“Declassifier processes pictures using the YOLO computer vision algorithm. Instead of showing the program’s prediction, the picture is overlayed with images from COCO, the training dataset from which the algorithm learned in the first place.”
“Anthropological Taxonomy in first photographs taken with a new digital camera.”
Pure CSS illustrations and discussions of their rendering differences in various browser versions.
http://diana-adrianne.com/purecss-francine/
https://twitter.com/
“The installation self-generates images using two flatbed scanners laying on their side, with scanning surfaces pointing at one another. A computer script creates automatic mouse movements, randomizing the settings of the proprietary scanning software interface, and beginning a scanning process.
Each newly created image is then analyzed by a series of deep-learning algorithms trained on a database of contemporary artworks in economic and institutional circulation. When an image matches an existing artwork beyond an 83% match, it uploads it to this website and a twitter account.”
“With 657 billion digital images per year being captured and pushed to the web, it is likely that at some point in your life you’ve taken a photo that already exists. And you will continue to do so with the help of this app.
CCamera is the first camera app that takes images that have already been uploaded to the internet. It brings your photos to the next level — because they’re not yours.”
Photoshop filters applied to the „first“ photoshopped image („Jennifer in Paradise“).
“Still File is a series of 4 photographs recreating computer renderings as physical scenes. The photos’ artifacts, surroundings, camera settings and lighting has been shaped intending to resemble 3d graphics of different types.”
“… is a hybrid graphics editor and programming environment for creating interactive diagrams.”
“A portrait ‘drawing’ machine at a shopping mall is made to create his own portrait by placing a mirror in the portrait booth.”
https://vimeo.com/
And other projects:
http://tarakelton.com
“These source images were randomly grouped and digitally merged with a Photomerge script inside Adobe Photoshop. The script is a common algorithm used to stitch separate images together into longer panoramas. In the case of “Iconoclashes,” the script attempts to blend these “God”-tagged images together, creating chimeric deities, hybrid talismans, and surreal stellae, gods and statues.”
“If completed, it would contain every possible combination of 1,312,000 characters, including lower case letters, space, comma, and period. Thus, it would contain every book that ever has been written, and every book that ever could be – including every play, every song, every scientific paper, every legal decision, every constitution, every piece of scripture, and so on. At present it contains all possible pages of 3200 characters, about 104677 books.”
Also, the principle applied to image data:
https://babelia.libraryofbabel.info
“The objective of allRGB is simple: To create images with one pixel for every RGB color (16777216); not one color missing, and not one color twice.”
“This project investigates the idea of using computation to “use up” a piece of technology, in this case a digital camera. Using custom-written software (and a very long period of time), every possible photograph is generated, one at a time and in numerical order.”
See also his other projects exploring ideas of technical images, algorithms, abstraction, and computational vision.
“This book contains the first Google image result for every word in the dictionary.”
Digital image atlas following ideas of Aby Warburg and Walter Benjamin, focused on objects of non-western culture. Not very rich of material.
“…for the display an open number of artifacts, objects and positions that may enter via an edited matrix of attributes into variable, unpredictable, and dynamic relations with each other.”
Book and website with essays about future forms of reading. Free to read online.
Research project about the possible role of networked images in the sciences. A system to assamble, categorise, annotate and link images wants to explore new forms of working with images in other scientific contexts than in art history. Some examples on the website.
The camera produces no image but a textual description of the motive, written by some strange user of Mechanical Turk web service.
Tool for drawing with tagged video content to create a dynamic networked image.
