Computer Generated Borough Group Paintings by Ella Chedburn

CREATING DATASET:

I gathered a dataset of 600 Borough Group paintings from Borough Road Collection archives, Tate, Art UK, and Google Images. I saved each image individually which facilitates higher quality outcomes (batch downloading would mean lower quality images and less control over what gets saved – would end up being photos of the artist or other random artists work etc mixed in).

FIRST TRAINING STAGE:

The original GAN was designed to create illustrations of birds, but I fed it my Borough Group paintings instead. After 3000 steps, the images weren’t really showing any particular subject and had a high FID score (which is bad – the lower the score, the closer the generated images are to the original images. A high score is not good – mine was around 120 and showing up red/bad), so I decided to train it for 2000 more steps. The FID score decreased a little but remained high.

Since the Borough Group paintings contain differing subjects (some are landscapes, others are people, some are objects, or totally abstract) I think it is hard for the software to create figurative images. It works by looking for patterns, and the different subjects create different patterns. To avoid this, I’d have to create individual datasets for each subject (one for people, one for landscapes etc) but there’s not enough images for this (you need between 500-5000 images in each dataset).

After 3000 steps, here are 24 of the sample images:

Figures look like they’re coming through. the one below in particular reminds me of several of the figures in my dataset, particularly ‘Standing Figure’ by Dorothy Mead. So I trained for longer to see if these figures would emerge fully.

Left: computer-generated, Right: Dorothy Mead

SECOND TRAINING STAGE:

I did 2000 more steps, so at 5000 steps the sample images looked like this:

At this point I generated 50 random full quality images. Impression of figures was no longer there in the ones I expected, although new figures did appear. I felt that there was no need to train further, as the figures seemed to get lost the more they’re trained.

EXPORTING IMAGES:

The software generates thousands and thousands of new images, so finding/saving the best ones can become a mammoth task! I can choose the level of truncation -- closer to 0 = less diverse but very realistic and 1 = more diverse but maybe deviating from the rest of the sample. I decided to go for truncation of around 0.8 to get a diverse range of pictures. Then I could scroll through the pictures in different directions to select individual favourites, or get the software to generate a random sample to remain objective.

CREATING A VIDEO:

I selected different images to merge together to create an interpolation video. I included abstract works, landscapes, and figures.

Creating its own signature style of quadrangular structures:

Seemed to keep getting preoccupied with painting these grey blobs!

COMPARISONS:

Left: computer generated. ‘Oxen Ploughing – Spain’ by Dennis Creffield

Left: computer generated. Right: ‘Bent Figure’ by Edna Mann

Left: computer generated. Right: ‘Tregor and Tregoff, Cornwall’ by David Bomberg

Left: computer generated. ‘Oxen Ploughing – Spain’ by Dennis Creffield

Left: computer generated. Right: ‘Children's Swimming Pool, Friday Evening’ by Leon Kossoff

Left: computer generated. Right: ‘From Willesden Green, Autumn’ by Leon Kossoff

Left: computer generated. Right: Standing Nude by Dennis Creffield

Left: computer generated. Right: ‘Seated Nude’ by Dennis Creffield

PROCESSING AND INPUT:

These are computer generated Borough Group paintings created by artist Ella Chedburn (@ellachedburn.art). Bomberg famously said he hoped his students would find the "spirit in the mass". By using machine learning software to generate paintings from a dataset of over 600 Borough Group images, perhaps the “spirit in the mass” has been found?

The generated artworks are primarily abstract with some landscapes and impressions of figures coming through. The software’s loosely painted nudes and linear abstract compositions could be lost Dennis Creffield paintings, while certain landscapes are eerily close to Bomberg’s hills and mountains. Although many images have a convincing texture of thick layered paint, several expose their computerised nature with their smoothness. However, the overall aesthetic could successfully pass as a member of the Borough Group: loose angular brushstrokes and mostly desaturated tones with occasional shots of bold warm pigment. Just like a true artist, the software has even begun to create its own signature style of large cross-hatched structures and mysterious dark grey blobs.

Do you think A.I. could be the Borough Group’s newest member?

ARTIST BIO

Ella Chedburn is a Fine Art (BA Hons) graduate from Kingston School of Art. Her practice squeezes nature through a digital lens: scanning trees, coding virtual reality forests, wiring plants to Arduinos, and projecting into woodland. She playfully misuses technology, encouraging glitches to run throughout her digital work and mimicking them in her prints and books. Over the past year, misinformation and context-twisting has been a particular driving force; sparking the creation of her dreamy algorithmic narratives, mystical inventions, and fictional documentaries blending science with folklore. Most recently, she has been creating computer-generated paintings for the Borough Road Collection and William Morris Society, questioning whether ‘the artist’ can be found within the machine.

