End-to-end tire defect detection model based on transfer learning techniques
Open Access
- 22 April 2024
- journal article
- research article
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (20) , 12483-12503
Abstract
Visual inspection of defective tires post-production is vital for human safety, as faulty tires can lead to explosions, accidents, and loss of life. With the advancement of technology, transfer learning (TL) plays an influential role in many computer vision applications, including the tire defect detection problem. However, automatic tire defect detection is difficult for two reasons. The first is the presence of complex anisotropic multi-textured rubber layers. Second, there is no standard tire X-ray image dataset to use for defect detection. In this study, a TL-based tire defect detection model is proposed using a new dataset from a global tire company. First, we collected and labeled the dataset consisting of 3366 X-ray images of faulty tires and 20,000 images of qualified tires. Although the dataset covers 15 types of defects arising from different design patterns, our primary focus is on binary classification to detect the presence or absence of defects. This challenging dataset was split into 70, 15, and 15% for training, validation, and testing, respectively. Then, nine common pre-trained models were fine-tuned, trained, and tested on the proposed dataset. These models are Xception, InceptionV3, VGG16, VGG19, ResNet50, ResNet152V2, DenseNet121, InceptionResNetV2, and MobileNetV2. The results show that the fine-tuned VGG19, DenseNet21 and InceptionNet models achieve compatible results with the literature. Moreover, the Xception model outperformed the compared TL models and literature methods in terms of recall, precision, accuracy, and F1 score. Moreover, it achieved on the testing dataset 73.7, 88, 80.2, and 94.75% of recall, precision, F1 score, and accuracy, respectively, and on the validation dataset 73.3, 90.24, 80.9, and 95% of recall, precision, F1 score, and accuracy, respectively.Keywords
Funding Information
- University of Kocaeli
This publication has 40 references indexed in Scilit:
- On fine-tuning deep learning models using transfer learning and hyper-parameters optimization for disease identification in maize leavesNeural Computing and Applications, 2022
- Effectiveness evaluation of different feature extraction methods for classification of covid-19 from computed tomography images: A high accuracy classification studyBiomedical Signal Processing and Control, 2022
- A comparative study of fourteen deep learning networks for multi skin lesion classification (MSLC) on unbalanced dataNeural Computing and Applications, 2022
- Transfer learning for image classification using VGG19: Caltech-101 image data setJournal of Ambient Intelligence and Humanized Computing, 2021
- Multilevel thresholding segmentation of color plant disease images using metaheuristic optimization algorithmsNeural Computing and Applications, 2021
- Ensemble deep transfer learning model for Arabic (Indian) handwritten digit recognitionNeural Computing and Applications, 2021
- Colorectal Histology Tumor Detection Using Ensemble Deep Neural NetworkEngineering Applications of Artificial Intelligence, 2021
- Automatic classification of volcanic rocks from thin section images using transfer learning networksNeural Computing and Applications, 2021
- Deep neural networks with transfer learning in millet crop imagesComputers in Industry, 2019
- Integration of CNN and Faster R-CNN for Tire Bubble Defects Detection2018