Featured Research

from universities, journals, and other organizations

Computer vision research: Do you see what I see?

Date:
December 22, 2011
Source:
DOE/Los Alamos National Laboratory
Summary:
A question confronting neuroscientists and computer vision researchers alike is how objects can be identified by simply "looking" at an image. But teaching a computer to "know" what it's looking at is far harder. Scientists have now modeled human brain structure to develop better programming approaches for computer object identification.

An essential question confronting neuroscientists and computer vision researchers alike is how objects can be identified by simply "looking" at an image. Introspectively, we know that the human brain solves this problem very well. We only have to look at something to know what it is.

But teaching a computer to "know" what it's looking at is far harder. In research published this fall in the Public Library of Science (PLoS) Computational Biology journal, a team from Los Alamos National Laboratory, Chatham University, and Emory University first measured human performance on a visual task ‑ identifying a certain kind of shape when an image is flashed in front of a viewer for a very short amount of time (20-200 milliseconds). Human performance gets worse, as expected, when the image is shown for shorter time periods. Also as expected, humans do worse when the shapes are more complicated.

But could a computer be taught to recognize shapes as well, and then do it faster than humans? The team tried developing a computer model based on human neural structure and function, to do what we do, and possibly do it better.

Their paper, "Model Cortical Association Fields Account for the Time Course and Dependence on Target Complexity of Human Contour Perception," describes how, after measuring human performance, they created a computer model to also attempt to pick out the shapes.

"This model is biologically inspired and relies on leveraging lateral connections between neurons in the same layer of a model of the human visual system," said Vadas Gintautas of Chatham University in Pittsburgh and formerly a researcher at Los Alamos.

Neuroscientists have characterized neurons in the primate visual cortex that appear to underlie object recognition, noted senior author Garrett Kenyon of Los Alamos. "These neurons, located in the inferotemporal cortex, can be strongly activated when particular objects are visible, regardless of how far away the objects are or how the objects are posed, a phenomenon referred to as viewpoint invariance."

The brain has an uncanny ability to detect and identify certain things, even if they're barely visible. Now the challenge is to get computers to do the same thing. And programming the computer to process the information laterally, like the brain does, might be a step in the right direction.

How inferotemporal neurons acquire their viewpoint invariant properties is unknown, but many neuroscientists point to the hierarchical organization of the human visual cortex as likely being an essential aspect.

"Lateral connections have been generally overlooked in similar models designed to solve similar tasks. We demonstrated that our model qualitatively reproduces human performance on the same task, both in terms of time and difficulty. Although this is certainly no guarantee that the human visual system is using lateral interactions in the same way to solve this task, it does open up a new way to approach object detection problems," Gintautas said.

Simple features, such as particular edges of the image in a specific orientation, are extracted at the first cortical processing stage, called the primary visual cortex, or V1. Then subsequent cortical processing stages, V2, V4, etc., extract progressively more complex features, culminating in the inferotemporal cortex where that essential "viewpoint invariant object identification" is thought to occur. But, most of the connections in the human brain do not project up the cortical hierarchy, as might be expected from gross neuroanatomy, but rather connect neurons located at the same hierarchical level, called lateral connections, and also project down the cortical hierarchy to lower processing levels.

In the recently published work, the team modeled lateral interactions between cortical edge detectors to determine if such connections could explain the difficulty and time course of human contour perception. This research thus combined high-performance computer simulations of cortical circuits, using a National Science Foundation funded neural simulation toolbox, called PetaVision, developed by LANL researchers, along with "speed-of-sight" psychophysical measurements of human contour perception. The psychophysical measurements refer to an experimental technique that neuroscientists use to study mechanisms of cortical processing, using the open-source Psychtoolbox software as an advanced starting point.

"Our research represented the first example of a large-scale cortical model being used to account for both the overall accuracy, as well as the processing time, of human subjects performing a challenging visual-perception task," said Kenyon.


Story Source:

The above story is based on materials provided by DOE/Los Alamos National Laboratory. Note: Materials may be edited for content and length.


Journal Reference:

  1. Vadas Gintautas, Michael I. Ham, Benjamin Kunsberg, Shawn Barr, Steven P. Brumby, Craig Rasmussen, John S. George, Ilya Nemenman, Luís M. A. Bettencourt, Garret T. Kenyon. Model Cortical Association Fields Account for the Time Course and Dependence on Target Complexity of Human Contour Perception. PLoS Computational Biology, 2011; 7 (10): e1002162 DOI: 10.1371/journal.pcbi.1002162

Cite This Page:

DOE/Los Alamos National Laboratory. "Computer vision research: Do you see what I see?." ScienceDaily. ScienceDaily, 22 December 2011. <www.sciencedaily.com/releases/2011/12/111221091922.htm>.
DOE/Los Alamos National Laboratory. (2011, December 22). Computer vision research: Do you see what I see?. ScienceDaily. Retrieved August 29, 2014 from www.sciencedaily.com/releases/2011/12/111221091922.htm
DOE/Los Alamos National Laboratory. "Computer vision research: Do you see what I see?." ScienceDaily. www.sciencedaily.com/releases/2011/12/111221091922.htm (accessed August 29, 2014).

Share This




More Computers & Math News

Friday, August 29, 2014

Featured Research

from universities, journals, and other organizations


Featured Videos

from AP, Reuters, AFP, and other news services

JPMorgan Chase Confirms Possible Cyber Attack

JPMorgan Chase Confirms Possible Cyber Attack

Reuters - US Online Video (Aug. 28, 2014) — Attackers stole checking and savings account information and lots of other data from JPMorgan Chase, according to the New York Times. Other banks are believed to be victims as well. Fred Katayama reports. Video provided by Reuters
Powered by NewsLook.com
Spend 2 Minutes Watching This Smartwatch Roundup

Spend 2 Minutes Watching This Smartwatch Roundup

Newsy (Aug. 28, 2014) — LG announces a round-faced smartwatch, Samsung adds 3G connectivity to its latest wearable, and Apple will reportedly announce the iWatch on Sept. 9. Video provided by Newsy
Powered by NewsLook.com
Google Reveals Drone Delivery Program, 'Project Wing'

Google Reveals Drone Delivery Program, 'Project Wing'

Newsy (Aug. 28, 2014) — Google has been developing a drone delivery system of its own, and it hopes to revolutionize how people view possessions with it. Video provided by Newsy
Powered by NewsLook.com
Why Apple Might Add Mobile Payment Options To iPhone 6

Why Apple Might Add Mobile Payment Options To iPhone 6

Newsy (Aug. 28, 2014) — A report by Wired suggests Apple's next iPhone will feature a mobile payment system and near-field communication. Video provided by Newsy
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