This document discusses how computer vision techniques can be applied to art history. It provides an overview of different computer vision approaches such as optical character recognition (OCR), face recognition, and image similarity/categorization. Unsupervised techniques like OCR and image similarity require little labeling of data but may not provide as interesting results. Supervised techniques can more precisely locate parts of images or categorize images but require large labeled datasets. The document recommends several free and open-source computer vision libraries and tools that can be used to explore applying these techniques to art history, along with some caveats about training data requirements.