Auto-Emoji

It's useful to include emojis in your messages as a quick indicator of emotional state, but why should you have to call up a special keyboard, or scroll through many alternatives, when your emotional state could be read off your face? The goal of this project is to augment the on-screen keyboard by using the front facing camera to just read off the emotional state (using a standard facial emotion classifier) and put the right emotion in. It could also be useful to use the rear camera to capture suitable non-emotional emojis, such as recognising a burger, a champagne glass, a cute puppy and so on.

An earlier version of this project was offered (but did not proceed) with the following description:

Client: James Jillians, Sparx <James.Jillians@sparx.co.uk>

People increasingly rely on emoji to express the tone of digital communications. But as the set of emoji icons grows, it is frustrating and time-consuming to select the right one. The OpenFace library (originally developed in Cambridge) is an open source facial behaviour analysis toolkit, that can monitor a webcam to detect emotional state via action units, such as smiling or raised eyebrows. Your task is to build a custom keyboard app that can insert appropriate emojis directly into the text, based on “commands" directly received from the user’s face.