Posts tagged eye tracking
Articles and news from the latest research reports.
Facial Recognition is More Accurate in Photos Showing Whole Person
Subtle body cues allow people to identify others with surprising accuracy when faces are difficult to differentiate. This skill may help researchers improve person-recognition software and expand their understanding of how humans recognize each other.
A study published in Psychological Science by researchers at The University of Texas at Dallas demonstrates that humans rely on non-facial cues, such as body shape and build, to identify people in challenging viewing conditions, such as poor lighting.
“Psychologists and computer scientists have concentrated almost exclusively on the role of the face in person recognition,” explains lead researcher Allyson Rice. “Our results show that the body can also provide important and sometimes sufficient identity information for person recognition.”
During several experiments, researchers asked college-age participants to look at images of two people side-by-side and identify whether the images showed the same person. Some pairs looked similar despite showing different people, while other image pairs showed the same person with a different appearance. The researchers used computer face recognition systems to find pairs of pictures in which facial characteristics were difficult to use for identity.
Overall, participants accurately discerned whether the images showed the same person when they were provided complete images that showed both the face and body. Participants were just as accurate in identifying people in the image pairs when the faces were blocked out and only the bodies were shown. But, similarly to the computer-based face recognition system, participants had trouble identifying images of the subjects’ faces without their bodies.
Image: Above are pairs of photographs that face-recognition software failed to identify correctly. The top two photos are of the same person, while the bottom two photos are of different people
When asked, participants thought they were using primarily facial features to identify the subjects. To unravel the paradox, the researchers used eye-tracking equipment to determine where participants were actually looking. They found participants spent more time looking at the body whenever the face did not provide enough information to identify the subjects.
“People’s recognition strategies were inaccessible to their conscious awareness,” Rice said. “This provides a cautionary tale in ascribing credibility to people’s subjective reports of how they came to an identity decision.”
Dr. Alice O’Toole, Aage and Margareta Møller Professor in the School of Behavioral and Brain Sciences, has worked on facial recognition for over 15 years and supervised the project.
“Given the widespread use of face recognition systems in security settings, it is important for these systems to make use of all potentially helpful information,” O’Toole said. “Our work shows that the body can be surprisingly useful for identification, especially when the face fails to provide the necessary identity information.”
(Source: utdallas.edu)
Brain and eye combined monitoring breakthrough could lead to fewer road accidents
Latest advances in capturing data on brain activity and eye movement are being combined to open up a host of ‘mindreading’ possibilities for the future. These include the potential development of a system that can detect when drivers are in danger of falling asleep at the wheel.
The research has been undertaken at the University of Leicester with funding from the Engineering and Physical Sciences Research Council (EPSRC), and in collaboration with the University of Buenos Aires in Argentina.
The breakthrough involves bringing two recent developments in the world of technology together: high-speed eye tracking that records eye movements in unprecedented detail using cutting-edge infra-red cameras*; and high-density electroencephalograph** (EEG) technology that measures electrical brain activity with millisecond precision through electrodes placed on the scalp.
The research has overcome previous technological challenges which made it difficult to monitor eye movement and brain activity simultaneously. The team has done this by developing novel signal processing techniques.
This could be the first step towards a system that combines brain and eye monitoring to automatically alert drivers who are showing signs of drowsiness. The system would be built into the vehicle and connected unobtrusively to the driver, with the EEG looking out for brain signals that only occur in the early stages of sleepiness. The eye tracker would reinforce this by looking for erratic gaze patterns symptomatic of someone starting to feel drowsy and different from those characteristic of someone driving who is constantly looking out for hazards. Fatigue has been estimated to account for around 20 per cent of traffic accidents on the UK’s motorways.***
The breakthrough achieved by the University of Leicester could also ultimately be built on to deliver many other everyday applications in the years ahead. For example:
- Computer games of the future could dispense with the need for the player to physically interact with any type of console, mouse or other hand-operated system. Instead, eye movement and brain activity data would be collected and processed to indicate what action the player wants to take. By distinguishing the tiny differences in various types of brain activity, the EEG would identify the precise action the player desires (e.g. run, jump or throw), while the eye movement data would show exactly where on the screen the player was looking when they had this thought. This information could be combined to enable the correct action to occur. An unobtrusive headset would be all that would be required to capture the necessary data.
- People who have no arm functionality could move their wheelchairs simply through their eye movements. These movements could be tracked and the corresponding brain activity analysed to identify when these indicate a desire to move in a certain direction. This would then automatically activate a steering and propulsion mechanism that would drive the wheelchair to that place.
- The breakthrough could also provide the basis for improved tests to diagnose dyslexia and other reading disorders. Current tests revolve around a rapid succession of single words flashed onto a computer screen, with the resulting brain activity monitored by EEG. The new technique could enable the person being tested to move their eyes and read longer passages of text in a natural way, making the tests much more realistic and revealing.
- With the basic concept now demonstrated successfully, the team aim to continue their work and eventually develop software that, in real time, automatically monitors both eye movement and brain activity.
