COGE: A Novel Binary Feature Descriptor Exploring Anisotropy and Non-uniformity

Matching keypoints across images is the base of numerous Computer Vision applications, which is often done with local feature descriptors. Hand-crafted descriptors such as SIFT and SURF are still established leaders in the field since they are discriminative as well as robust. In this paper, we introduce a novel COGE descriptor, a simple yet effective method for keypoint description. By exploiting the anisotropy and the non-uniformity of the underlying gradient distributions, the proposed COGE is highly discriminative and robust. In addition, COGE contains only 480/240/120 bits and can be matched by using Hamming distance, making it ideal for mobile applications. To evaluate the performance of COGE, a comprehensive comparison against SIFT, SURF, ORB and BRISK is performed on three benchmark datasets: the dataset of Mikolajczyk, the INRIA Holidays and the UKbench. Experimental results show that our proposed COGE descriptor significantly outperforms existing schemes.

[1]  Bernd Girod,et al.  Compressed Histogram of Gradients: A Low-Bitrate Descriptor , 2011, International Journal of Computer Vision.

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

[3]  Meng Wang,et al.  Unified Video Annotation via Multigraph Learning , 2009, IEEE Transactions on Circuits and Systems for Video Technology.

[4]  Pierre Vandergheynst,et al.  FREAK: Fast Retina Keypoint , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

[6]  Roland Siegwart,et al.  BRISK: Binary Robust invariant scalable keypoints , 2011, 2011 International Conference on Computer Vision.

[7]  Matthieu Guillaumin,et al.  Segmentation Propagation in ImageNet , 2012, ECCV.

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

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

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

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

[12]  Vincent Lepetit,et al.  DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[14]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[15]  Tat-Seng Chua,et al.  Image Annotation by Graph-Based Inference With Integrated Multiple/Single Instance Representations , 2010, IEEE Transactions on Multimedia.

[16]  Jan-Michael Frahm,et al.  Comparative Evaluation of Binary Features , 2012, ECCV.

[17]  Andrew J. Davison,et al.  Active Matching , 2008, ECCV.

[18]  Shuicheng Yan,et al.  Inferring semantic concepts from community-contributed images and noisy tags , 2009, ACM Multimedia.

[19]  Cordelia Schmid,et al.  Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search , 2008, ECCV.

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

[21]  Antti Oulasvirta,et al.  Computer Vision – ECCV 2006 , 2006, Lecture Notes in Computer Science.