Featured Research

from universities, journals, and other organizations

MIT Reports New Insights In Visual Recognition; Work Could Lead To Improved Machine Vision Systems

Date:
April 2, 2004
Source:
Massachusetts Institute Of Technology
Summary:
MIT scientists are reporting new insights into how the human brain recognizes objects, especially faces, in work that could lead to improved machine vision systems, diagnostics for certain neurological conditions and more.

Objects can be defined both by intrinsic and contextual cues. In image A, some of the runner's faces have enough intrinsic information to permit their classification as faces based on local image structure (image B), while others almost entirely lack such intrinsic cues (image C) and rely on contextual information. Many real-world viewing situations (such as observing objects at a distance, through haze or with refractive errors in the eyes) necessitate such contextual cuing of objects. Now MIT scientists report direct experimental evidence that such contextual cues can elicit object-specific neural responses in the brain. (PHOTO / KEENE STATE COLLEGE)

CAMBRIDGE, Mass. -- MIT scientists are reporting new insights into how the human brain recognizes objects, especially faces, in work that could lead to improved machine vision systems, diagnostics for certain neurological conditions and more.

Look at a photo of people running a marathon. The lead runners' faces are quite distinct, but we can also make out the faces of those farther in the distance. Zoom in on that distant runner, however, "and you'll see that there's very little intrinsic face-related information, such as eyes and a nose. It's just a diffuse blob. Yet somehow we can classify that blob as a face," said Pawan Sinha, an assistant professor in the Department of Brain and Cognitive Sciences (BCS). In contrast, performing this task reliably is beyond even the most advanced computer-recognition systems.

In the April 2 issue of Science, Sinha and colleagues show that a specific brain region known to be activated by clear images of faces is also strongly activated by very blurred images, just so long as surrounding contextual cues (such as a body) are present. "In other words, the neural circuitry in the human brain can use context to compensate for extreme levels of image degradations," Sinha said.

Past studies of human behavior and the work of many artists have suggested that context plays a role in recognition. "What is novel about this work is that it provides direct evidence of contextual cues eliciting object-specific neural responses in the brain," Sinha said.

The team used functional magnetic resonance imaging to map neuronal responses of the brain's fusiform face area (FFA) to a variety of images. These included clear faces, blurred faces attached to bodies, blurred faces alone, bodies alone, and a blurred face placed in the wrong context (below the torso, for example).

Only the clear faces and blurred faces with proper contextual cues elicited strong FFA responses. "These data support the idea that facial representations underlying FFA activity are based not only on intrinsic facial cues, but rather incorporate contextual information as well," wrote BCS graduate student David Cox, BCS technical assistant Ethan Meyers, and Sinha.

"One of the reasons that reports of such contextual influences on object-specific neural responses have been lacking in the literature so far is that researchers have tended to 'simplify' images by presenting objects in isolation. Using such images precludes consideration of contextual influences," Cox said. The findings not only add to scientists' understanding of the brain and vision, but also "open up some very interesting issues from the perspective of developmental neuroscience," Sinha said. For example, how does the brain acquire the ability to use contextual cues? Are we born with this ability, or is it learned over time? Sinha is exploring these questions through Project Prakash, a scientific and humanitarian effort to look at how individuals who are born blind but later gain some vision perceive objects and faces. (See MIT Tech Talk, Aug. 25, 2003.)

Potential applications

Computer recognition systems work reasonably well when images are clear, but they break down catastrophically when images are degraded. "A human's ability is so far beyond what the computer can do," Meyers emphasized. "The new work could aid the development of better systems by changing our concept of the kind of image information useful for determining what an object is."

There could also be clinical applications. For example, said Sinha, "contextually evoked neural activity, or the lack of it, could potentially be used as an early diagnostic marker for specific neurological conditions like autism, which are believed to be correlated with impairments in information integration. We hope to address such questions as part of the Brain Development and Disorders Project, a collaboration between MIT and Children's Hospital" in Boston.

