Object Detection and Recognition
When we look at a picture, we can immediately localize and name a plethora of things represented in it. Even since before the advent of deep learning, researchers have been trying to create machines that can do the same. In recent years, these detectors have reached a level of accuracy that has made many areas of computer vision possible, including self-driving cars, identity verification, object tracking, medical imaging and more. In this talk, Giulio Alessandrini shows how to use the Wolfram Language to build a full object detection pipeline, import or generate the necessary data and create a model to process the result.