Accuracy assessment of the effect of different feature descriptors on the automatic co-registration of overlapping images
Abstract
This research seeks to assess the effect of different selected feature descriptors on the accuracy of an automatic image registration scheme. Three different feature descriptors were selected based on their peculiar characteristics, and implemented in the process of developing the image registration scheme. These feature descriptors (Modified Harris and Stephens corner detector (MHCD), the Scale Invariant Feature Transform (SIFT) and the Speeded Up Robust Feature (SURF)) were used to automatically extract the conjugate points common to the overlapping image pairs used for the registration. Random Sampling Consensus (RANSAC) algorithm was used to exclude outliers and to fit the matched correspondences, Sum of Absolute Differences (SAD) which is a correlation-based feature matching metric was used for the feature match, while projective transformation function was used for the computation of the transformation matrix (T). The obtained overall result proved that the SURF algorithm outperforms the other two feature descriptors with an accuracy measure of -0.0009 pixels, while SIFT with a cumulative signed distance of 0.0328 pixels also proved to be more accurate than MHCD with a cumulative signed distance of 0.0457 pixels. The findings affirmed the importance of choosing the right feature descriptor in the overall accuracy of an automatic image registration scheme.
Keyword : image registration, data fusion, feature descriptors, digital image processing, remote sensing applications, mosaic generation
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Ajayi, O. G. (2019). Development of an integrated automatic image registration scheme [PhD thesis]. Department of Surveying and Geoinformatics, School of Postgraduate Studies, Federal University of Technology, Minna, Nigeria.
Ajayi, O. G. (2020). Performance analysis of selected feature descriptors used for automatic image registration. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B3-2020, 559–566. https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-559-2020
Al-Ruzouq, R. (2004). Semi-Automatic registration of multisource satellite imagery with varying geometric resolutions [PhD thesis]. Geomatics Engineering Department, Faculty of Graduate Studies, Calgary, Alberta.
Bay, H., Ess, A., Tuytelaars, T., & Van, G. L. (2008). Speeded Up Robust Features (SURF). Computer Vision and Image Understanding, 110(3), 346–359. https://doi.org/10.1016/j.cviu.2007.09.014
Bolarinwa, O. O. (2017). Development of a semi-automated digital stereo comparator [MSc thesis]. Department of Surveying and Geoinformatics, University of Lagos, Akoka-Lagos.
Calvin, J. M., Gotsman, C. J., & Zheng, C. (2019). Global optimization for image registration. AIP Conference Proceedings, 2070, Article 020008. https://doi.org/10.1063/1.5089975
Cuiyin, L., Jishang, X., & Feng, W. (2021). A review of keypoints’ detection and feature description in image registration. Scientific Programming, 2021, Article 8509164. https://doi.org/10.1155/2021/8509164
Flusser, J. (1994). A moment-based approach to registration of images with affine geometric distortion. IEEE Transaction on Geoscience and Remote Sensing, 32(1), 382–387. https://doi.org/10.1109/36.295052
Goshtasby, A. (1988). Registration of images with geometric distortions. IEEE Transactions on Geoscience and Remote Sensing, 26, 60–64. https://doi.org/10.1109/36.3000
Goshtasby, A., Lawrence, S., Studholme, C., & Terzopoulos, D. (2003). Non-rigid image registration: Guest editor’s Introduction. Computer Vision and Image Understanding, 89, 109–113. https://doi.org/10.1016/S1077-3142(03)00016-X
Guorong, Y., & Shuangming, Z. (2020). A new feature descriptor for multimodal image registration using phase congruency. Sensors, 20(18), Article 5105. https://doi.org/10.3390/s20185105
Harris, C., & Stephens, M. (1988). A combined corner and edge detector. In Proceedings of the 4th Alvey Vision Conference (pp. 147–151). Alvety Vision Club. https://doi.org/10.5244/C.2.23
Kanade, K., Jansa, J., & Kager, H. (1997). Photogrammetry- advanced methods and applications. Ferd. Dummlers Verlag.
Kleissl, J. (2013). Solar energy forecasting and resource assessment. Academic Press.
Krishna, S., & Varghese, A. (2015). Feature based automatic multiview image registration. International Journal of Computer Science and Software Engineering, 4(11), 308–314.
Lin, Q., & Labuz, J. F. (2013). Fracture of sandstone characterized by digital image correlation. International Journal of Rock Mechanics and Mining Sciences, 60, 235–245. https://doi.org/10.1016/j.ijrmms.2012.12.043
Lowe, D. G. (1999). Object recognition from local scale-invariant features. In Proceedings of the International Conference on Computer Vision (pp. 1150–1157). IEEE. https://doi.org/10.1109/ICCV.1999.790410
Olaleye, J. B. (2010). Mapping from images by vector photogrammetry. [Unpublished Series in Geoinformatics, Lecture Note 10-1]. Dept. of Surveying and Geoinformatics, University of Lagos.
Olaleye, J. B., Ajayi O. G., Omogunloye, O. G., Odumosu, J. O., & Okorocha, C. V. (2015). Automatic registration of simultaneously overlapping images. NED University Journal of Research – Applied Sciences, XII(4), 53–66.
Panchal, P. M., Panchal, S. R., & Shah, S. K. (2013). A comparison of SIFT and SURF. International Journal of Innovative Research in Computer and Communication Engineering, 1(2), 323–327.
Rittavee, M., Yuan, F. Z., & Robert, L. E. (2009). Image registration using adaptive polar transform. IEEE Transaction on Image Processing, 18(10), 2340–2354. https://doi.org/10.1109/TIP.2009.2025010
Scharstein, D., & Szeliski, R. (2002). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 47(1/2/3), 7–42. https://doi.org/10.1023/A:1014573219977
Shih-Ming, J. (2012). Technique of image registration in digital image processing – A review. International Journal of Information Technology and Knowledge Management, 5(2), 239–243.
Sindhu, M. G. (2014). Classification of image registration techniques and algorithms in digital image processing – a research survey. International Journal of Computer Trends and Technology, 15(2), 78–82. https://doi.org/10.14445/22312803/IJCTT-V15P118
Ting, X. L., & Herng, H. C. (2016). Medical image registration based on an improved ant colony optimization Algorithm. International Journal of Pharmacy, Medicine and Biological Sciences, 5(1), 17–22.
Tsai, C.-H., & Lin, Y.-C. (2017). An accelerated image matching technique for UAV orthoimage registration. ISPRS Journal of Photogrammetry and Remote Sensing, 128, 130–145. https://doi.org/10.1016/j.isprsjprs.2017.03.017
Vivek, K. G., & Kanchan, C. (2014). An analytical study of SIFT and SURF in image registration. International Journal of Engineering and Innovative Technology, 3(9), 130–134.
Xiaolong, D., & Siamak, K. (1999). A feature based image registration algorithm using improved chain-code representation combined with invariant moments. IEEE Transactions on Geoscience and Remote Sensing, 37(5), 2351–2362. https://doi.org/10.1109/36.789634
Zhang, P. F., Li, X. Y., & Ma, L. (2014). Grid computing based on game optimization theory for networks scheduling. Journal of Network and Computer Applications, 9(5), 1295–1300. https://doi.org/10.4304/jnw.9.5.1295-1300
Zhong, Z., Guo, X., Cai, Y., Yang, Y., Wang, J., Jia, X., & Mao, W. (2016). 3D-2D deformable image registration using feature based nonuniform meshes. BioMed Research International, 2016, Article 4382854. https://doi.org/10.1155/2016/4382854