Project definition
Have you ever feel this blackout during an conversation, when you want to talk about an object but you don't know how this object is called ?
This blackout can be due to a lack of vocabulary, or more simply because of too much beer during the happy hour on the rooftop. But this situation can be really upseting and tiring. What if i tell you thay AI can recognize this object that you really want to talk about and put an end to your blackout ? That is exactly what our application, object detector is made for !
What are we using ?
To create this AI, we're going to use ml5.js which is a JavaScript library.
This library aims to make machine learning approachable for a broad audience of artists, creative coders, and students.
With the deep learning we can teach to an artificial intelligence to recognize images.
We give to a computer many images, like cat's images, but with different cat in each image : different colors, different postures, different races, different sizes.
With all those images, the artificial intelligence (AI) will learn and keep those images in its image database.
With an algorithm, the AI will try to recognize another image that we gave to it later.
The AI will try to compare the image with all of the images which are on its image database.
And finally we will answer that the image that we gave him is indeed a cat because he has compared it to his database.
How do we use it ?
Firstly, you have to reference the library in your index.html file :
Afterwards, you will have to create a .js file to include the code for ml5.
Our ml5 code will have two essential components.
One that will hold the image and another that will give the result with the highest probability :
It's also possible for the user to drop directly his image on the app, and if you want this to be possible, here is what you have to write :
Of course, if you want this option be available for the user, you will have to write this in the html file, so that they have somewhere to drop the image:
