Featured Research

from universities, journals, and other organizations

Computer Vision May Not Be As Good As Thought

Date:
January 31, 2008
Source:
Massachusetts Institute of Technology
Summary:
For years, scientists have been trying to teach computers how to see like humans, and recent research has seemed to show computers making progress in recognizing visual objects. A new study, however, cautions that this apparent success may be misleading because the tests being used are inadvertently stacked in favor of computers.

The human brain easily recognizes that these cars are all the same object, but the variations in the car's size, orientation and position are a challenge for computer-vision algorithms.
Credit: Nicolas Pinto

For years, scientists have been trying to teach computers how to see like humans, and recent research has seemed to show computers making progress in recognizing visual objects. A new MIT study, however, cautions that this apparent success may be misleading because the tests being used are inadvertently stacked in favor of computers.

Computer vision is important for applications ranging from "intelligent" cars to visual prosthetics for the blind. Recent computational models show apparently impressive progress, boasting 60-percent success rates in classifying natural photographic image sets. These include the widely used Caltech101 database, intended to test computer vision algorithms against the variety of images seen in the real world.

However, James DiCarlo, a neuroscientist in the McGovern Institute for Brain Research at MIT, graduate student Nicolas Pinto and David Cox of the Rowland Harvard Institute argue that these image sets have design flaws that enable computers to succeed where they would fail with more authentically varied images. For example, photographers tend to center objects in a frame and to prefer certain views and contexts. The visual system, by contrast, encounters objects in a much broader range of conditions.

"The ease with which we recognize visual objects belies the computational difficulty of this feat," explains DiCarlo, senior author of the study in the online Jan. 25 PLoS Computational Biology. "The core challenge is image variation. Any given object can cast innumerable images onto the retina depending on its position, distance, orientation, lighting and background."

The team exposed the flaws in current tests of computer object recognition by using a simple "toy" computer model inspired by the earliest steps in the brain's visual pathway. Artificial neurons with properties resembling those in the brain's primary visual cortex analyze each point in the image and capture low-level information about the position and orientation of line boundaries. The model lacks the more sophisticated analysis that happens in later stages of visual processing to extract information about higher-level features of the visual scene such as shapes, surfaces or spaces between objects.

The researchers intended this model as a straw man, expecting it to fail as a way to establish a baseline. When they tested it on the Caltech101 images, however, the model did surprisingly well, with performance similar or better than five state-of-the-art object-recognition systems.

How could that be" "We suspected that the supposedly natural images in current computer vision tests do not really engage the central problem of variability, and that our intuitions about what makes objects hard or easy to recognize are incorrect," Pinto explains.

To test this idea, the authors designed a more carefully controlled test. Using just two categories-planes and cars-they introduced variations in position, size and orientation that better reflect the range of variation in the real world.

"With only two types of objects to distinguish, this test should have been easier for the 'toy' computer model, but it proved harder," Cox says. The team's conclusion: "Our model did well on the Caltech101 image set not because it is a good model but because the 'natural' images fail to adequately capture real-world variability."

As a result, the researchers argue for revamping the current standards and images used by the computer-vision community to compare models and measure progress. Before computers can approach the performance of the human brain, they say, scientists must better understand why the task of object recognition is so difficult and the brain's abilities are so impressive.

This study was supported by the National Eye Institute, The Pew Charitable Trust and The McKnight Foundation.


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. "Computer Vision May Not Be As Good As Thought." ScienceDaily. ScienceDaily, 31 January 2008. <www.sciencedaily.com/releases/2008/01/080124233657.htm>.
Massachusetts Institute of Technology. (2008, January 31). Computer Vision May Not Be As Good As Thought. ScienceDaily. Retrieved July 22, 2014 from www.sciencedaily.com/releases/2008/01/080124233657.htm
Massachusetts Institute of Technology. "Computer Vision May Not Be As Good As Thought." ScienceDaily. www.sciencedaily.com/releases/2008/01/080124233657.htm (accessed July 22, 2014).

Share This




More Computers & Math News

Tuesday, July 22, 2014

Featured Research

from universities, journals, and other organizations


Featured Videos

from AP, Reuters, AFP, and other news services

Uruguayan Creates Chess Game for Multiple Opponents

Uruguayan Creates Chess Game for Multiple Opponents

AFP (July 19, 2014) It no longer takes two to play chess – or at least according to a new version of the game invented by Uruguayan Gabriel Baldi, where up to four opponents can play. Duration: 00:31 Video provided by AFP
Powered by NewsLook.com
Clock Ticks Down on Internet Speed Debate

Clock Ticks Down on Internet Speed Debate

Reuters - US Online Video (July 18, 2014) The FCC received more than 800,000 comments on whether and how internet speeds should be regulated, even crashing its system. Lily Jamali reports. Video provided by Reuters
Powered by NewsLook.com
Google Won't Call Games With In-App Add-Ons Free, Apple Will

Google Won't Call Games With In-App Add-Ons Free, Apple Will

Newsy (July 18, 2014) The European Commission asked Google and Apple not to label apps "free" if they include in-app purchases. Google has complied; Apple has resisted. Video provided by Newsy
Powered by NewsLook.com
Will 'Kindle Unlimited' Get Amazon In More Legal Trouble?

Will 'Kindle Unlimited' Get Amazon In More Legal Trouble?

Newsy (July 18, 2014) Amazon launched "Kindle Unlimited," and for $9.99/month, subscribers can read and listen to books. However, will this cause any legal issues? 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