Abstract
Scale invariant feature transform (SIFT) is one of the most effective techniques in image matching applications. However, it has a main drawback: existing numerous redundant keypoints located very close to each other in the image. These redundant keypoints increase the computational complexity while they decrease the image matching performance. Redundant keypoint elimination method (RKEM)–SIFT are incorporated to eliminate these points by comparing their distances with a fixed experimental threshold value. However, this value has a great impact on the matching results. In this paper, an adaptive RKEM is presented which considers type of the images and distortion thereof, while adjusting the threshold value. Moreover, this value is found separately for the reference and sensed images. In an image, the adaptive RKEM finds the histogram of the keypoints distances, for which the number and the width of the bins are determined based on the number of keypoints and the distances distribution metrics. Then, a maximum value for searching the optimal threshold value is determined. Finally, for each integer value smaller than the mentioned maximum, a set containing distances smaller than that value is created and the one with the smallest variance is selected. The integer value corresponding to that set is chosen as the adaptive threshold for that image. This approach can improve the efficiency of the RKEM-SIFT in eliminating redundant keypoints. Simulation results validated that the proposed method outperforms the SIFT, A2 SIFT and RKEM-SIFT in terms of the matching performance indices.
Similar content being viewed by others
References
Sedaghat A, Mokhtarzade M, Ebadi H (2011) Uniform robust scale-invariant feature matching for optical remote sensing images. IEEE Trans Geosci Remote Sens 49:4516–4527
Hossein-Nejad Z, Nasri M (2017a) A Review on Image Registration Methods, Concepts and applications. J Mach Vis Image Process 5:39–67
Radke RJ, Andra S, Al-Kofahi O, Roysam B (2005) Image change detection algorithms: a systematic survey. IEEE Trans Image Process 14:294–307
Liu Y, Liu S, Wang Z (2015) Multi-focus image fusion with dense SIFT. Inf Fusion 23:139–155
Tsai C-L, Li C-Y, Yang G, Lin K-S (2009) The edge-driven dual-bootstrap iterative closest point algorithm for registration of multimodal fluorescein angiogram sequence. IEEE Trans Med Imaging 29:636–649
Guo Y, Lei Y, Liu L, Wang Y, Bennamoun M, Sohel F (2016) EI3D: Expression-invariant 3D face recognition based on feature and shape matching. Pattern Recogn Lett 83:403–412
Zitova B, Flusser J (2003) Image registration methods: a survey. Image Vis Comput 21:977–1000
Rubeaux M, Nunes J-C, Albera L, Garreau M (2014) Medical image registration using Edgeworth-based approximation of Mutual Information. IRBM 35:139–148
Remondino F, El-Hakim SF, Gruen A, Zhang L (2008) Turning images into 3-D models. IEEE Signal Process Mag 25:55–65
Sagayam KM, Hemanth DJ (2019) A probabilistic model for state sequence analysis in hidden Markov model for hand gesture recognition. Comput Intell 35:59–81
Sagayam KM, Hemanth DJ (2018) ABC algorithm based optimization of 1-D hidden Markov model for hand gesture recognition applications. Comput Ind 99:313–323
Sagayam KM, Hemanth DJ (2017) “Application of pseudo 2-D hidden Markov model for hand gesture recognition.” In: Proceedings of the first international conference on computational intelligence and informatics 179–188
Sagayam KM, Hemanth DJ2018) “Comparative analysis of 1-D HMM and 2-D HMM for hand motion recognition applications.”Progress in intelligent computing techniques: theory, practice, and applications 227–234
Hsu C-T, Beuker RA (2000) (2000)Multiresolution feature-based image registration. Vis Commun Image Process 4067:1490–1498
Aghajani K, Yousefpour R, Zohrehvandi M (2019) A robust non-local total-variation based image registration method under illumination changes in medical applications. Biomed Signal Process Control 49:96–112
Rosten E, Drummond T (2006) Machine learning for high-speed corner detection. Eur Conf Comput Vis 3951:430–443
Rublee E, Rabaud V, Konolige K, Bradski GR (2011) “ORB: An efficient alternative to SIFT or SURF.” ICCV 1–8
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60:91–110
Sagayam KM, Hemanth DJ, Ramprasad YN, Menon R (2017) “Optimization of hand motion recognition system based on 2D HMM approch using ABC algorithm.” In: Hybrid Intelligent Techniques for pattern Analysis and Understanding, pp 167–192
Gu L, Su J (2008) “Natural hand posture recognition based on Zernike moments and hierarchical classifier.” In: 2008 IEEE international conference on robotics and automation 3088–3093
Mikolajczyk K, Schmid C (2005) A performance evaluation of local descriptors. IEEE Trans Pattern Anal Mach Intell 27:1615–1630
