Custom Vision provides developers with the possibility to personalize the image detection and analysis service of Azure Cognitive Service, to tailor the data model to specific use cases. This session describes the architecture of the Custom Vision service to build ML image classifiers, to bulk label images with a REST API, and to train a model and use it online and offline in a "smart helmet". Trained models can also be utilized "at the edge", on devices with no live connectivity to the Cloud, offering computer vision capability to field technicians and in IIoT (Industrial Internet of Things) contexts.