- Dr Matias Ison, who has led the research, says: “Historically, eye-tracking and EEG have evolved as independent fields. We have managed to overcome the challenges that were standing in the way of integrating these technologies. This is already leading to a much better understanding of how the brain responds when the eyes are moving. Monitoring the alertness of drivers is just one of many potential applications for this work. Building on the foundation provided by our EPSRC-funded project, we hope to see the first of these starting to become feasible within the next three to five years.”
(Source: epsrc.ac.uk)
Neuro-magic: Magician uses magic tricks to study the brain’s powers of perception and memory
A magician is using his knowledge of magic theory and practice to investigate the brain’s powers of observation.
Hugo Caffaratti, engineer and semi-professional magician from Barcelona, Spain, has embarked on a PhD with the University of Leicester’s Centre for Systems Neuroscience.
Hugo has 12 years of experience working with magic – specialising in card tricks – and is a member of the Spanish Society of Illusionism (SEI-ACAI).
The engineer also has a longstanding interest in neuroscience and bioengineering, having taken a Master’s degree in Biomedical Engineering at University of Barcelona.
He hopes to combine his two interests in his PhD thesis project, which covers a new field of Cognitive Neuroscience: Neuro-Magic.
As part of his work, he will investigate how our brains perceive what actually happens before our eyes – and how our attention can be drawn away from important details.
He also plans to study “forced choice” - a tool often used by magicians where we are fooled into thinking we have made a free choice.
Among other experiments, Hugo will ask participants to watch videos of card trick performances, while sitting in front of an eye-tracker device.
This will allow him to monitor where our attention is focused during illusions – and how our brain can be deceived when our eyes miss the whole picture.
Hugo said: “I have always been interested in the study of the brain. It is amazing to be involved in the process of combining the disciplines of neuroscience and magic.
“I am really interested in the fields of decision making and forced-choice. It is incredible that many times a day we make a decision and feel free. We do not realise that we have been forced to make that decision.
“I am constructing an experiment to study what happens when we make forced decisions – to try and find the reasons for it. I am thinking about which kinds of tricks I know could be useful to give more insights about brain function.”
He will work under the tutelage of Professor Rodrigo Quian Quiroga, director of the Centre for Systems Neuroscience.
Professor Quian Quiroga’s recent work on memory formation was the topic of his recent book “Borges and memory” (MIT Press) and was also featured on the front page of the international science publication Scientific American.
Professor Rodrigo Quian Quiroga said: “I am very interested in connections between science and the arts. Last year, for example, we organized an art and science exhibition as a result of a 1-year rotation in my lab of visual artist Mariano Molina. Hugo’s PhD will look at decision-making and attention – and although he is doing his first steps in neuroscience, I think he already has a lot of expertise in this area based on his training as a magician.
“Magic theory has thousands of years of experience. Magicians have been answering similar questions that we have in the lab, and they have an intuitive knowledge of how the mind works. Hugo will likely bring a fresh new view on how to address questions we deal with in neuroscience.”
Hugo is also keen to carry on with his work in magic while studying for his PhD, and is hoping to perform in bars in Leicester while staying here.
He has also applied for membership with The Magic Circle – a prestigious magic society of London. He will have to sit exams to prove his magical mettle in order to join the exclusive club.
Seeing the world through the eyes of an Orangutan
Dr Neil Mennie, from The University of Nottingham Malaysia Campus (UNMC), has received funding from Ministry of Science and Technology and Innovation, Malaysia (MOSTI) to study the eye movements of Tsunami — a seven year old orangutan at The National Zoo of Malaysia (Zoo Negara). Not only will Dr Mennie’s research address vital questions about the visual cognition of humans and apes in natural tasks, it will also provide valuable enrichment for the juvenile captive-born orangutan.
Dr Mennie said: “Orangutans are particularly interesting because to survive in the treetops they must be very spatially aware of their surroundings. I hope to investigate their ability to search for food and to compare their progress with humans in 3D search and foraging tasks.
Dr Mennie, who is from the Cognitive and Sensory Systems Research Group in the School of Psychology at UNMC, is interested in how humans and apes use their brains to learn and make predictions about our surroundings. With the help of Tsunami’s keeper, Mohd Sharullizam Ramli, and the special eye tracking equipment that is worn over her head and shoulders, Dr Mennie has spent the last year recording Tsunami’s eye and body movements during the performance of complex actions such as locomotion, foraging for food and manipulation of small objects.
The eyes may be windows into the soul, but following their movement also could allow doctors to make quick, accurate diagnoses for disorders like autism, schizophrenia, or attention deficit hyperactivity disorder, various research projects suggest.
Eye tracking, which records where subjects focus when watching visual displays, could diagnose brain disorders more accurately than subjective questionnaires or medical examinations do, researchers say. Exams are expensive and time-consuming, and subjective tests have been known to wrongly identify healthy people or misdiagnose disorders.
To make sense of all that people see, the brain filters huge amounts of visual information, fills in gaps and focuses on certain objects. That complex task uses many mental circuits, so differences in what people choose to look at ― differences so subtle that only a computer can spot them ― could provide unprecedented insight into common neurological problems.