Tuesday, August 25, 2009

Real-life relationships with Xbox

Lionhead Studios' Peter Molyneux has shown off a game character that recognises and responds to a player's mood.

The human interaction system is possible with Natal, a system being developed for the Xbox 360.

It monitors and reacts precisely to the player's movements and the way they talk.

Microsoft demonstrated Natal at the start of the E3 gaming conference in Los Angeles.


Tuesday, May 26, 2009

Real-time object recognition on a Windows Mobile

iVisit, a company who makes video conferencing software, has, with the help of a NIH grant, turned its talents to helping the blind be even more independent.

They have developed two products which in the demo below appear pretty amazing.

The first, clearly an outgrowth of their video conferencing business, is called SeeStar, and would allow a blind person to transmit video to a sighted partner, who would then be able to describe the scene to the partner. The application integrate with Google maps using GPS, providing even more information to the sighted partner. The software does not just depend on the sighted partner however, with it being able to independently recognize land marks in the video stream.

Progressing from there is SeeScan, which takes that talent to a different level, being able to recognize and read out the names of common objects, even when they are partly obfuscated. The database can also be trained and extended, meaning the software should be useful in many situations beyond shopping for example.

The software package is still under development and has not yet been released to the public.

See the video below for the app in action.


Friday, December 5, 2008


What is Leonar3Do?

"Anyone wishing to create anything in three-dimensions must be able to see, think and plan in 3D. But our most important and most widely used tools for this purpose are two-dimensional: a paper and pencil. Leonar3Do, is capable of transforming an ordinary PC into a 3D system that is easily accessible to a mass user base."

Home page:

Thursday, December 4, 2008

Tuesday, September 30, 2008

Neural Network for Recognition of Handwritten Digits

The next article is about an artificial neural network designed to recognize handwritten digits:

The source code is written in VC++ 6.0. It's a very professional work.

Wednesday, January 30, 2008

Professor Kevin Warwick

Kevin Warwick is Professor of Cybernetics at the University of Reading, England, where he carries out research in artificial intelligence, control, robotics and biomedical engineering.
He has very interesting projects like Cyborg 2.0

On the 14th of March 2002 a one hundred electrode array was surgically implanted into the median nerve fibres of the left arm of Professor Kevin Warwick. The operation was carried out at Radcliffe Infirmary, Oxford, by a medical team headed by the neurosurgeons Amjad Shad and Peter teddy. The procedure, which took a little over two hours, involved inserting a guiding tube into a two inch incision made above the wrist, inserting the microelectrode array into this tube and firing it into the median nerve fibres below the elbow joint.

A number of experiments have been carried out using the signals detected by the array, most notably Professor Warwick was able to control an electric wheelchair and an intelligent artificial hand, developed by Dr Peter Kyberd, using this neural interface. In addition to being able to measure the nerve signals transmitted down Professor Wariwck’s left arm, the implant was also able to create artificial sensation by stimluating individual electrodes within the array. This was demonstrated with the aid of Kevin’s wife Irena and a second, less complex implantconnecting to her nervous system.

More information on his web page: here

Wednesday, December 26, 2007

Download BETA v1.0.0

When I have some spare time, I develop the new version of my Neocognitron simulator.
If you have any sugestions to the new version, please write a post to the forum: here.
The latest BETA version is availabel to download from my home page (Main page): here.