Smart Tyre Monitoring: Unleashing the Power of InceptionV3 for Accurate Defect Detection

Modern running understands and upholds tyre safety as well as optimizes its performance in any automotive industry. This paper discusses tyre condition classification using the Inception_v3 model, a deep convolutional neural network. The objective of this work was to come up with an effective and accurate system that can be used to classify tyres based on visual inspection. It was trained on tyre images against which the model devised performed well: regular tyres {0.0} class with a precision of 0.95, recall of 0.96, and an F1-score of 0.95; worn tyres {1.0} class with a precision of 0.97, recall of 0.96, and an F1-score of 0.96. The overall accuracy was 0.96, evaluated on a test set of 372 images. The macro and weighted averages for precision, recall, and F1-score were high at 0.96 and showed the model's ability to perform well on both classes by a good margin. These results show that there is potential in the Inception_v3 model for contributing to a reliable solution for automatic tyre classification, which is of importance for predictive maintenance and road safety. This research suggests that deep learning models could be applied in the automotive sector and prove effective in visual classification tasks. Future work will be oriented toward integrating this model into working real-time systems and extending the application to a broader range of tyre types and conditions.