Scientists create system that ’simulates handwritten captchas’
October 16th, 2010 - 6:06 pm ICT by ANI
Washington, Oct 16 (ANI): Researchers at the Center for Unified Biometrics and Sensors are developing ways to simulate handwritten captchas.
University at Buffalo computer scientist Venu Govindaraju believes that this annoying 21st-century problem has a decidedly old-fashioned solution: handwriting.
“Our perspective is that humans are good at reading handwriting, machines are not. It comes naturally to humans. But computer scientists typically consider handwriting a hopeless case, until someone comes along and shows them that it isn’t,” Govindraju said.
“We developed an archive that can automatically generate as many different styles of handwriting as we want,” he added.
The research is based on pattern recognition, a subfield of machine learning in computer science that is concerned with developing systems based on detecting patterns in data.
The team is developing “smart rooms” - indoor environments equipped with sensitive, but unobtrusive devices, such as cameras and microphones that can identify and track the movements and gestures of inhabitants for a broad range of applications, from providing supplemental supervision in assisted living
facilities for the elderly or disabled, to monitoring office workplaces and retail establishments for security.
Eventually, the goal is to extend “smart room” features to larger arenas, such as shopping centers, airports and other transportation centers.
“This, too, is all pattern recognition,” Govindaraju said, “but instead of letters, here, we’re trying to standardize gestures. The idea is to control objects on a monitor without technology.” (ANI)
- A machine that can tell when you're lying - Mar 27, 2012
- Making 3-D face from 2D photo for security applications, forensics - Jan 20, 2011
- Machines can't recognise images like humans as yet - Sep 10, 2009
- Now, emergency detection systems for elderly people - Feb 05, 2011
- Machines still way behind humans in image recognition - Sep 10, 2009
- Soon, computers to understand how you feel! - Mar 05, 2011
- Now, a smartphone app that monitors what you are up to - Nov 27, 2010
- 'Touche' gives human touch to doorknobs, smartphones - May 06, 2012
- A bionic leg which responds to muscular signals - Apr 21, 2011
- Software to fight hacking technique bags award - Oct 31, 2010
- Human cues to improve computer's user-friendliness - Mar 06, 2011
- 'Gesture recognition,' robotic nurses to help surgeons of the future - Feb 04, 2011
- Soon, control TV with a simple wave of the hand - Dec 25, 2009
- New robotic hand types like its human counterpart - Mar 04, 2011
- IBM unveils computing chips that mimic human brain - Aug 18, 2011
Tags: assisted living facilities, biometrics, computer scientist, computer scientists, developing systems, different styles, gestures, handwriting, hopeless case, indoor environments, monitoring office, pattern recognition, retail establishments, room features, shopping centers, smart room, smart rooms, university at buffalo, venu govindaraju, workplaces