When is scene recognition just texture recognition?
Author(s) -
L L Walker,
Jitendra Malik
Publication year - 2010
Publication title -
journal of vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.126
H-Index - 113
ISSN - 1534-7362
DOI - 10.1167/2.7.255
Subject(s) - categorization , artificial intelligence , classifier (uml) , computer science , superordinate goals , pattern recognition (psychology) , grayscale , cognitive neuroscience of visual object recognition , computer vision , object (grammar) , image (mathematics) , psychology , social psychology
Subjects were asked to discriminate scenes after very brief exposures (37-69 ms). Their performance was always above chance and increased with exposure duration, confirming that subjects can get the gist of a scene with one fixation. We propose that a simple texture analysis of the image can provide a useful cue towards rapid scene identification. Our model learns texture features across scene categories and then uses this knowledge to categorize new scenes. The texture analysis leads to similar categorizations and confusions as subjects with limited processing time. We conclude that a simple texture discrimination model mostly explains early scene identification.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom