Imagine you are attending the Cannes film festival or visiting a capital and taking pictures. Wouldn’t it be great if when you are about to share these pictures with your friends and followers, the app automatically proposed hashtags by interpreting the picture, identifying buildings, landmarks and famous people?
While we wait for this capability to come in popular image sharing apps, let’s build something like this with IBM Bluemix:
To analyze the images, the IBM Bluemix catalog provides us with the Watson Visual Recognition and AlchemyAPI (more specifically AlchemyVision) services from IBM Watson. You provide the API with an image (URL or raw data) and in return you get a list of tags or keywords with a confidence score. Watson Visual Recognition can even be trained for fine-grain classification,
For the app, we will pick iOS as our first target; this will be an opportunity to develop with Swift,
Given IBM Bluemix OpenWhisk was just announced at IBM InterConnect, all of the image processing and analysis will be running as an IBM Bluemix OpenWhisk action, outside of the app logic code, with no server to set up and reusable by others.
Voilà, a sample iOS application to automatically tag images and detect faces by using IBM visual recognition technologies:
Take a photo or select an existing picture in the camera roll,
Let the application generate a list of tags and detect people, buildings, objects in the picture,
Share the results with your network.
See how it was done!
While working on this, a colleague asked about the choice of IBM Bluemix OpenWhisk to implement the processing with a question: “Why not call the Watson services directly from the application?” Indeed, this would also work, at least at first since today we’re only considering an iOS app. Now let’s consider this is a real business—you will want to target other systems like Android, Windows Phone or even a more traditional web app. Do you want to have to rewrite the logic in several different languages? What if you want to tune the results a bit before displaying them? And if this image tagging microservice becomes successful, you could even consider providing it as an API for others to consume and integrate (many photo library software would benefit from a well-trained automatic tagging capability). In these cases, you would not want to have to manage the scalability of the service. Instead, you would leave that to IBM Bluemix OpenWhisk to handle transparently.
If you have feedback, suggestions, or questions about the app, please reach out to me on Twitter @L2FProd.
This is exciting and will like to know if the system can be trained to recognize sometimes not so famous personalities.. Essentially, can I load my client images for recognition (private data of course..)
Following InterConnect 2016, I was trying Openwhisk and Swift on Bluemix. I was searching a good demo that implement both, and you did it in a very nice way. I just finish your tutorial in less than 30 min ! and the result is AWESOME !
Now I have to deep in the code… Thank you very much Frédéric ! I can’t wait your next one !
Note : check out the SOmusic article : https://developer.ibm.com/bluemix/2015/05/08/somusic-and-bluemix/
Very nice tutorial. I tried the app but I get TypeError: Cannot read property ‘use’ of undefined” for the openwhisk activation. stderr: at mainImpl (eval at NodeActionRunner (/nodejsAction/runner.js:32:21)
Yantra transformed into an award winning Fintech powerhouse. Yantra Financial Technologies was recognized as a “Company to Watch” as part of the 2016 FinTech Forward rankings released by American Banker and BAI.
The WealthEngine API lets you look up the net worth and financial capacity of almost anyone in the United States, in real time, giving you insight into the wallet share of clients and prospects. Simple to use, it's a restful API that returns JSON.
While working with a client a few weeks ago, we defined a process and organizational governance model for managing Kubernetes clusters in a Bluemix PaaS environment. This blog will outline these best practices to deploy Kubernetes clusters in your environment and the importance of leveraging service policies.