Friction stir welding is a solid-state welding process. The technology is used in high precision applications such as aerospace. Thus, monitoring the weld quality is highly relevant for detecting inaccurate welds. Various studies have shown a significant dependence of the weld quality on the welding speed and the rotational speed of the tool. Frequently, an unsuitable setting of these parameters can be detected by visual examination of the resulting surface defects, such as increased flash formation or surface galling. The visual inspection for these defects is often conducted manually and is therefore associated with increased costs and personnel effort. In this work, a deep learning approach to automatically detect irregularities on the weld surface is introduced. For training and testing of the artificial neural networks, 112 welds with a total length of 18.4 m were produced. Color images of the welds were taken using a digital camera and images of the weld surface topography were made with a three-dimensional profilometer. The approach consisted of a two-step procedure. First, an object detector using a neural network localized the friction stir weld on the image. Second, a neural network classified the surface properties of the weld seam. The object detector localized the friction stir welds with an intersection over union up to 89.5%. The best result in classifying the surface properties was achieved by using the topography images. Thereby, a classification accuracy of 92. % was reached by the convolutional neural network DenseNet-121. The results are the basis for the future development of an inline quality monitoring and parameter control method for friction stir welding.