How Computers Imagine Humans

João Martinho Moura (2017)

Picture (top) and video (bottom):
“How Computers Imagine Humans?”
João Martinho Moura (2017).

Exhibition in Duisburg, Germany, December 2018

Those faces don’t exist. Artificial intelligence (AI) can bring unprecedented benefits to the society, but also it’s becoming potentially more dangerous. Don’t forget that AI is us, made by us and it’s being fed and improved by us every second. 

In this media artwork, AI is used against AI to discover How Computers Imagine Humans, using a selected computer visual noise (one computer) and an AI face detector system (another computer). Both systems running against each other. Both systems running in real-time against each other, using just built-in cameras to communicate with each other.

In current times where GANs (generative adversarial networks) are propagating and also saturating our screens, the subject of art made with AI it’s gaining attention and also reflections on how will we deal with this kind of medium in the future. So, inspired on the foundations of these GANs, I’m presenting a kind of very simple and almost manually made try, using a very well known algorithm used for face detection (a classical one) and an unusual use of its technique, intended to do the opposite of what it is supposed to achieve: instead of trying to locate and capture faces, I generate facial images ‘imagined’ by a computer through the exploration of hypothetical possibilities, starting just from visual randomness (as generating noise it’s a basic procedure on computers). More than what if offers in terms of visualization of what is behind algorithms, this work, as it is presented, with 2 machines interacting with each other without a wired or wireless connection, demonstrates the ‘knowledge’ we humans try to implement into machines to detect ourselves. A kind of awareness about these technologies and their effects (negative or positive) on our society. The result is a kind of a ghost-human face, made by mathematics and probabilities, appearing very slowly as the algorithms work over time.

In the recent years, face detection technologies have been widely used by artists to create digital art. Face detection provides new forms of interaction and allows digital artifacts to detect the presence of human beings, through video capture and facial detection, in real-time. In this work, I explore the algorithm proposed by Paul Viola and Michael Jones, presented in 2001, sixteen years ago, in order to generate imagined faces from visual randomness.

How Computers Imagine Humans. João Martinho Moura (2016)

The first step of any face processing system is detecting the locations in images where faces are present (Yang, Kriegman, & Ahuja, 2002). In 2001, Paul Viola and Michael Jones introduced a machine learning approach for visual object detection which is capable of processing images extremely fast and achieving high detection rates (Viola & Jones, 2001). The Viola-Jones face detection algorithm is the first ever real-time face detection system in computer vision (Wang, 2014). OpenCV, a widely used free open-source library that enables computers to see (Bradski & Kaehler, 2008), implements a version of the Viola-Jones technique, which was extended by Rainer Lienhart and Jochen Maydt (Lienhart & Maydt, 2002). It is then used to detect objects in other images. These objects can be faces or others, like pedestrians or eyes. In my research, I use compulsive brute force requests into a well-known face detection algorithm, widely used in research and industry.

Having studied the Viola-Jones face detection algorithm, I got a very simple question: can a computer imagine and draw a human face, based only on that proposed algorithm?

I present an unusual use of the Viola-Jones technique, intended to do the opposite of what it is supposed to achieve: instead of trying to locate and capture faces, I generate facial images ‘imagined’ by a computer through the exploration of hypothetical possibilities.


Video preview of the artwork (time was accelerated for this demonstration): 


João Martinho Moura, Paulo Ferreira-Lopes (2017), Generative Face from Random Data, on “How Computers Imagine Humans”, ARTECH 2017 – 8th International Conference on Digital Arts, p85-91. ISBN: 978-1-4503-5273-4
Macau, China. ACM New York, NY, USA

Link (Conference)
Link (ACM)

Download paper: [PDF]

Main references:

Yang, M. H., Kriegman, D. J., & Ahuja, N. (2002). Detecting faces in images: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(1), 34–58.

Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 (Vol. 1, p. I-511-I-518). IEEE Comput. Soc. 

Wang, Y.-Q. (2014). An Analysis of the Viola-Jones Face Detection Algorithm. Image Processing On Line, 4, 128–148. 

Bradski, G., & Kaehler, A. (2008). Learning OpenCV: Computer Vision with the OpenCV Library. OReilly Media Inc (Vol. 1). O’Reilly. 

Lienhart, R., & Maydt, J. (2002). An extended set of Haar-like features for rapid object detection. Proceedings. International Conference on Image Processing, 1, 900–903. 

more references in the paper


Related and previous work:
Generative Face Algorithms, João Martinho Moura, 2014
Carpax e o Homem Surdo, João Martinho Moura, 2008

No posts were found.