Convolutional Neural Network GoogleNet Architecture for Detecting the Defect Tire

Defect tire detection plays a vital role in industrial quality checking. The system and manual human vision can automatically detect defective tires using Artificial Intelligence. This study detects tire defects using the Convolutional Neural Network method with GoogleNet architecture. The tire industry will save much time on quality checking by detecting the defective tire automatically. This study uses secondary data obtained from the Kaggle web dataset. This proposed method produces the best accuracy of 92% and the average value of precision, recall and an F-1 score of 0.92. The tire industry can use the automatic defect tire detection system to check the tire's quality.