In order to observe internal bubble defects of tires that cannot be observed by the naked eye, digital shearography has been used to inspect tire defects. However, the inspection quality is highly dependent on experienced operators. This requires considerable personnel resources and misjudgment may be introduced due to human fatigue. In order to overcome these shortcomings, this study proposes to apply the convolutional neural networks and the faster regions with convolutional neural networks for detecting the bubble defects. Experimental results showed that the proposed tire bubble defect detection system can completely detect the bubble defects and reduce the false alarm.
CITATION STYLE
Chang, C. Y., & Wang, W. C. (2019). Integration of CNN and Faster R-CNN for Tire Bubble Defects Detection. In Lecture Notes on Data Engineering and Communications Technologies (Vol. 25, pp. 285–294). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-02613-4_25
Mendeley helps you to discover research relevant for your work.