FasT-Match: Fast Affine Template Matching

Fast-Match is a fast algorithm for approximate template matching under 2D affine transformations that minimizes the Sum-of-Absolute-Differences (SAD) error measure. There is a huge number of transformations to consider but we prove that they can be sampled using a density that depends on the smoothness of the image. For each potential transformation, we approximate the SAD error using a sub linear algorithm that randomly examines only a small number of pixels. We further accelerate the algorithm using a branch-and-bound scheme. As images are known to be piecewise smooth, the result is a practical affine template matching algorithm with approximation guarantees, that takes a few seconds to run on a standard machine. We perform several experiments on three different datasets, and report very good results. To the best of our knowledge, this is the first template matching algorithm which is guaranteed to handle arbitrary 2D affine transformations.

[1]  Daniel Keren,et al.  Applying Property Testing to an Image Partitioning Problem , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Kimmo Fredriksson.  Rotation Invariant Template Matching , 2001 .

[3]  Daniel Reichman,et al.  Tight Approximation of Image Matching , 2011, ArXiv.

[4]  J. H. van Hateren,et al.  Modelling the Power Spectra of Natural Images: Statistics and Information , 1996, Vision Research.

[5]  Jean-Michel Morel,et al.  ASIFT: A New Framework for Fully Affine Invariant Image Comparison , 2009, SIAM J. Imaging Sci..

[6]  Steven M. Seitz,et al.  Filter flow , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[7]  David G. Lowe,et al.  Scalable Nearest Neighbor Algorithms for High Dimensional Data , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Sofya Raskhodnikova,et al.  Approximate Testing of Visual Properties , 2003, RANDOM-APPROX.

[9]  Michael Werman,et al.  Accelerating Pattern Matching or How Much Can You Slide? , 2007, ACCV.

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

[11]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[12]  Petros Maragos,et al.  Motion displacement estimation using an affine model for image matching , 1991 .

[13]  Yuandong Tian,et al.  Globally Optimal Estimation of Nonrigid Image Distortion , 2012, International Journal of Computer Vision.

[14]  Simon Baker,et al.  Lucas-Kanade 20 Years On: A Unifying Framework , 2004, International Journal of Computer Vision.

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

[16]  Shu-Yuan Chen,et al.  Retrieval of translated, rotated and scaled color textures , 2003, Pattern Recognit..

[17]  Vittorio Ferrari,et al.  Exploiting spatial overlap to efficiently compute appearance distances between image windows , 2011, NIPS 2011.

[18]  Sunil Arya,et al.  An optimal algorithm for approximate nearest neighbor searching fixed dimensions , 1998, JACM.

[19]  Federico Tombari,et al.  Performance Evaluation of Full Search Equivalent Pattern Matching Algorithms , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Hae Yong Kim,et al.  Grayscale Template-Matching Invariant to Rotation, Scale, Translation, Brightness and Contrast , 2007, PSIVT.

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

[22]  Du-Ming Tsai,et al.  Rotation-invariant pattern matching using wavelet decomposition , 2002, Pattern Recognit. Lett..

[23]  Dana Ron,et al.  Testing Properties of Sparse Images , 2010, FOCS.

[24]  Quan Wang,et al.  Real-Time Image Matching Based on Multiple View Kernel Projection , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[26]  William Rucklidge.  Efficient guaranteed search for gray-level patterns , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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