emojiFind

emojiFind's easy to use interface - the best four emoji matches for your expression are displayed, and if you're not satisfied, just retry!
The emoji is automatically pasted into the textbox when you select it.

Inspiration

You are typing in a chatroom with your best buds and you find the perfect opportunity to use a certain emoji. You open a new tab and search for your emoji on Google and you finally find it and copy it onto your clipboard. But, by the time it took to get back to your chat, you realize that the conversation has shifted to another topic and you feel disappointed that it took long to express your emotions. This common problem inspired our team to create a seamless and elegant solution.

What it does

When provided with a picture of the user expressing the emotion that he or she wants to convery, emojiFind will analyze the picture and suggest the closest matching emojis.

How we built it

For our frontend, we used Electron alongside Html/CSS. With Node.js, we were able to use JavaScript for both our frontend and backend. With our backend JavaScript code, we interfaced with a Microsoft Face API to obtain numerical values for the emotions, anger, contempt, disgust, fear, happiness, neutral, and sadness. Then, we compared these obtained values with a database of emotion values of 15 emojis. The best 4 emojis were then displayed to our frontend, which gives the user the choice to copy suggested emojis to the clipboard to paste into their chatrooms.

Challenges we ran into

One problem we ran into was being able to access the laptop webcam to take a picture and passing it through to our API. Another problem we ran into was learning to simulate a keypress with JavaScript. A third problem was finding a way of searching for the closest matching emojis.

Accomplishments that we're proud of

We are proud of being able to have a high degree of accuracy with suggesting the emojis desired by the user. We were surprised by how often the desired emoji was included in the 4 emojis which our application suggested to the user.

What we learned

We learned how to make JavaScript send images as binary data to APIS and gained experienced with formating details on the frontend to appear more aesthetically appealing.

What's next for emojiFind

We would love to increase the amount of emojis that emojiFind could support and search from so that users could have a greater variety of emojis to select from.