African Mask Art (Art + AI)

I have explored some experiments with generating African Mask art with neural networks. This page is a list of curated collections from my experiments.

The Ikenga Collection

These art pieces are my interpretations of African Mask Art, developed using a two-stage generative adversarial network (GAN). GANs are a class of deep neural networks (a subset of the general field of artificial intelligence) which can be used to model the properties of a given dataset and leverage this knowledge in recreating samples that are distinct but similar to the original dataset. In this collection, I first curate a dataset of African mask art images, representing work dominantly from West, Central and South Africa. Next, a range of experiments are conducted where model parameters are selected and used to train a deep convolutional GAN. The resulting GAN is used to _generate_ a set of novel images. These images are further curated (the pieces below), and a second stage GAN (super resolution) is applied in upsampling the final collection.

The title of the collection (ikenga - which translates to place of strength) (and the names of each piece) are drawn from the igbo language of West Africa.