In-Store Facial Recognition Market Research
New technology from Japan can monitor all shop visitors, discerning age, gender, and visiting frequency, and measures the data with a system called ‘NeoFace’, all with a normal PC and webcam - via DigInfo (video embedded below):
NEC has developed a marketing service that utilizes facial recognition technology to estimates the age and gender of customers, and accumulates the data, along with the dates and times that customers visit stores. This data is then used to analyze trends in customer behavior and visit frequency.
This service is provided in Japan via NEC’s cloud computing technology, only requires a regular PC and video camera, and is available for approximately $880 (70,000 yen) per month per store.
“This service is mainly intended for retailers that have several stores. It provides retailers with customer attributes based on facial images. That information is helpful for sales strategies.”
This service can also detect repeat customers across multiple stores. It uses a face detection and comparison engine developed by NEC, called NeoFace.
LTU student shows that computers “understand” art
First of two news stories that could get you thinking about the future of technology and art museums.
The first, a student puts together a database of examples of art history for a computer program to visually analyse and make connections (such as above) - from Lawrence Technology University blog:
LTU student Jane Tarakhovsky showed, for the first time, that computers can match art historians in understanding and analysis of visual art.
In the experiment she let the computer analyze ~1000 paintings by 34 well-known painters, and let the computer automatically deduce the similarities between the artistic styles without using any information other than the visual content. The similarities were then visualized using a phylogeny (a tool normally used to visualize similarities between genomes of different species, but in this case was used to visualize the similarities between artistic styles). Surprisingly, the analysis of the computer was almost identical to the analysis of Art Historians.
For instance, the computer automatically placed the High Renaissance artists Raphael, Da Vinci, and Michelangelo very close to each other, and the Baroque painters Vermeer, Rubens and Rembrandt were placed by the algorithm in another cluster, indicating that the computer sensed that these painters share a common artistic style.
Music/Technology: The Hip-Hop Word Count (HHWC)
The Hip-Hop Word Count (HHWC) is a new Kickstarter project that aims to build a database that will allow for the analysis of hip-hop lyrics – to ultimately ‘chart the migration of ideas and build a geography of language’ that will serve as the engine for a K-12 teaching curriculum.
- OpenInvo: A Marketplace For Innovation (techcrunch.com)
- Fund Your Next Music Album With Kickstarter (jasonkeath.com)
hamlet.line_lengths_diffirence.2_minus_1.excel by culturevis
data: text of Hamlet
X - line position
Y - difference between each two lines, i.e.
(2 - 1), (3 - 2), etc
Original size can be found here
hamlet_line_lengths.mondrian by culturevis
data - text of Hamlet (from project Guttenberg)
X - line number
Y - line length
Full size image here
hamlet_line_lengths.one_word_line_removed.excel by culturevis
data: text of Hamlet
number of lines: 6786
x - line position
y - line length (in words)
Original large size here
Brand Mapping As A Consumer Insights Tool via PSFK
… we cataloged over 7,000 photographs on OkCupid.com, analyzing three primary things:
In looking closely at the astonishingly wide variety of ways our users have chosen to represent themselves, we discovered much of the collective wisdom about profile pictures was wrong.
- Facial Attitude. Is the person smiling? Staring straight ahead? Doing that flirty lip-pursing thing?
- Photo Context. Is there alcohol? Is there a pet? Is the photo outdoors? Is it in a bedroom?
- Skin. How much skin is the person showing? How much face? How much breasts? How much ripped abs?