Cloud Vision includes several options that you can use to integrate machine learning vision models into your applications and web sites.
The Vision API allows you to easily integrate vision detection features in your applications, including image labeling, face and landmark detection, optical character recognition (OCR), object localization, and tagging of explicit content.
AutoML Vision enables you to train your own, custom machine learning models to classify your images according to labels that you define.
Vision Product Search
Vision Product Search allows retailers to create a set of products and of reference images that visually describe the product from a set of viewpoints.