A Novel Deep Learning-Based Approach for Defect Detection of Synthetic Leather Using Gaussian Filtering

Synthetic leather is a commonly used material, especially in the clothing industry. It is employed in the production of footwear, such as shoes and boots, as well as handbags and other accessories. Prior to exportation, the leather is subjected to a series of processing stages, which may result in the formation of surface defects. Quality assurance, which serves to identify defective leather in a timely manner, is still partially conducted by humans. This step is time-consuming and is associated with a higher error rate. To address these challenges, the deployment of image processing systems for the automated inspection of leather defects is becoming increasingly crucial. The objective of this study is to develop an effective deep learning model for the classification of defective synthetic leather, with the aim of implementing it in the quality control of synthetic leather production. To this end, a variety of architectural approaches are employed, including Xception, InceptionV3, ResNet50V2, VGG19, and VGG16. In addition to hyperparameter tuning, all architectures utilize transfer learning. Moreover, the impact of the Gaussian filter as a pre-processing step for images is examined. The results show that by using an innovative Gaussian filtering approach, an accuracy of 100% was achieved with the VGG16 model. Furthermore, the results show that the filtering approach has a positive influence on the accuracy of all other models. The high accuracies of the deep learning models show that the use of machine vision systems for the automatic inspection of defects in the synthetic leather industry is an effective economic step for companies, as it leads to cost and time savings in production due to the high classification performance. This study provides an overview of the results achieved and other key performance indicators for all the models used.