When is scene recognition just texture recognition

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.

[1]  P. O. Bishop,et al.  Spatial vision. , 1971, Annual review of psychology.

[2]  J. Beck.  Similarity grouping and peripheral discriminability under uncertainty. , 1972, The American journal of psychology.

[3]  I. Biederman.  Perceiving Real-World Scenes , 1972, Science.

[4]  M. Potter.  Short-term conceptual memory for pictures. , 1976, Journal of experimental psychology. Human learning and memory.

[5]  A. Friedman.  Framing pictures: the role of knowledge in automatized encoding and memory for gist. , 1979, Journal of experimental psychology. General.

[6]  B. Julesz.  Textons, the elements of texture perception, and their interactions , 1981, Nature.

[7]  BELA JULESZ,et al.  Rapid discrimination of visual patterns , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  G. Loftus,et al.  Differential Acquisition Rates for Different Types of Information from Pictures , 1983, The Quarterly journal of experimental psychology. A, Human experimental psychology.

[9]  E. Adelson,et al.  Early vision and texture perception , 1988, Nature.

[10]  P Perona,et al.  Preattentive texture discrimination with early vision mechanisms. , 1990, Journal of the Optical Society of America. A, Optics and image science.

[11]  J. Bergen,et al.  Texture segregation and orientation gradient , 1991, Vision Research.

[12]  Jitendra Malik,et al.  A Computational Framework for Determining Stereo Correspondence from a Set of Linear Spatial Filters , 1991, ECCV.

[13]  Denis Fize,et al.  Speed of processing in the human visual system , 1996, Nature.

[14]  Jitendra Malik,et al.  Textons, contours and regions: cue integration in image segmentation , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[15]  A. Oliva,et al.  Diagnostic Colors Mediate Scene Recognition , 2000, Cognitive Psychology.

[16]  Jitendra Malik,et al.  Contour and Texture Analysis for Image Segmentation , 2001, International Journal of Computer Vision.

[17]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[18]  D. Sagi,et al.  Gabor filters as texture discriminator , 1989, Biological Cybernetics.

[19]  B. Julesz,et al.  Texton gradients: The texton theory revisited , 2004, Biological Cybernetics.

[20]  R. Rosenfeld.  Nature , 2009, Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery.