Blade Runner Collages

Posted: April 25, 2017 at 3:50 pm

I have not started work on making large collages from Blade Runner clusters and segments since the residency. I ended up writing some code for my public art commission (“As our gaze peers off into the distance, imagination takes over reality…“, 2016) that arranged segments using a SOM. I did not end up using that approach in the final work, so I’m now adapting it to make collages from Blade Runner clusters and then segments.

The following image shows the colour values of each of the 200,000 clusters, in no particular order:

sampleVectorsColoursBGR

Note the palette is largely brownish, which makes sense due to the averaging process and warm fleshy tones in the film. This ground is punctuated by highly saturated colours. I wanted to visualize the underlying data in order to make sure the SOM training is working well and representing the underlying frequency of similar clusters. The following image shoes a SOM trained on all clusters over 500,000 iterations:

SOMResults_500000

It does look to be representing the distribution of colours quite well. Some of the complex structure is due to the network being trained on colour as well as width and height of clusters (not visualized in the image above). Note, this version is using the same HSV colour model used in ‘Watching’, but does not work very well as colour information is highly compressed in 8 bit, which results in some fringing effects (see the dark blue border between magenta and cyan in the lower left of the image).