comvis

Projects on Face Detection/Recognition

[comvis]

Smile TV by David Hedberg, 2014. A TV works while only the viewer smiles.

[comvis]

Unseen Portrait by Philipp Schmitt, 2014-2015. Portraits distorted until unidentifiable as a face by machine vision.

[comvis]

font-face by Andy Clymer, 2011.

via h&fj

[comvis]

Pay per Laugh, 2014. Barcelona comedy venue, the Teatreneu club uses facial recognition software to charge €0.30 per laugh, not per show.

Project video

via The Independent

[comvis]

Eye Catcher by Interactive Architecture, 2014. A frame that follows its viewer and looking back at it.

Using a combination of industrial robotics and high power magnets, a seemingly inconspicuous frame on a wall, magically comes to life. The Eye Catcher project in its conclusion has developed a novel expressive interface where emotion recognition algorithms read audience faces and in-turn trigger the animation of a face formed of ferrofluid.

via Prosthetic Knowledge

[comvis]

Anobymous Gods by Marion Balac, 2014.

"Screen shots from Google Street View, Where the Google robot blurs Automatically Recognizes Every face it - Including statues' ones.

In Las Vegas from Google Street View , the Sphinx swapped his flamboyant mask against the face Touthankhamon eroded his Egyptian model.

If any of our images contains an identifiable face [...], our technology automatically blurs these elements to prevent identification of the person .

Blurred by Google, all faces are equal. So these large statues - religious or commercial - they ignore those who look unilaterally from their seats."

[comvis]

Face Cages by Zach Blas, 2013. A cage-like mask inspired by biometric diagram.

"A visual motif in biometric facial recognition is the minimal, colorful diagrams that visualize over the face for authentication, verification, and tracking purposes. These diagrams are a kind of abstraction gone bad, a visualization of the reduction of the human to a standardized, normalized, ideological diagram. When these diagrams are extracted from the humans they cover over, they appear as harsh and sharp incongruous structures; they are, in fact, digital portraits of dehumanization.

Face Cages is a dramatization of the abstract violence of the biometric diagram. Diagrams are fabricated as three-dimensional metal objects, evoking a material resonance with handcuffs, prison bars, and torture devices used during slavery in the US and the Medieval period. The virtual biometric diagram, a supposedly perfect measuring and accounting of the face, once materialized as a physical object, transforms into a cage that does not easily fit the human head, that is extremely painful to wear. These cages exaggerate and perform the irreconcilability of the standardized, neoliberal biometric diagram with the materiality of the human face itself–and the violence that occurs when the two are forced to coincide."

[comvis]

Nonfacial Mirror by Shinseungback Kimyonghun, 2013. A mirror that turns when it sees a face.

"The mirror avoids faces. One can look at his/her face in the mirror only when it’s a nonface.”

[comvis]

Anthroptic by Benjamin Rosenbaum and Ethan Ham, 2007. A book consisting of 8 Images containing the artist's face faultily recognized by a facial recognition algorithm and one story for each image.

The images were taken from Ham’s online project “Self-Portraits” in which he trained a facial recognition program to his face before unleashing it onto the internet photo service Flickr. While searching the millions of photos on Flickr for its creator, the computer program sometimes made mistakes, identifying inanimate objects as the artist.

These mistake images became the starting point for Rosenbaum’s short short story that can be read in any order.

See the book online Buy the book Hear the stories

[comvis]

Avatar, Portrait by Shinseungback Kimyonghun, 2013.

"‘Portrait’ is a series of portraits representing an identity of a movie.

A custom software detects faces from every 24 frames of a movie, and creates an average face of all found faces. The composite image reflects the centric figure(s) and the visual mood of the movie."

Interview with Wired UK Article on Creative Applications Net

[comvis]

Anti Face by Adelheid Mers and Robert Woodley, 2013. Anti Face creates a face that is opposite to a given face.

"The Anti Face program is face recognition turned upside-down. After looking at your image, it creates a face as different from yours as possible. It might change your gender, your age, your expression. The one dimension it will not work with much is skin color or skin tone. This is because we apply a lighting equalization calculation prior to performing the recognition.

Here are the technical details: Eigenfaces analysis is a statistical face recognition technique. It uses Principal Component Analysis to calculate a set of Eigenvectors, or Eigenfaces. These Eigenfaces can be thought of as ‘face ingredients’. To calibrate the model, we calculated 60 Eigenfaces on a training set of over one thousand faces. Whenever an image is uploaded, it is subjected to a subspace projection that reconstitutes it as a linear combination of these Eigenfaces. Normally at this point, a face recognition algorithm would look for the closest match in this 60-dimensional Eigenface space. However the anti-face calculation is not a face recognition algorithm. Instead, it creates a face opposite to yours, rather than finding a face similar to yours. It does this by multiplying each eigen value by -1.”

Also available as App Anti-Face Model Specification and Calculation Details (via algopop)

[comvis]

Face It - Workshop on Face Detection/Recognition/Tracking

Face It - Workshop on Face Detection/Recognition/Tracking by Daniel Shiffman, 2013.

A "syllabus" and repository of Processing examples for ITP fall workshop about face detection, recognition, and miscellaneous tracking methods.

[comvis]

Reface by Golan Levin & Zachary Lieberman, 2007. Face detection captures video of visitors' faces and composes endless combinations of them.

"Reface uses face-tracking techniques to allow automatic alignment and segmentation of its participants' faces. As a result, visitors to the project can move around freely in front of the display without worrying about lining up their face for the system's camera. The video clips recorded by the project are 'edited' by the participants' own eye blinks. Blinking also triggers the display to advance to the next set of face combinations.

Through interactions with an image wholly constructed from its own history of being viewed, Reface makes possible a new form of inventive play with one's own appearance and identity. The resulting kinetic portraiture blends the personalities and genetic traits of its visitors to create a 'generative group portrait' of the people in the project's locale."

[comvis]

Drawing faces instructed by facial recognition by Matthew Plummer-Fernandez, 2013.

"...when my drawing receives a higher face detection score I progress with my drawing, when I score lower my last mark is undone. Its a very strange feeling, like being one of those artists at a police station working with a witness who is trying to describe a face, but limited to a vocabulary of just 'getting warmer, getting colder'."

[comvis]

The Face of TV by David Tinapple, 2007. Face Detection finds faces from TV and makes an average face.

"Custom software, automatically gather all faces it finds on TV to compute an average. Here I examine eight different cable TV channels, gathering thousands of faces over the course of a day. Here we have Fox News, CNN, MSNBC, BET, MTV, CSPAN, PBS, and CBS."

[comvis]

Hit Counter by Zach Gage, 2009. Facial recognition counts the number of people who have viewed the work.

"Using facial recognition software, Hit Counter narcissistically counts the number of people who have viewed it, and displays that number as the artwork. 

It is a throwback to the early days of the internet when hit counters were proudly displayed as signs of social status, re-contextualized into the gallery environment."

(Artist's interview with Rhizome)

[comvis]

Cheese by Christian Moeller, 2003. Models trying to keep smiling in front of an emotion recognition system.

“Cheese is an experiment in the architecture of sincerity. On camera, six actresses each try to hold a smile for as long as they could, up to one and half hours.

Each ongoing smile is scrutinized by an emotion recognition system and whenever the display of happiness fell below a certain threshold, an alarm alerted them to show more sincerity. The performance of sincerity is hard work. ”