Rapid Online Analysis of Local Feature Detectors and Their Complementarity

A vision system that can assess its own performance and take appropriate actions online to maximize its effectiveness would be a step towards achieving the long-cherished goal of imitating humans. This paper proposes a method for performing an online performance analysis of local feature detectors, the primary stage of many practical vision systems. It advocates the spatial distribution of local image features as a good performance indicator and presents a metric that can be calculated rapidly, concurs with human visual assessments and is complementary to existing offline measures such as repeatability. The metric is shown to provide a measure of complementarity for combinations of detectors, correctly reflecting the underlying principles of individual detectors. Qualitative results on well-established datasets for several state-of-the-art detectors are presented based on the proposed measure. Using a hypothesis testing approach and a newly-acquired, larger image database, statistically-significant performance differences are identified. Different detector pairs and triplets are examined quantitatively and the results provide a useful guideline for combining detectors in applications that require a reasonable spatial distribution of image features. A principled framework for combining feature detectors in these applications is also presented. Timing results reveal the potential of the metric for online applications.

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

[2]  Q. Mcnemar.  Note on the sampling error of the difference between correlated proportions or percentages , 1947, Psychometrika.

[3]  Klaus D. McDonald-Maier,et al.  Improved repeatability measures for evaluating performance of feature detectors , 2015, ArXiv.

[4]  D E Wrede,et al.  Central axis tissue--air ratios as a function of area-perimeter at depth and their applicability to irregularly shaped fields. , 1972, Physics in medicine and biology.

[5]  Klaus D. McDonald-Maier,et al.  An Algorithm for the Contextual Adaption of SURF Octave Selection With Good Matching Performance: Best Octaves , 2012, IEEE Transactions on Image Processing.

[6]  Wolfgang Förstner,et al.  Coding Images with Local Features , 2010, International Journal of Computer Vision.

[7]  Frédéric Jurie,et al.  Sampling Strategies for Bag-of-Features Image Classification , 2006, ECCV.

[8]  Bodo Rosenhahn,et al.  NF-Features - No-Feature-Features for Representing Non-textured Regions , 2010, ECCV.

[9]  Klaus D. McDonald-Maier,et al.  Measuring the Coverage of Interest Point Detectors , 2011, ICIAR.

[10]  Wolfgang Förstner,et al.  Detecting interpretable and accurate scale-invariant keypoints , 2009, 2009 IEEE 12th International Conference on Computer Vision.

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

[12]  James Hanley,et al.  If we're so different, why do we keep overlapping? When 1 plus 1 doesn't make 2. , 2002, CMAJ : Canadian Medical Association journal = journal de l'Association medicale canadienne.

[13]  H. Goldstein,et al.  The Graphical Presentation of a Collection of Means , 1995 .

[14]  Antonio Torralba,et al.  Learning hierarchical models of scenes, objects, and parts , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[15]  Andrew Zisserman,et al.  An Affine Invariant Salient Region Detector , 2004, ECCV.

[16]  Alexei A. Efros,et al.  Discovering object categories in image collections , 2005 .

[17]  Umeshwar Dayal,et al.  K-Harmonic Means - A Spatial Clustering Algorithm with Boosting , 2000, TSDM.

[18]  Andrew Zisserman,et al.  Video Google: a text retrieval approach to object matching in videos , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[19]  Bernt Schiele,et al.  Multiple Object Class Detection with a Generative Model , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[20]  W. Grove.  Statistical Methods for Rates and Proportions, 2nd ed , 1981 .

[21]  Tinne Tuytelaars,et al.  Dense interest points , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[22]  Cordelia Schmid,et al.  A sparse texture representation using affine-invariant regions , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[23]  D. A. Bell,et al.  Applied Statistics , 1953, Nature.

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

[25]  Stepán Obdrzálek,et al.  Stable Affine Frames on Isophotes , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[26]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

[27]  J. Fleiss.  Statistical methods for rates and proportions , 1974 .

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

[29]  Mads Nielsen,et al.  Feature-Based Image Analysis , 2003, International Journal of Computer Vision.

[30]  Wolfgang Förstner,et al.  Evaluating the Suitability of Feature Detectors for Automatic Image Orientation Systems , 2009, ICVS.