Finding Naked People (Image Processing)

May 2nd, 2009 by Ruwan

lolz, have a look at this blog on Keeping Abreast of Pornographic Research in Computer Science

Lenna and Image Processing

May 2nd, 2009 by Ruwan

len_std

The Lenna (or Lena) picture is one of the most widely used standard test images used for compression algorithms. The comp.compression FAQ says the following:

For the curious: ‘lena’ or ‘lenna’ is a digitized Playboy centerfold, from November 1972. (Lenna is the spelling in Playboy, Lena is the Swedish spelling of the name.) Lena Soderberg (ne Sjööblom) was last reported living in her native Sweden, happily married with three kids and a job with the state liquor monopoly. In 1988, she was interviewed by some Swedish computer related publication, and she was pleasantly amused by what had happened to her picture. That was the first she knew of the use of that picture in the computer business.

for more information please visit http://www.cs.cmu.edu/~chuck/lennapg/

Sixth Sense : A Nice Fluid Interfaces Project

April 3rd, 2009 by Ruwan

Today I came across a nice project: Sixth Sense, by MIT Media Lab. More than anything I would love to buy that tiny projector!!!! Wonder how much it cost. The project web site[1] says,

‘SixthSense’ is a wearable gestural interface that augments the physical world around us with digital information and lets us use natural hand gestures to interact with that information. By using a camera and a tiny projector mounted in a pendant like wearable device, ‘SixthSense’ sees what you see and visually augments any surfaces or objects we are interacting with. It projects information onto surfaces, walls, and physical objects around us, and lets us interact with the projected information through natural hand gestures, arm movements, or our interaction with the object itself. ‘SixthSense’ attempts to free information from its confines by seamlessly integrating it with reality, and thus making the entire world your computer.

References
[1] http://fluid.media.mit.edu/projects.php?action=details&id=68

Computer Vision to determine the shape of your unclad body ;-)

November 3rd, 2008 by Ruwan

Extracted from [1],

The newest computer vision technology can’t literally see through your sweater and slacks, but it can determine the shape of your unclad body.

Brown University computer scientists have developed software that takes ordinary images of people dressed in street clothes and digitally peels away the layers to determine their 3-D body shape.

In a partnership with Rhode Island State Police, Brown computer scientist Michael Black developed tools to figure out a person’s basic physical attributes from a grainy surveillance video.

[1] Boston News, Science Article.

Robotics Software

November 3rd, 2008 by Ruwan

robotics.youngster.com has compiled a nice list of Robotics related software. Have a look at here

http://robotics.youngester.com/2008/11/robotics-software.html

Treat your keys like you treat your credit card and “keep it in your pocket unless you need to use it.”

October 31st, 2008 by Ruwan

University of California, San Diego computer scientists have built a software program that can perform key duplication without having the key. Instead, the computer scientists only need a photograph of the key.

In this “Sneakey” Computer Vision project, features of the key is extracted from the photograph and accordingly a duplicate of the key is produced. Most importantly, photos can be taken even 200 feet away from keys without the owners knowledge.

So it is time to blur out the your keys in the photograph, like you did for number plates, credit card numbers before publishing to facebook, flickr etc. :) )

For more information have a look at here

Learning OpenCV from Gary Bradski & Adrian Kaehler

October 30th, 2008 by Ruwan

If you are new to OpenCV or If you want to expand your knowledge in OpenCV you would find following book is useful. I’ve been using OpenCV for almost 6 years up to now. It is “the” Open Source Computer Vision Library out there.

Learning OpenCV

The book includes:

  • A thorough introduction to OpenCV
  • Getting input from cameras
  • Transforming images
  • Shape matching
  • Pattern recognition, including face detection
  • Segmenting images
  • Tracking and motion in 2 and 3 dimensions
  • Machine learning algorithms

[1] Learning OpenCV Book at Safari
[2] OpenCV Library

Artificial eyeball does away with distorted images

October 30th, 2008 by Ruwan

I found this interesting article [1] at NewScientistTech written by Kurt Kleiner. They have a nice approach to create a curved digital sensor (spherical) mostly using conventional photolithography. There can be endless applications since this will help to get wide-angle but less distorted images from a small camera. Also the author suggests, these can be used in military surveillance as well as in medical applications. Read on for more information on how they created the sensor.

Artificial Eyeball

Artificial Eyeball

Extracted from the Article:
Mimicking the curves of a human retina has enabled a digital image sensor to take wide-angle pictures without distortion. This is possible thanks to an improved method of transferring silicon sensors onto a curved surface.

They built their hemispherical electronic eye by first using conventional photolithography to build silicon photodiodes 500 micrometers square and 1 micrometer thick. These were then wired into a flexible 16-by-16 array using chromium and gold.

Separately, they created a 1-cm-wide hemisphere out of a stretchy plastic, and stretched it into a flat surface. That stretched surface, or “drumhead”, was then pressed against the photodiode array.

The silicon squares stuck to the stretched plastic thanks to van der Waals forces, which was then allowed to spring back to its original hemispherical shape. As the array took its new form, the photodiodes packed together tightly and the connecting wires arced away from the surface, but the array was undamaged.

The reformed array was then glued to a curved glass surface, and a conventional lens attached. It now resembled a human eye in construction, with light entering the lens from the front, and passing to the curved “retina” containing the matrix of photodiodes behind.

[1] http://technology.newscientist.com/article/dn14477

Developing a WordPress theme from scratch!

October 29th, 2008 by Ruwan

It didn’t take too long for me to get rid of the previous “black” WordPress theme I’ve been using. But the most immediate reason was some encouragements given by few friends.

Okay, that is how the fun began! :) .

First, I wanted to use the layout I used back in 2004. Second, I wanted to make it a WordPress theme.

After extensive work with Photoshop, theme was okay to proceed to CSS design level. I found Guides and Slice Tools really useful in Photoshop. After playing with CSS a bit, the theme was ready to upload. There are few glitches here and there, but decided to deal with them later. The theme was tested in Firefox, Chrome and IE.

[1] and [2] tutorials made my life so easy. However, M$ Internet Exploder gave me enough trouble. Specially with the Sidebar. If I make a small change in a width of a DIV tag, the sidebar goes and sits right at the bottom of the screen.

[1] A CSS Layout with 2 columns
[2] So you want to create WordPress themes huh?

Pillow Talk: One more reason to “love” Computer Vision

October 19th, 2008 by Ruwan

How you can feel the love across thousands of miles?

Pillow Talk: A computer vision system enables couples to ‘touch’ each other while living far apart
More info found here