Shashank Singh, 29, took a three-month sabbatical from his job as lead engineer at a Vidyavihar-based tech firm to create an app with which he hopes will fight child trafficking. He had completed his Bachelors of Technology in Computer Science and started his first start-up by the age of 23. But the inspiration behind this initiative came from much before his education and entrepreneurial ventures.
“When I was nine, a man tried to abduct me. A bystander intervened, and united me with my parents. According to Wikipedia stats, a child goes missing in India every eight minutes,” says Singh.
Along with colleague Amol Gupta, he created an Android application called Helping Faceless in October last year. It allows citizen volunteers to snap a picture of a street child and compare it to photos from an NGOs database. Singh tweaked an open source technology that Facebook uses called Deep Face to create the algorithm that would match the images.
How did it start?
We started with a simple Ruby on Rails API server to accept information from apps and other sources. Slowly but steadily we have been adding complexity around this simple server to create more functionality.
To keep growing complexity in check, we use Service-Oriented Architecture, the whole system is broken into smaller modular application connecting with each other on wire. So at end of we use whatever language or framework is best suited for the task at hand.
Our current technology stack is as follows:
- Server Side : Ruby on Rails
- Client Side: Java for Android, Objective C for IOS, Web frontend for NGO’s
- Analytics: Python (Scipy/Pandas/Numpy/scipy.stats FTW!! ). We are in process of integratingApache Storm and Apache Mahout for analytics and subsequent report generation.
We Use Heroku, Linode as VPS. Airbrake guys were amazing and they helped us with a beefier free account to catch bugs and errors. Also we use Heap Analytics to talk figure out service usage in terms of traffic.
For face recognition needs we use library from University of Michigan called OpenBR (Open Biometrics). It’s modular design makes it much more easier to drop it into our pipeline (see the 2013 paper Open Source Biometric Recognition). This modular design gives it a distinct advantage over OpenCV, also making experimentation quite simple.
If you want to help us out our code is available at Github, just fork it and start coding.
What ‘s next?
- Lower Rate of false detection in Face Recognition phase, we are looking at you Facebook (see the Facebook publicationDeepFace: Closing the Gap to Human-Level Performance in Face Verification)
- Better Gender and Age Detection .
With ideal wish-list being so big, we had to prune it to fit into realistic timelines but these are few things I would love to have.
- Gamification of Pledge and based on frequency of contributions.
- App side face recognition.
- Real-time alerts in case a child goes missing.
- Take it nationwide and even to more south-east asian countries like the Philippines .
- Human trafficking: Currently the model we are using for face recognition is only trained on face from age of 10-20, we want to extend it by increasing training data.
- Establish a platform for NGO and governmental organization to safely share data.
To help out: www.helpingfaceless.