A convolutional neural network approach for visual recognition in wheel production lines

China has been the world's largest automotive manufacturing country since 2008. The automotive wheel industry in China has been growing steadily in pace with the automobile industry. Visual recognition system that automatically classifies wheel types is a key component in the wheel production line. Traditional recognition methods are mainly based on extracted feature matching. Their accuracy, robustness, and processing speed are often compromised considerably in actual production. To overcome this problem, we proposed a convolutional neural network approach to adaptively classify wheel types in actual production lines with a complex visual background. The essential steps to achieve wheel identification include image acquisition, image preprocessing, and classification. The image differencing algorithm and histogram technique are developed on acquired wheel images to remove track disturbances. The wheel images after image processing were organized into training and test sets. This approach improved the residual network model ResNet-18 and then evaluated this model based on the wheel test data. Experiments showed that this method can obtain an accuracy over 98% on nearly 70,000 wheel images and its single image processing time can reach millisecond level.