Object Detection with AutoML Vision

This tutorial shows you step by step how to use Google Cloud Platform's AutoML vision API to performance object detection and object localization using bounding boxes. AutoML offers a drag and drop interface to label your data before running the model. In this video we create a machine learning model that can both label and localize particular object of interest with a set of training data images. We analyze medical congresses and work to create a model that can extract figures and images included with each abstract as well as any tables found in these publications. The entire process will involve zero coding and leverage Google's Automl Vision product. #automl #googlevision #computervision Example Training Data CSV https://storage.cloud.google.com/marketing-files/pdf-images_pdf-extraction.csv