###

This work was supported by the Athinoula A. Martinos Center for Biomedical Imaging, the National Center for Research Resources and the Mental Illness and Neuroscience Discovery (MIND) Institute, as well as the National Defense Science and Engineering Graduate Fellowship, the Alfred P. Sloan Foundation and the John Merck Scholars Award.


Story Source:

The above story is based on materials provided by Massachusetts Institute Of Technology. Note: Materials may be edited for content and length.


Cite This Page:

Massachusetts Institute Of Technology. "MIT Reports New Insights In Visual Recognition; Work Could Lead To Improved Machine Vision Systems." ScienceDaily. ScienceDaily, 2 April 2004. <www.sciencedaily.com/releases/2004/04/040402071910.htm>.
Massachusetts Institute Of Technology. (2004, April 2). MIT Reports New Insights In Visual Recognition; Work Could Lead To Improved Machine Vision Systems. ScienceDaily. Retrieved July 25, 2014 from www.sciencedaily.com/releases/2004/04/040402071910.htm
Massachusetts Institute Of Technology. "MIT Reports New Insights In Visual Recognition; Work Could Lead To Improved Machine Vision Systems." ScienceDaily. www.sciencedaily.com/releases/2004/04/040402071910.htm (accessed July 25, 2014).

Share This




More Computers & Math News

Friday, July 25, 2014

Featured Research

from universities, journals, and other organizations


Featured Videos

from AP, Reuters, AFP, and other news services

Bill Gates: Health, Agriculture Key to Africa's Development

Bill Gates: Health, Agriculture Key to Africa's Development

AFP (July 24, 2014) Health and agriculture development are key if African countries are to overcome poverty and grow, US software billionaire Bill Gates said Thursday, as he received an honourary degree in Ethiopia. Duration: 00:36 Video provided by AFP
Powered by NewsLook.com
Creative Makeovers for Ugly Cellphone Towers

Creative Makeovers for Ugly Cellphone Towers

AP (July 24, 2014) Mobile phone companies and communities across the country are going to new lengths to disguise those unsightly cellphone towers. From a church bell tower to a flagpole, even a pencil, some towers are trying to make a point. (July 24) Video provided by AP
Powered by NewsLook.com
Robot Parking Valet Creates Stress-Free Travel

Robot Parking Valet Creates Stress-Free Travel

AP (July 23, 2014) 'Ray' the robotic parking valet at Dusseldorf Airport in Germany lets travelers to avoid the hassle of finding a parking spot before heading to the check-in desk. (July 23) Video provided by AP
Powered by NewsLook.com
Facebook Earnings Put Smile on Investors Faces

Facebook Earnings Put Smile on Investors Faces

Reuters - Business Video Online (July 23, 2014) Facebook earnings beat forecasts- with revenue climbing 61 percent. Bobbi Rebell reports. Video provided by Reuters
Powered by NewsLook.com

Search ScienceDaily

Number of stories in archives: 140,361

Find with keyword(s):
Enter a keyword or phrase to search ScienceDaily for related topics and research stories.

Save/Print:
Share:

Breaking News:
from the past week

In Other News

... from NewsDaily.com

Science News

    Health News

      Environment News

        Technology News



          Save/Print:
          Share:

          Free Subscriptions


          Get the latest science news with ScienceDaily's free email newsletters, updated daily and weekly. Or view hourly updated newsfeeds in your RSS reader:

          Get Social & Mobile


          Keep up to date with the latest news from ScienceDaily via social networks and mobile apps:

          Have Feedback?


          Tell us what you think of ScienceDaily -- we welcome both positive and negative comments. Have any problems using the site? Questions?
          Mobile: iPhone Android Web
          Follow: Facebook Twitter Google+
          Subscribe: RSS Feeds Email Newsletters
          Latest Headlines Health & Medicine Mind & Brain Space & Time Matter & Energy Computers & Math Plants & Animals Earth & Climate Fossils & Ruins