High-Speed and Local-Changes Invariant Image Matching

SUMMARY In recent years, many variants of key point based image descriptors have been designed for the image matching, and they have achieved remarkable performances. However, to some images, local fea- tures appear to be inapplicable. Since theses images usually have many local changes around key points compared with a normal image, we define this special image category as the image with local changes (IL). An IL pair (ILP) refers to an image pair which contains a normal image and its IL. ILP usually loses local visual similarities between two images while still holding global visual similarity. When an IL is given as a query image, the purpose of this work is to match the corresponding ILP in a large scale image set. As a solution, we use a compressed HOG feature descriptor to extract global visual similarity. For the nearest neighbor search problem, we propose random projection indexed KD-tree forests (rKDFs) to match ILP e ffi ciently instead of exhaustive linear search. rKDFs is built with large scale low-dimensional KD-trees. Each KD-tree is built in a ran- dom projection indexed subspace and contributes to the final result equally through a voting mechanism. We evaluated our method by a benchmark which contains 35,000 candidate images and 5,000 query images. The results show that our method is e ffi cient for solving local-changes invariant image matching problems.

[1]  Chao Zhang,et al.  Compressive image retrieval with modified images , 2015, 2015 10th Asian Control Conference (ASCC).

[2]  Chao Zhang,et al.  Robust Visual Tracking via Coupled Randomness , 2015, IEICE Trans. Inf. Syst..

[3]  Patrick Pérez,et al.  Revisiting the VLAD image representation , 2013, ACM Multimedia.

[4]  Noah Snavely,et al.  Image matching using local symmetry features , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Peng Li,et al.  Image local invariant features matching using global information , 2012, 2012 IEEE International Conference on Information Science and Technology.

[6]  Alexei A. Efros,et al.  Data-driven visual similarity for cross-domain image matching , 2011, ACM Trans. Graph..

[7]  Marc Alexa,et al.  Sketch-Based Image Retrieval: Benchmark and Bag-of-Features Descriptors , 2011, IEEE Transactions on Visualization and Computer Graphics.

[8]  Jean Ponce,et al.  Automatic alignment of paintings and photographs depicting a 3D scene , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[9]  Antonio Torralba,et al.  SIFT Flow: Dense Correspondence across Scenes and Its Applications , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Ying He,et al.  Randomly Projected KD-Trees with Distance Metric Learning for Image Retrieval , 2011, MMM.

[11]  Andrea Vedaldi,et al.  Vlfeat: an open and portable library of computer vision algorithms , 2010, ACM Multimedia.

[12]  Steven J. Gortler,et al.  A perception-based color space for illumination-invariant image processing , 2008, ACM Trans. Graph..

[13]  Richard I. Hartley,et al.  Optimised KD-trees for fast image descriptor matching , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

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

[15]  R. DeVore,et al.  A Simple Proof of the Restricted Isometry Property for Random Matrices , 2008 .

[16]  Florent Perronnin,et al.  Fisher Kernels on Visual Vocabularies for Image Categorization , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[18]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

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

[20]  Trevor Darrell,et al.  Efficient image matching with distributions of local invariant features , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

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

[22]  Dimitris Achlioptas,et al.  Database-friendly random projections: Johnson-Lindenstrauss with binary coins , 2003, J. Comput. Syst. Sci..

[23]  Piotr Indyk,et al.  Similarity Search in High Dimensions via Hashing , 1999, VLDB.

[24]  J. T. Robinson,et al.  The K-D-B-tree: a search structure for large multidimensional dynamic indexes , 1981, SIGMOD '81.

[25]  Jon Louis Bentley,et al.  An Algorithm for Finding Best Matches in Logarithmic Expected Time , 1976, TOMS.

[26]  David G. Lowe,et al.  Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration , 2009, VISAPP.

[27]  Christopher Hunt SURF: Speeded-Up Robust Features , 2009 .

[28]  Antonio Torralba,et al.  Building the gist of a scene: the role of global image features in recognition. , 2006, Progress in brain research.

[29]  Yan Ke,et al.  Efficient Near-duplicate Detection and Sub-image Retrieval , 2004 .

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