Inspiration

Have you ever had trouble figuring out which picture you look better in? I realized that people spend a lot of time asking their friends what they should post on Instagram, Facebook, SnapChat, Tinder, and other social media platforms.

What it does

LookBot.AI prompts the user to input how many photos they want to ultimately upload to social media and to upload all of the images they're considering. It then returns the "best" images based on multiple variables: the emotion portrayed by the person, the tilt of the person's face, and the blur, exposure, and noise levels of the image.

How I built it

I used Flask, Python, Microsoft Azure's Face API, JavaScript, and HTML.

Challenges I ran into

In order for the Python script I wrote to work with the images in the browser, I needed to upload them to a local Flask server. This step was the most difficult for me.

Accomplishments that I'm proud of

I'm glad I was able to create a full-scale web application using Flask. I've experimented with the framework in the past, making web crawlers, but never have built a complete and deployed product using it.

What I learned

I learned how to work with the server-side capabilities of Flask.

What's next for LookGood.AI

I plan on strengthening the algorithm and UI. I also will eventually purchase the LookGood.AI domain so I can make the app available to everyone.

Built With

Share this project:

Updates