Characterizing surface structures and interfaces is an important step for the design of novel energy materials, e.g., catalysts, batteries, etc. In principle, trained materials scientists can assign interface structures of materials by looking at high-resolution imaging and diffraction data obtained by aberration-corrected scanning transmission electron microscopy (STEM). However, the high-acquisition rates in STEM pose a challenge to a purely human-based identification of interfaces or defects. As of today, STEM datasets are being massively accumulated, but they cannot be fully exploited due to the lack of automatic analysis tools. Here, we present a newly developed artificial-intelligence tool for accurately extracting the key features of (poly)crystalline materials, i.e., crystal-structure prototype, lattice constant, and (relative) orientation from STEM images. The tool is based on a convolutional neural network, and it is trained on 31,470 simulated STEM images. Then, our model achieves excellent predictive performance for automatically identifying crystal structure and lattice misorientations.