Learning to see lemon
Learning to See Lemon uses machine learning to identify objects and lemons. It is an artwork created alongside Of Machines Learning to See Lemon, shown at the 2018 London Design Festival.
For the London Design Festival Alistair McClymont worked with Dr. John Fass to create an installation:
Of Machines Learning to See Lemon is a part of an extended project that aims to materialise the way machine learning algorithms categorise and assign value to the data they are trained on. This invisible classification process is usually intended to produce automated decisions, which can have profound consequences for individual and collective freedom. The possible benefits of machine learning are many, but we run the risk of developing technologies of such complexity that our abilities to shape them to serve the common good are severely limited. With this installation we hope to situate machine learning as open to creative exploration and critique. Read more about this artwork here.
Have a look at the machine learning website here:
This uses https://ml5js.org/ and its image classifier to recognise images via the webcam. It then lets tries to classify that image and state how 'lemony' it is. Watch a video below: