Zeki Sistemler Teori ve Uygulamaları Dergisi

Yazarlar: Gültekin ÇAĞIL, Fatma OKCU, Nazlı Hilal GÜNGÖR

Konular:Bilgisayar Bilimleri, Yapay Zeka

Anahtar Kelimeler:Image Processing,Python Programming Language,OpenCv,Food Packaging,Quality Control

Özet: This work; The aim of this study is to detect the defects on the surfaces of packaging products by means of Image Processing in a company producing food packaging.In the Images of products received from the company, with the support of OpenCV Library in Python Programming Language in Pycharm Platform; types of defects such as paint, signal, misalignment, knife line are detected. The OpenCv Library saves time and improves system performance. In this study, firstly by color masking, two sets of blue color which are “dusuk” and “yuksek” are created. The image is converted to HSV format, because the masking process requires the HSV format of the image. After masking, the blue background becomes white and all other colors become black. After this process, the pixels with white color are converted to their original values so that the values of the pixels with black color do not change. In order to perform Edge Detection, the image is converted to gray tone so that unwanted noise is obtained in the image. Then, the images of the faulty parts are taken and similarities are applied to find the faulty parts in the real image. Finally, the defective parts are indicated in the yellow rectangle. Operators in the company make the error detection by visual inspection. In this system, when the operator cannot detect the error, the wrong packages continue to be produced in the coils where the wrapping is made. In order to minimize the costs incurred in this situation, it was decided to use the Image Processing method and appropriate results were obtained.

---