Learning about Canonical Views from Internet Image Collections

Although human object recognition is supposedly robust to viewpoint, much research on human perception indicates that there is a preferred or "canonical" view of objects. This phenomenon was discovered more than 30 years ago but the canonical view of only a small number of categories has been validated experimentally. Moreover, the explanation for why humans prefer the canonical view over other views remains elusive. In this paper we ask: Can we use Internet image collections to learn more about canonical views? We start by manually finding the most common view in the results returned by Internet search engines when queried with the objects used in psychophysical experiments. Our results clearly show that the most likely view in the search engine corresponds to the same view preferred by human subjects in experiments. We also present a simple method to find the most likely view in an image collection and apply it to hundreds of categories. Using the new data we have collected we present strong evidence against the two most prominent formal theories of canonical views and provide novel constraints for new theories.

[1]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[2]  Thomas Deselaers,et al.  Visual and semantic similarity in ImageNet , 2011, CVPR 2011.

[3]  M J Tarr,et al.  What Object Attributes Determine Canonical Views? , 1999, Perception.

[4]  Krista A. Ehinger,et al.  SUN database: Large-scale scene recognition from abbey to zoo , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Krista A. Ehinger,et al.  Canonical views of scenes depend on the shape of the space , 2011, CogSci.

[6]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[7]  Bastian Leibe,et al.  Discovering favorite views of popular places with iconoid shift , 2011, 2011 International Conference on Computer Vision.

[8]  Alexander C. Berg,et al.  Finding iconic images , 2009, 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[9]  Svetlana Lazebnik,et al.  Computing iconic summaries of general visual concepts , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[10]  Peter M. Hall,et al.  Simple Canonical Views , 2005, BMVC.

[11]  Cordelia Schmid,et al.  Evaluation of GIST descriptors for web-scale image search , 2009, CIVR '09.

[12]  Michael Werman,et al.  On View Likelihood and Stability , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Steven M. Seitz,et al.  Photo tourism: exploring photo collections in 3D , 2006, ACM Trans. Graph..

[14]  William T. Freeman,et al.  The generic viewpoint assumption in a framework for visual perception , 1994, Nature.

[15]  Steven M. Seitz,et al.  Scene Summarization for Online Image Collections , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[16]  H H Bülthoff,et al.  Psychophysical support for a two-dimensional view interpolation theory of object recognition. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[17]  Shumeet Baluja,et al.  Canonical image selection from the web , 2007, CIVR '07.

[18]  Wayne D. Gray,et al.  Basic objects in natural categories , 1976, Cognitive Psychology.

[19]  M. Fatih Demirci,et al.  Selecting canonical views for view-based 3-D object recognition , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[20]  Mohan M. Trivedi,et al.  Head Pose Estimation in Computer Vision: A Survey , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  S. Palmer.  Vision Science : Photons to Phenomenology , 1999 .