Visual Recognition with IBM Watson and Python – Video Series
I posted three videos in which I show you how to do visual recognition in Python by making calls to IBM Watson’s API.
Watson is a supercomputer, a specific form of artificial intelligence. You can register for a free account on IBM Bluemix website and use its super-powers.
Breakdown of my video tutorials:
- In the first video I explain how to use Watson for image classification.
- In the second video I show you how recognize text from images with Watson.
- I the third video I show you how to use Watson for face detection and facial recognition.
Not so very long ago, it would require one to write hundreds, if not thousands, of lines of code and work with big computer vision libraries to reach the same goals. Now, call an API in 2-3 lines of code, and there you have it…
With these minimum requirements and with the readily available modules, libraries, and APIs, I think the opportunity now stands in building code algorithms that would allow for all of these to work together smoothly.
One example is my voice assistant that I wrote in Python:
- Uses Google’s Speech Recognition API to get input
- Uses Amazon’s Ivona for Speech Synthesis
- Uses WolframAlpha, Google, and Wikipedia’s APIs to retrieve results
- Uses different Python Modules to execute commands
My voice assistant is only ~400 lines of code and it took a couple of summer nights to build it; it is modest but it serves its purposes; it sucks resources (like a vampire) from many amazing technologies (mentioned above). Had I challenged myself to build it just a few years ago, I could not have done it as easily and as conveniently as I can do it now.
Anyway, bottom line: there has never been a better time to learn programming…