Image compression and retrieval for Mobile Visual Search

Mobile Visual Search (MVS) is an emerging area of research given the explosion of smart and computationally powerful mobile devices. Typically, MVS involves the computation of local image features which are then used within a matching process. Such applications pose certain unique challenges due to computation, power and bandwidth constraints of the mobile device. This paper examines the trade-off between two general frameworks for implementing MVS: 1. sending compressed images and performing feature extraction and matching on a server; and 2. performing feature extraction on the mobile device and sending these to a server for matching. A number of local image feature algorithms are studied using various image compression schemes from the point view of matching accuracy and processing time. Results show that the matching accuracy of sending compressed images is comparable to sending compact image features when using a high quality image coder, in this case JPEG2000 and HDPhoto.

[1]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[2]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[3]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[4]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[5]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

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

[7]  Michael W. Marcellin,et al.  JPEG2000 - image compression fundamentals, standards and practice , 2013, The Kluwer international series in engineering and computer science.

[8]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Huizhong Chen,et al.  The stanford mobile visual search data set , 2011, MMSys.

[10]  Kurt Konolige,et al.  CenSurE: Center Surround Extremas for Realtime Feature Detection and Matching , 2008, ECCV.

[11]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[12]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[13]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

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

[15]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

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

[17]  Bernd Girod,et al.  Mobile Visual Search , 2011, IEEE Signal Processing Magazine.