Data Mining: Text Mining, Visualization and Social Media

How Old Are You Really?

Bryant Smith sent me a link to a tool he's developed which uses a game-like mechanism to gather age perception data from users: How Old Are You?While it is interesting to compare your guess with the ground truth, I think the real opportunity here is in getting the data in the hands of a number of groups including psychologists and machine learning people.

I've spoken with Bryant about this and he's certainly open to the idea.

The Age of Immersive Photography

I've posted before about PhotoSynth, EveryScape and Antonio Criminisi's work. I wanted to round out that set with a pointer to the Global Connection work at CMU in collaboration with NASA, National Geographic and Google. The Global Connection project has, in part, a system called GigaPan which allows for the exploration - via the familiar tiled image interface - of very high resolution images: something like an AJAX version of SeaDragon here at Live Labs. The project can trace its roots back to technology originally created to help NASA scientists explore the images being sent back to earth from the mars rovers.

An interesting distinction between the approach taken by PhotoSynth and EveryScape, and that taken by GigaPan is the manner in which images are gathered and assembled. PhotoSynth and EveryScape rely on collections of images that may be only loosely associated at origin (taken at different times, by different people, with different cameras and so on). GigaPan, on the other hand, involves a special camera mount which hosts a consumer grade digital camera. The robotic mount then takes a series of pictures which are then stitched together algorithmically.

One of the best examples available on the Global Connections site is this image of the Golden Temple in India.

Zooming in, we can see a great amount of detail: