Registration for the O'Reilly Artificial Intelligence Conference, September 18-20, 2017, in San Francisco, is now open. Recently, I set out to install a doorbell in my new house and thought: why doesn't my doorbell tell me who is at the door? Most of my DIY projects end up costing more than the equivalent product, even if I value my time at $0 per hour. Something about supply chains and economies of scale, I guess. In the course of this project, I built a door camera that is not only way cheaper than my Dropcam, but it has some genuinely useful features that, for some reason, aren't available on the market yet.
Imagine you work for a marketing agency that has tens of thousands of stock images. You find that many images don't have descriptive file names and others are completely mislabeled. You don't want to spend hours and hours relabeling them and moving them around to different folders. But what if you could find the images you need without relying on metadata? In this blog post, we will review an end-to-end solution to show you how to do this using Amazon Rekognition.
In this post, we will build a voice control smart light with Azure IoT hub. All hardwares we need are shown in the picture below, a Raspberry Pi, 3 LEDs, 3 220Ω resistances, a breadboard, some DuPont lines, and Amazon Echo Dot. Don't worry if you do not have one of them or even any of them, we still can make things work with simulated device, and I will explain how to do that and the end of this post. Before we begin this awesome job, let's make it clear how does the entire flow of the information go from your voice to the light turn off or on status. Firstly, Amazon Echo Dot records your voice and send it to Amazon Cloud, and Amazon Cloud transforms your voice to command.
Object recognition is one of the most exciting areas in machine learning right now. Computers have been able to recognize objects like faces or cats reliably for quite a while, but recognizing arbitrary objects within a larger image has been the Holy Grail of artificial intelligence. Maybe the real surprise is that human brains recognize objects so well. We effortlessly convert photons bouncing off objects at slightly different frequencies into a spectacularly rich set of information about the world around us. Machine learning still struggles with these simple tasks, but in the past few years, it's gotten much better.