Similarity Limits of Orientation Changes in Affine Transformations With Applications to Planar Pattern Matching
DOI:
https://doi.org/10.5566/ias.2734Keywords:
affine transformation, geometrical orientations, hypothesis testing, planar pattern matching, similarity biasAbstract
Besides descriptor designing, factoring out the categorical effects of affine transformations is also an effective way to match features. This paper proposed and demonstrated a hypothesis that any coplanar orientations have limited geometrical changes when observed in the camera screen under given ranges of 3D affine transformations. Confirmatory experiments are accomplished by Matlab simulations focusing on specific influences of 3D affine transformations on similarity biases between concerned orientation changes. Statistical analyses and results show that rotations about plane axes mainly affect the geometrical biases of orientation changes. A set of fit limits standing for the biggest influences of most affine transformations in specified ranges are numerically approximated by total sample space distribution and experimental extreme values. We use these Similarity Limits of Orientation Changes(SLOC) as optimization constraints in matching problems, and an application example of planar pattern matching is given. The effectiveness and efficiency of SLOC are proved by the experimental results in Mikolajczyk and HPatches testbed.
References
Alahi A, Ortiz R, Vandergheynst P (2012). FREAK: Fast retina keypoint. In CVPR:510–7.
Balntas V, Lenc K, Vedaldi A, Mikolajczyk K (2017). HPatches: A benchmark and evaluation of handcrafted and learned local descriptors, In CVPR:3852–61.
Bay H, Ess A, Tuytelaars T, Gool LV (2008). Speeded-up robust features (SURF). Comput Vis Image Und 110:346–59.
Calonder M, Lepetit V, Strecha C (2010). BRIEF: Binary robust independent elementary features. In ECCV 6314:778–92.
Fischler MA, Bolles RC (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24: 381–95.
Forsyth DA, Ponce J (2002). Computer vision: a modern approach. Prentice Hall Professional Technical Reference.
Hamzah RA, Ibrahim H, Hassan AHA (2016). Stereo matching algorithm based on illumination control to improve the accuracy. Image Anal Stereol 35:39–52.
Hu MK (1962). Visual pattern recognition by moment invariants. IEEE T Inform Theory 8:179–87.
Lepetit V, Lagger P, fua P (2005). Randomized trees for real-time keypoint recognition. In CVPR 2: 775–81.
Leutenegger S, Chli M, Siegwart RY (2011). BRISK: Binary robust invariant scalable keypoints, In ICCV 2548–55.
Lieberknecht S, Benhimane S, Meier P, Navab N (2009). A dataset and evaluation methodology for template-based tracking algorithms. In ISMAR 145–51.
Lowe DG (2004). Distinctive image features from scale-invariant keypoints. Int J Comput Vision 60: 91–110.
Mikolajczyk K, Schmid C (2005). A performance evaluation of local descriptors. IEEE T Pattern Anal 27:1615–30.
Mikolajczyk K, Tuytelaars T, Schmid C, Zisserman A， Matas J，Schaffalitzky F, et al. (2005). A comparison of affine region detectors. Int J Comput Vision 65: 43–72.
Valery N，Jesús A，Antonio A, Mossi JM, Soledad G (2007). Gradual transition detection for video partitioning using morphological operators. Image Anal Stereol 26:51–61.
Ozuysal M, Fua P, Lepetit V (2007). Fast keypoint recognition in ten lines of code. In CVPR 1:1–8.
Ozuysal M, Lepetit V, Fua P (2009). Pose estimation for category specific multiview object localization. In CVPR 778–85.
Rublee E, Rabaud V, Konolige K, Bradski G (2011). ORB: An efficient alternative to SIFT or SURF. In ICCV 2564–71.
Se S, Jasiobedzki P (2006). Photo-realistic 3D model reconstruction. In ICRA 3076–82.
Tomaževič D, Likar B, Pernuš F (2012). Multi-feature mutual information image registration. Image Anal Stereol 31:43–53.
Xie T, Xie LJ, Song GH, Zheng Y (2013). Augmented reality registration from nature features based on planar color distribution. J Zhejiang Univ(Eng Sci) 47:2243–52.
Zhou H, Yuan Y, Shi C (2009). Object tracking using SIFT features and mean shift. Comput Vis Image Und 113:345–52.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Image Analysis & Stereology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
