Random | Archive | Twitter | About

Ben Bashford - Notebook of Things

1 post filed under face recognition

15834155771

a quote posted 3 weeks ago

filed under: robot readability, face recognition,

It starts off with “huh?”, a sense of mystification about what the algorithm could be responding to. Then there’s a kind of aesthetic of the glitch. “Oh it’s a screw up, how funny and slightly troubling”. But then finally, the more of these I saw, the more the effect started to feel truly other: like a coherent, but alien idea of what faces were. It made me wonder what I was missing. “What is it seeing there?

— Greg Borenstein - Machine Pareidolia: Hello Little Fella meets FaceTracker

1 post filed under face recognition

15832264400

a photo posted 3 weeks ago

filed under: computer vision, face recognition, pareidoila, facetracker,

Greg Borenstein pointed FaceTracker at Matt Jones’ Hello Little Fella Flickr group.
An exploration of machine pareidolia.

Greg Borenstein pointed FaceTracker at Matt JonesHello Little Fella Flickr group.

An exploration of machine pareidolia.

1 post filed under face recognition

7839978975

a video (reblogged from elephantcandy) posted 6 months ago

filed under: face recognition, input,

FaceOSC by Kyle McDonald is built on open source FaceTracker code from Jason Saragih. It’s a tool for prototyping face-based interaction. .

(Source: elephantcandy)

1 post filed under face recognition

5607900936

a photo posted 8 months ago

filed under: art, face recognition, openframeworks,

Hit Counter by Zach Gage uses face recognition to count (and display) the number of people that have looked at it.
“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.”

Hit Counter by Zach Gage uses face recognition to count (and display) the number of people that have looked at it.

“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.”


1 post filed under face recognition

4340444989

a video posted 10 months ago

filed under: computer vision, tracking, face recognition,

TLD (aka Predator) is an algorithm for tracking of unknown objects in unconstrained video streams. The object of interest is defined by a bounding box in a single frame. TLD simultaneously tracks the object, learns its appearance and detects it whenever it appears in the video. The result is a real-time tracking that typically improves over time.

Would you like to know more?

1 post filed under face recognition

1150198407

a photo posted 1 year ago

filed under: face recognition, projection, art, open frameworks, Magic,

Durchsehen, Exp. 01 (augmented perspective) by Markus Ison and Daniel Franke uses face tracking and projection to allow the viewer to magically “see through” a concrete cube.




Durchsehen Exp. 01 (Docu) from Daniel Franke on Vimeo.
“A camera fixed on the concrete cube sculpture recognizes the presence of human faces within its scope. With a randomized choice it will focus on one of the bystanders and adjust its movement to his; tracking the eye movements of the viewer, a software computes the corresponding angle of view projecting onto the cube the very section of the space the sculpture is blocking from the viewers eye; thus making the cube appear transparent.”

Durchsehen, Exp. 01 (augmented perspective) by Markus Ison and Daniel Franke uses face tracking and projection to allow the viewer to magically “see through” a concrete cube.

Durchsehen Exp. 01 (Docu) from Daniel Franke on Vimeo.

“A camera fixed on the concrete cube sculpture recognizes the presence of human faces within its scope. With a randomized choice it will focus on one of the bystanders and adjust its movement to his; tracking the eye movements of the viewer, a software computes the corresponding angle of view projecting onto the cube the very section of the space the sculpture is blocking from the viewers eye; thus making the cube appear transparent.”

1 post filed under face recognition

953408857

a photo posted 1 year ago

filed under: face recognition, responsive objects, retail, uncanny valley,

Pallette and UT Pallette are $50,000 Japanese mannequins that change their pose when they “sense” people looking at them. It’s all based on motion capture with proximity sensors at the moment but their designer Tatsuya Matsu, boss of Flower Robotics says that future versions will feature face recognition.
 ”It makes the product the mannequin wears look more attractive, increasing consumers’ appetite to buy”. He also says “Consumer attention would be diverted to the face if there were one.” which explains why they look the way they do. They’re avoiding the uncanny valley.
Via Inventorspot.

Pallette and UT Pallette are $50,000 Japanese mannequins that change their pose when they “sense” people looking at them. It’s all based on motion capture with proximity sensors at the moment but their designer Tatsuya Matsu, boss of Flower Robotics says that future versions will feature face recognition.

 ”It makes the product the mannequin wears look more attractive, increasing consumers’ appetite to buy”. He also says “Consumer attention would be diverted to the face if there were one.” which explains why they look the way they do. They’re avoiding the uncanny valley.

Via Inventorspot.

1 post filed under face recognition

949745409

a video posted 1 year ago

filed under: advertising, analytics, face recognition, privacy, screens,

Minority Report comes true (again). In Tokyo, facial recognition technology in billboards read your face and run tailored ads.

Also see: CNN - Ads with cameras and Quividi.