SymPaD: Symbolic Patch Descriptor

We propose a new local image descriptor named SymPaD for image understanding. SymPaD is a probability vector associated with a given image pixel and represents the attachment of the pixel to a previously designed shape repertoire. As such the approach is model-driven. The SymPad descriptor is illumination and rotation invariant, and extremely flexible on extending the repertoire with any parametrically generated geometrical shapes and any desired additional transformation types.

[1]  Sinem Aslan,et al.  Symbolic feature detection for image understanding , 2014, Electronic Imaging.

[2]  Lewis D. Griffin.  The Second Order Local-Image-Structure Solid , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[4]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.

[5]  Frédéric Jurie,et al.  Creating efficient codebooks for visual recognition , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[6]  B. H. Shekar,et al.  KID: Kirsch Directional Features Based Image Descriptor , 2013, PReMI.

[7]  Lewis D. Griffin,et al.  Novel image feature alphabets for object recognition , 2008, 2008 19th International Conference on Pattern Recognition.

[8]  Matthieu Cord,et al.  Bag-of-Words Image Representation: Key Ideas and Further Insight , 2014, Fusion in Computer Vision.

[9]  D. Lowe,et al.  Fast Matching of Binary Features , 2012, 2012 Ninth Conference on Computer and Robot Vision.

[10]  Lewis D. Griffin,et al.  Natural image profiles are most likely to be step edges , 2004, Vision Research.

[11]  Lewis D. Griffin,et al.  Feature category systems for 2nd order local image structure induced by natural image statistics and otherwise , 2007, Electronic Imaging.

[12]  R. Weale.  Vision. A Computational Investigation Into the Human Representation and Processing of Visual Information. David Marr , 1983 .

[13]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[15]  J. Koenderink.  The structure of images , 2004, Biological Cybernetics.

[16]  Lewis D. Griffin,et al.  Using Basic Image Features for Texture Classification , 2010, International Journal of Computer Vision.

[17]  Lewis D. Griffin,et al.  Writer identification using oriented Basic Image Features and the Delta encoding , 2014, Pattern Recognit..

[18]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.