Twenty Xerox scientists specialized in machine vision and image processing, joined colleagues from Google, Facebook, Microsoft Research, Amazon and some of the leading academic institutions in the world to share their research, in late June.
The purpose of this committee is to make computers behave increasingly like 'human beings', mimicking the way the brain sees and thinks.
The annual conference IEEE Computer Vision / Pattern Recognition, held between 23 and 28 June in Columbus, Ohio (USA), meets annually to leading scientists around the world to work on improving the artificial vision, discipline that allows computers to improve their performance, rise and sometimes even surpassing human capabilities.
"Xerox has extensive knowledge of business processes in many sectors and is a pioneer in teaching computers to extract image analysis and meaningful and actionable videos," said Raja Bala, Scientific Research Center that Xerox in Webster, NY York. "Although there has been significant progress in recent years, scientists still challenges that we have to solve."
Xerox Research presented at the conference this year include:
Detect if drivers use mobile devices when they are driving down the highway
Some state and federal government organizations prohibit cell phone use while driving to improve safety on the roads. Xerox scientists are working on a camera system for motorways employing pattern recognition technology and detects whether a driver is using a mobile phone.
Turn smartphones into personal assistants Driving
Webster researchers are also working on a project of artificial vision that mobile phones become assistants for driving. Using a detection technology facial features, the phone identify the direction of gaze of the driver and detect if distracted or is paying attention to the road.
Call to make images more attention
Xerox researchers in both Europe and Harvard University are studying what attracts the attention of people when they see a picture first. This may develop images that have the greatest effect to predict where people look when viewing a scene, a picture or a game.
Making sense of the information in computer vision: visual signatures
Pictures and video account for 90 percent of current Internet traffic. Therefore it is necessary to have a technology that can automatically analyze an image and create a unique visual signature that distinguishes it from others. The European Research Center Xerox (XRCE) has invented a patented front-line firms make these extremely compact and solid methodology, surpassing current methods of learning, to address the challenging problems of image classification that currently exist.
Designing "golden questions" in complex tasks crowdsourcing Crowdsourcing is commonly used as a forum for individuals found to label images. But it has its challenges when experts are needed for specific issues, as they rarely are available crowdsourcing platforms. To help unskilled annotators, the Xerox Research Centers in Europe and India have designed a system that can make an initial filter to propose a limited number of categories to choose from. The system automatically includes key questions to identify the experts that are selected are reliable and provide some quality work.
Press Release:
Xerox Scientists Share Innovations that Teach Computers to See, Think and Help Humans with their Work
Mobile technology that turns your smartphone into a driving coach and imaging technology that can detect texting drivers among innovations shown at international conference
NORWALK, Conn. —
Twenty leading computer vision and imaging scientists from Xerox (NYSE: XRX) will join their peers from Google, Facebook, Microsoft Research, Amazon and many of the world’s top academic institutions later this month to share their research on making computers more “human like,” mimicking how the brain sees and thinks.
Steadily closing the gap between reality and Hollywood depictions of artificial intelligence, the annual IEEE Computer Vision/Pattern Recognition Conference set for June 23-28 in Columbus, Ohio, draws top scientists worldwide working on ways to advance computer vision, a field that empowers machines to “see” and make sense of the world, augmenting and often exceeding human capabilities.
“Xerox has firsthand knowledge of business processes across many industries, and is a pioneer in teaching computers to extract meaningful and actionable analytics from images and video,” said Raja Bala, a Xerox principal scientist in Webster, N.Y. “Although there’s been significant progress in recent years, a number of scientific challenges remain to be resolved.”
Xerox research presented at this year’s conference includes:
Detecting cell phone use by highway drivers
Motivated by its impact on public safety and property, several state and federal government organizations prohibit cell phone use while driving. Xerox scientists are working on a camera system for highways that uses pattern recognition technology to detect if a driver is using a cell phone.
Turning smartphones into a personal driving coach
Researchers in Webster are also working on a computer vision project that would turn smartphones into driving assistants. Using facial feature detection technology the phone would estimate a driver’s gaze direction, and detect if a driver is distracted and not paying attention to the road.
Making images more eye catching
Researchers from both Xerox in Europe and at Harvard University are studying what attracts people’s attention first when they look at a picture. Understanding that eye-catching element enables visuals to be composed for greater effect and can predict where people will look when facing a scene, a photo or game.
Making sense of big data in computer vision – image signatures
Images and video make up 90 percent of today’s Internet traffic. To explore and use this massive amount of data requires technology that can automatically analyze an image and create a unique ‘visual signature’ that distinguishes it from other images. The Xerox Research Centre Europe (XRCE) has invented a patented state-of-the-artmethodology that creates such signatures in an extremely compact and robust fashion, beating current deep learning methods for such challenging image classification problems as recognizing the brand and model of a car.
Pigeon or dove? Designing ‘gold’ questions in complex crowdsourcing tasks
Crowdsourcing is frequently used as a forum to find individuals to label images but presents challenges when specific subject matter experts are required (such as ornithologists to identify species of birds), since such experts are rarely available on crowdsourcing platforms. To assist non-expert annotators, the Xerox research centers in Europe and India have designed a system that can do a first filter to propose a very limited number of categories to choose from. The system automatically includes ‘gold’ questions to identify untrustworthy annotators and ensure the quality of labeling.
Xerox’s leadership in computer vision
Xerox conducts computer vision research at its centers in New York and France. TheXerox Innovation Group also collaborates with the world’s top academic institutions including the University of Oxford, Harvard University, the French National Institute for Research in Computer Science (INRIA), the Massachusetts Institute of Technology, Carnegie Mellon, the University of Illinois at Urbana-Champaign, Penn State University, Notre Dame and University of Maryland.
About Xerox
Since the invention of Xerography more than 75 years ago, the people of Xerox have helped businesses simplify the way work gets done. Today, we are the global leader in business process and document management, helping organizations of any size be more efficient so they can focus on their real business. Headquartered in Norwalk, Conn., we have more than 140,000 Xerox employees and do business in more than 180 countries, providing business services, printing equipment and software for commercial and government organizations. Learn more atwww.xerox.com.
No comments:
Post a Comment