Interpretation of the Meaning a new work by Sara Choudhrey

Interpretation of the Meaning, Sara Choudhrey

Watch the full piece here.

Still from Interpretation of the Meaning, Sara Choudhrey, 2020

Layering, displacement, and motion are key elements explored in Interpretation of the Meaning, an animation produced in response to the early work of David Bomberg and his contemporaries engaged with the Vorticist and Furturist movements. It is a consideration of alternative ways of looking, of materiality, technological advancement and our perceptions of time and continuity.

David Bomberg is often portrayed as someone who was in lifelong search, in contemplation of a truth and seeking a sense of belonging. His work produced in response to time in the Middle East, and Toledo in Spain also resonated with me. There is also his diaspora identity whilst living in London, and his having travelled to locations significant to Islamic history, including Jerusalem. Of course, the contentious situation in this region has evolved greatly, and with a change and movement of time, one wonders what the futurists may have made of the world in which their works are viewed now.

The title of the piece:

There is also a strong theme of spiritual and religious heritage in the work, and is conveyed through the title ‘Interpretation of the Meaning’, a phrase that is used for explaining and translating sacred text, often from one language to another. It implies that in the process of translating, there is a limitation in portraying the original intended meaning. Those who are multi-lingual will appreciate this, where there may not always be an equivalent phrase or word to describe the extent and essence of the original, however, in using the phrase ‘interpretation of the meaning’ there is an implied acknowledgement and value for authenticity. The play on words continues in the notion of artistic movements, movement as portrayed in the audio, in the animation format, with its own timeline and the movement of the geometric forms.

The audio:

The audio for this artwork uses the sounds of various clocks ticking in and out of sync, with additional chimes and sounds of timepieces and machinery. They are as abstracted as the sense of the space that is being explored in this virtual and unknown landscape. The viewers movement and that of the geometric shapes is an investigation of what we perceive of as our surroundings and how a space is to us as we are to it. The sound is heavily influenced by my current surroundings at home, where my father, a horologist, has set up many clocks in the midst of repairs. They have not all been set up with the same times. The correction of the time shown on the clock face is almost arbitrary. These clocks embody their own timelines, speak of having their place somewhere, belonging to someone and therefore being of material significance. They act as both props and reminders of the passing of time.

The geometry:

The animation presents what is known as an Islamic geometric pattern. It is an expanded design from an in-laid panel from the early 16th Century Al Ghuri complex in Cairo, Egypt. I chose this pattern as I found the formation of shapes and structure intriguing. It is not common to find pentagons on a 6-fold composition yet upon analysis there appear to be hidden correlations in the structure of the design that allows the 5-sided shapes to become apparent through divisions in a 6-fold layout. The geometers from this period and region would have cleverly discovered these hidden properties but did not leave many clues behind regarding their construction methods, and so there is a further connection to the idea of interpretation here. It is only through deconstructing and analysing which allows for possibilities in reconstruction of the pattern, an aspect of my practice which I wrack my brain over but also thoroughly enjoy.

My interest in the Vorticist movement:

I am in awe of artists who were inspired and exposed to cubism and the style that developed into Futurism and Vorticism. There is an abstracted conveyance of the world through this style yet it is not entirely unidentifiable through the sliced forms. The style also lends itself to an acknowledgement of the geometry present in our habitat, whether spaces of nature or those which are constantly manipulated by humankind. I feel the success of the movement centred on a strong understanding and contemplation of the way we engage with spaces through movement and also our understanding of spaces centred on a perception of light.

Still from Interpretation of the Meaning, Sara Choudhrey, 2020

Still from Interpretation of the Meaning, Sara Choudhrey, 2020

Still from Interpretation of the Meaning, Sara Choudhrey, 2020

Stevie Rae Hope Scanner GIF

In examining the works of Bomberg, I found myself most interested in the textural quality of the work, which acts as evidence of the process of creating the painting, and of the painters presence within the work. Keeping this in mind, I chose to work with a scanner, creating my own self portraits and scanning as I painted, and also as I removed these paintings from the scanner bed in order to create the next one. I animated some of the painting process, to show how the buildup of paint works to create an image. The paintings created only exist permanently in digital form, as each is wiped away upon completion. 

See more works by Stevie Rae Hope here.

What are we but meat? Original posters by Cecilia Reeves

Original posters designed by Cecilia Reeves for the performance “What are we but meat?” at the Borough Road Gallery.