistemi geliştirilmiştir. Ürün grubu olarak sektörde sıklıkla
üretilen ve dairesel boşluklar içeren sac levhalar seçilmiştir. Levhalar
üzerindeki dairesel boşluklara ait bilgiler dairesel Hough dönüşümü
kullanılarak elde edilmiştir. Hatalı ürünlerin tespiti referans görüntü
kullanılarak karşılaştırma yoluyla yapılmıştır. Gömülü sistem olarak Raspberry
Pi Model 3 B+ seçilmiştir. Geliştirilen sistemin başarım incelemesi çalışmaya
özel oluşturulmuş farklı çözünürlükteki görüntü kümeleri üzerinde yapılmıştır.
Yapılan deneyler sonucunda geliştirilen sistemin 10MP çözünürlükteki görüntü
kümesinde %96,29 doğruluk oranına sahip olduğu gösterilmiştir.
Primary Language | Turkish |
---|---|
Subjects | Engineering |
Journal Section | Research Articles |
Authors | |
Publication Date | April 30, 2019 |
Submission Date | February 11, 2019 |
Acceptance Date | April 3, 2019 |
Published in Issue | Year 2019 Volume: 24 Issue: 1 |
Announcements:
30.03.2021-Beginning with our April 2021 (26/1) issue, in accordance with the new criteria of TR-Dizin, the Declaration of Conflict of Interest and the Declaration of Author Contribution forms fulfilled and signed by all authors are required as well as the Copyright form during the initial submission of the manuscript. Furthermore two new sections, i.e. ‘Conflict of Interest’ and ‘Author Contribution’, should be added to the manuscript. Links of those forms that should be submitted with the initial manuscript can be found in our 'Author Guidelines' and 'Submission Procedure' pages. The manuscript template is also updated. For articles reviewed and accepted for publication in our 2021 and ongoing issues and for articles currently under review process, those forms should also be fulfilled, signed and uploaded to the system by authors.