Per-patch Descriptor Selection Using Surface and Scene Properties

Local image descriptors are generally designed for describing all possible image patches. Such patches may be subject to complex variations in appearance due to incidental object, scene and recording conditions. Because of this, a single-best descriptor for accurate image representation under all conditions does not exist. Therefore, we propose to automatically select from a pool of descriptors the one that is best suitable based on object surface and scene properties. These properties are measured on the fly from a single image patch through a set of attributes. Attributes are input to a classifier which selects the best descriptor. Our experiments on a large dataset of colored object patches show that the proposed selection method outperforms the best single descriptor and a-priori combinations of the descriptor pool.

[1]  E. Adelson,et al.  Image statistics for surface reflectance perception. , 2008, Journal of the Optical Society of America. A, Optics, image science, and vision.

[2]  John Langford,et al.  Cost-sensitive learning by cost-proportionate example weighting , 2003, Third IEEE International Conference on Data Mining.

[3]  Matti Pietikäinen,et al.  Descriptor Learning Based on Fisher Separation Criterion for Texture Classification , 2010, ACCV.

[4]  Sebastian Nowozin,et al.  On feature combination for multiclass object classification , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[5]  Hongping Cai,et al.  Learning Linear Discriminant Projections for Dimensionality Reduction of Image Descriptors , 2011, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Todd E. Zickler,et al.  Blind Reflectometry , 2010, ECCV.

[7]  E. Adelson,et al.  Recognition of Surface Reflectance Properties from a Single Image under Unknown Real-World Illumination , 2001 .

[8]  Joost van de Weijer,et al.  Improving Color Constancy by Photometric Edge Weighting , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  E. Adelson,et al.  Image statistics and the perception of surface qualities , 2007, Nature.

[10]  François Fleuret,et al.  Tasting families of features for image classification , 2011, 2011 International Conference on Computer Vision.

[11]  Xiaofeng Ren,et al.  Toward Robust Material Recognition for Everyday Objects , 2011, BMVC.

[12]  Arnold W. M. Smeulders,et al.  The Amsterdam Library of Object Images , 2004, International Journal of Computer Vision.

[13]  Brian V. Funt,et al.  A data set for color research , 2002 .

[14]  GeversTheo,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010 .

[15]  Jan C. van Gemert,et al.  Exploiting photographic style for category-level image classification by generalizing the spatial pyramid , 2011, ICMR.

[16]  Koen E. A. van de Sande,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Peter Auer,et al.  Generic object recognition with boosting , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Oliver Wang,et al.  Material classification using BRDF slices , 2009, CVPR.

[19]  Edward H. Adelson,et al.  Estimating surface reflectance properties from images under unknown illumination , 2001, IS&T/SPIE Electronic Imaging.

[20]  Edward H. Adelson,et al.  On seeing stuff: the perception of materials by humans and machines , 2001, IS&T/SPIE Electronic Imaging.

[21]  Radim Sára,et al.  A Weak Structure Model for Regular Pattern Recognition Applied to Facade Images , 2010, ACCV.

[22]  Jan-Mark Geusebroek,et al.  Significance of the Weibull Distribution and its Sub-models in Natural Image Statistics , 2009, VISAPP.

[23]  Joost van de Weijer,et al.  Edge and corner detection by photometric quasi-invariants , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Thomas Deselaers,et al.  Measuring the Objectness of Image Windows , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Gang Hua,et al.  Discriminative Learning of Local Image Descriptors , 1990, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Thomas Deselaers,et al.  ClassCut for Unsupervised Class Segmentation , 2010, ECCV.

[27]  Edward H. Adelson,et al.  Exploring features in a Bayesian framework for material recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[28]  Manik Varma,et al.  Learning The Discriminative Power-Invariance Trade-Off , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[29]  Mario Fritz,et al.  Classifying materials in the real world , 2010, Image Vis. Comput..

[30]  Steven A. Shafer,et al.  Using color to separate reflection components , 1985 .

[31]  R. Fergus,et al.  Learning invariant features through topographic filter maps , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Michael Isard,et al.  Descriptor Learning for Efficient Retrieval , 2010, ECCV.