Transform coding of image feature descriptors

We investigate transform coding to efficiently store and transmit SIFT and SURF image descriptors. We show that image and feature matching algorithms are robust to significantly compressed features. We achieve near-perfect image matching and retrieval for both SIFT and SURF using ~2 bits/dimension. When applied to SIFT and SURF, this provides a 16× compression relative to conventional floating point representation. We establish a strong correlation between MSE and matching error for feature points and images. Feature compression enables many application that may not otherwise be possible, especially on mobile devices.

[1]  Chuohao Yeo,et al.  Rate-efficient visual correspondences using random projections , 2008, 2008 15th IEEE International Conference on Image Processing.

[2]  Michelle Effros,et al.  On the rate-distortion performance and computational efficiency of the Karhunen-Loeve transform for lossy data compression , 2002, IEEE Trans. Image Process..

[3]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Gregory Shakhnarovich,et al.  Learning task-specific similarity , 2005 .

[5]  Gang Hua,et al.  Discriminant Embedding for Local Image Descriptors , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, CVPR 2004.

[7]  Michael W. Marcellin,et al.  JPEG2000 - image compression fundamentals, standards and practice , 2002, The Kluwer International Series in Engineering and Computer Science.

[8]  Cordelia Schmid,et al.  A Comparison of Affine Region Detectors , 2005, International Journal of Computer Vision.

[9]  Antonio Torralba,et al.  Small codes and large image databases for recognition , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  David Nistér,et al.  Scalable Recognition with a Vocabulary Tree , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[11]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[12]  Bernd Girod,et al.  Outdoors augmented reality on mobile phone using loxel-based visual feature organization , 2008, MIR '08.

[13]  Matthew A. Brown,et al.  Unsupervised 3D object recognition and reconstruction in unordered datasets , 2005, Fifth International Conference on 3-D Digital Imaging and Modeling (3DIM'05).

[14]  Trevor Darrell,et al.  Fast pose estimation with parameter-sensitive hashing , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[15]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[16]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[17]  Matthew A. Brown,et al.  Learning Local Image Descriptors , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.