Investigating essence in images by letting algorithms identify, enhance and erase the areas of most visual importance
Erasing/Enhancing Essentials is an ongoing project that investigate essence in images by letting algorithms identify, enhance and erase areas of images that are of the most visual importance.
The project uses a neural network trained by scientists from MIT, Havard and Adobe to predict visual importance within images “trained on human clicks and importance annotations on hundreds of designs” (Bylinskii et al. 2017). When exposed to a new image the algorithm creates a heatmap which highlights the parts of the image it thinks are most likely to attract the gaze of a viewer.
I use this heatmap to create a mask containing the most important part(s) or essence of the image.
Inside Adobe Photoshop the mask is either used to erase or enhance this “essence”.
In this process the masked area of the image is erased and replaced using Content-Aware Fill. The process is automated and the images are not edited after the Content-Aware Fill step.
The results are empty and cold yet evocative settings, where textures, backgrounds and often overlooked parts of images become the core elements and the center of attention.
In this process the masked area is retained and all other parts of the image are replaced by the “essential parts” using Content-Aware Fill. The process is automated and the images are not edited after the Content-Aware Fill step.
The results are dense collages where key elements of the images simultaneously acts as background, foreground, patterns and texture chaotically fight for the attention of the viewer.