Defect detection of seals in multilayer aseptic packages using deep learning

Kemal Adem,Cemil Közkurt

doi:10.3906/elk-1903-112

Abstract

Sealing in aseptic packages, one of the healthiest and cheapest technologies to protect food from parasites in the liquid food industry, requires a detailed and careful control process. Since the controls are made manually and visually by expert machine operators, the human factor can lead to the failure to detect defects, resulting in high cost and food safety risks. Therefore, this study aims to perform a leak test in aseptic package seals by a system that makes decisions using independent deep learning methods. The proposed Faster R-CNN and the Updated Faster R-CNN deep learning models were subjected to training and testing with a total of 400 images taken from a real production environment, resulting in a correct classification rate of 99.25 %. As a result, it can be said that the study is the second study that performs a computer-aided quality control process with promising results, having distinctive features such as being the first study that conducts analysis using the deep learning method.

Highlights

In industrial societies, food safety is one of the most important criteria for human health due to the widespread consumption of industrial food products
Since the controls are made manually and visually by expert machine operators, the human factor can lead to the failure to detect defects, resulting in high cost and food safety risks [1]
Machine learning methods, and the original Faster convolutional artificial neural network (CNN) model were not able to achieve the performance of the updated Faster R-CNN model we proposed in the study

Summary

Introduction

Food safety is one of the most important criteria for human health due to the widespread consumption of industrial food products. Small changes in the parameters of aseptic packaging systems, such as temperature and pressure, lead to defective or leaking package sealing Since these defects cannot be measured in production at effective speeds, samples are taken from the production line and destructive detection-based quality controls are performed. In [1], the authors converted seal images into binary format after thresholding in order to detect the defects in LS and TS regions, used the Canny method for edge detection, and classified the images by regression and support vector machine (SVM) methods. A CNN-based method for quality control tests in aseptic liquid food packages is discussed. Increases in success rates have been observed in line with updates on CNN parameters

Dataset used in the study

Experimental studies

Conclusion

Findings

Method