Mohtaram N, Radgui A, Caron G, Mouaddib EM (2018) “Amift: affine-mirror invariant feature transform.” In: 2018 25th IEEE International Conference on Image Processing (ICIP) 893–897
Zhang Q, Wang Y, Wang L (2015) Registration of images with affine geometric distortion based on maximally stable extremal regions and phase congruency. Image Vis Comput 36:23–39
Liao K, Liu G, Hui Y (2013) An improvement to the SIFT descriptor for image representation and matching. Pattern Recognit Lett 34:1211–1220
Chen Y, Shang L (2016) Improved SIFT image registration algorithm on characteristic statistical distributions and consistency constraint. Optik Int J Light Electron Opt 127:900–911
Yi Z, Zhiguo C, Yang X (2008) Multi-spectral remote image registration based on SIFT. Electron Lett 44:107–108
Castillo-Carrión S, Guerrero-Ginel J-E (2017) SIFT optimization and automation for matching images from multiple temporal sources. Int J Appl Earth Obs Geoinf 57:113–122
Ding X, Ding Y (2017) “Image matching with an improved descriptor based on SIFT,” In: Seventh international conference on electronics and information engineering 10322: 1–6
Hossein-Nejad Z, Nasri M (2017b) An adaptive image registration method based on SIFT features and RANSAC transform. Comput Electr Eng 62:524–537
Zhu Y, Cheng S, Stanković V, Stanković L (2013) Image registration using BP-SIFT. J Vis Commun Image Represent 24:448–457
Hossein-Nejad Z, Nasri M (2017c) RKEM: redundant keypoint elimination method in image registration. IET Image Proc 11:273–284
Wang F, You H, Fu X (2014) Adapted anisotropic Gaussian SIFT matching strategy for SAR registration. IEEE Geosci Remote Sens Lett 12:160–164
Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (SURF). Comput Vis Image Underst 110:346–359
Morel J-M, Yu G (2009) ASIFT: A new framework for fully affine invariant image comparison. SIAM J Imaging Sci 2:438–469
Fan J, Wu Y, Wang F, Zhang Q, Liao G, Li M (2014) SAR image registration using phase congruency and nonlinear diffusion-based SIFT. IEEE Geosci Remote Sens Lett 12:562–566
Wang S, You H, Fu K (2011) BFSIFT: A novel method to find feature matches for SAR image registration. IEEE Geosci Remote Sens Lett 9:649–653
Dellinger F, Delon J, Gousseau Y, Michel J, Tupin F (2015) SAR-SIFT: a SIFT-like algorithm for SAR images. IEEE Trans Geosci Remote Sens 53:453–466
Ma J, Zhao J, Jiang J, Zhou H, Guo X (2019) Locality preserving matching. Int J Comput Vis 127:512–531
Zhou Z, Cheng S, Li Z (2016) “MDS-SIFT: an improved SIFT matching algorithm based on MDS dimensionality reduction.” In: 2016 3rd International Conference on Systems and Informatics (ICSAI), 896–900
Ran S, Zhong W, Ye L, Zhang Q (2015) “An improved SIFT algorithm based on adaptive threshold canny.” In: 2015 8th international congress on image and signal processing (CISP), 340–345
Zhou D, Zeng L, Liang J, Zhang K (2016) Improved method for SAR image registration based on scale invariant feature transform. IET Radar Sonar Navig 11:579–585
Tajeripour F, Kabir E, Sheikhi A (2008) Fabric defect detection using modified local binary patterns. EURASIP J Adv Signal Process 2008:1–12
Hossein-Nejad Zahra, Nasri M (2019) “Retianl image registration based on auto-adaptive SIFT and redundant keypoint elimination method.” In: 27th Iranian conference on electrical engineering (ICEE2019)
Hossein-Nejad Z, Nasri M (2020) Natural image mosaicing based on redundant keypoint elimination method in SIFT algorithm and adaptive RANSAC method. Signal Data Process 17:1–13
Hossein-Nejad Z, Nasri M (2019) Copy-move image forgery detection using redundant keypoint elimination method. In: Ramakrishnan S (ed) Cryptographic and information security approaches for images and videos. CRC Press, Boca Raton, pp 773–797
https://lear.inrialpes.fr/people/mikolajczyk/Database/index.html
https://github.com/jagracar/OpenCV-python-tests/blob/master/OpenCV-tutorials/data/box.png
Lingua A, Marenchino D, Nex F (2009) Performance analysis of the SIFT operator for automatic feature extraction and matching in photogrammetric applications. Sensors 9:3745–3766
Alcantarilla PF, Bartoli A, Davison AJ (2012) “KAZE features.” In: European conference on computer vision 7577: 214–227
Acknowledgements
The authors would like to thank the Pattern Analysis and Applications Associate Editor and the anonymous reviewers for their valuable comments.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Hossein-Nejad, Z., Agahi, H. & Mahmoodzadeh, A. Image matching based on the adaptive redundant keypoint elimination method in the SIFT algorithm. Pattern Anal Applic 24, 669–683 (2021). https://doi.org/10.1007/s10044-020-00938-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-020-00938-w