Linked Life Data

19216820

Source:http://linkedlifedata.com/resource/pubmed/id/19216820

Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
1
pubmed:dateCreated
2009-3-24
pubmed:abstractText
The human visual system is remarkably tolerant to degradation in image resolution: human performance in scene categorization remains high no matter whether low-resolution images or multimegapixel images are used. This observation raises the question of how many pixels are required to form a meaningful representation of an image and identify the objects it contains. In this article, we show that very small thumbnail images at the spatial resolution of 32 x 32 color pixels provide enough information to identify the semantic category of real-world scenes. Most strikingly, this low resolution permits observers to report, with 80% accuracy, four to five of the objects that the scene contains, despite the fact that some of these objects are unrecognizable in isolation. The robustness of the information available at very low resolution for describing semantic content of natural images could be an important asset to explain the speed and efficiently at which the human brain comprehends the gist of visual scenes.
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:status
MEDLINE
pubmed:issn
1469-8714
pubmed:author
pubmed:issnType
Electronic
pubmed:volume
26
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
123-31
pubmed:meshHeading
pubmed:articleTitle
How many pixels make an image?
pubmed:affiliation
Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA. torralba@csail.mit.edu
pubmed:publicationType
Journal Article, Research Support, U.S. Gov't, Non-P.H.S.