Hi guys,

As I said in the previous post, there is a big opportunity working with Web Apps and Computer Vision. I took a dive into the Internet looking for some tutorials/libraries I could use and I found JsFeat. JsFeat is an open-source project that provides Computer Vision functionality (color model conversions, histogram equalizing, face recognition) on the browser side.

Unfortunately, there isn’t a lot of documentation, only some examples in the official page. Also, there hasn’t been any contribution to the project since two years ago. However, I could make this little application work! Take a look!

First Computer Vision Web App!

This app converts an RGB Image into a GrayScale Image. Yep, that’s all! I’ll add some functionality so you can upload any image you want and this app will display it in grayscale.

If you want to take a look to the code, you can find it at my GitHub repository! If you have any questions, please comment in this post or feel free to contact me.

Technology stack used

  • NodeJs
  • ExpressJs
  • JsFeat
  • Heroku (Deployment)

Conclusions

  • Computer Vision processing can be executed on the browser side nowadays. This app may be seen as something simple, but this kind of processing a few years ago was unthinkable.
  • Everything is moving to a cloud environment. It’s almost for sure that any Computer Vision project will be developed with browser-side processing.
  • Unfortunately, JsFeat seems to be an abandoned project. However, I’m sure similar projects will arise and in a few months we will have an OpenCV version for JavaScript.
  • WebApp allows user interaction easily (Webcam + interactive UI’s)
Advertisements