- Detecting text with optical character recognition
- Navigating through the Vision API documentation
- How the Vision API can detect facial expressions
- Detecting and extracting multiple objects
- Preparing data for batch images
- Working with JSON and Pandas
Skill Level Intermediate
- [Jonathan] So you're a data scientist or maybe you're a developer, and you're trying to wrap your head around machine learning and AI, but the experience is overwhelming. And quite frankly, I don't blame you. There's a lot of material out there that can help you build out machine learning for whatever you need, but sometimes it's just easier to see it in action. Enter Google Cloud Vision. Google's Cloud Vision is built on powerful computer vision models that power several Google services. This means that you have access to Google AI-level capabilities with simple API calls without having to train any machine learning model. Hi, I'm Jonathan Fernandes, and in this course, I'll show you how to use Python to make calls to Vision API. You can also use C#, Go, Java, Node.js, PHP, or Ruby, but let's just dip our toes into this with Python. That being said, you might want to brush up on Python a bit before launching this course if you haven't touched it in a while. Now, most of the stuff is pretty straightforward, so even if you're familiar with another programming language, you should be able to follow along. Some of the services I'll delve into are text detection, label detection, and face detection, amongst others. I really enjoy this stuff and want to make it accessible for those who want to get into it as well. So let's get started.