Abstract
Texture analysis is a significant area in image processing, but feature point extraction is pretty susceptible to noise in texture images. In this paper, a new method for extracting feature points, especially from the paper overlapping images, is presented, which is using dynamic threshold, mathematical morphology and image thinning to extract potential feature points. And an optimization algorithm is also proposed to promote the repeatability of feature points via analyzing corresponding skeletons. Results show that the proposed algorithm could depress noise, and the repeatability of this method (60%) outperforms traditional feature extraction algorithms, like Harris (46%), FAST (57%), and SUSAN (45%), in paper overlapping images.
Similar content being viewed by others
REFERENCES
Z. Boulkenafet, J. Komulainen, and A. Hadid, “Face spoofing detection using colour texture analysis,” IEEE Trans. Inf. Forensics Secur. 11 (8), 1818–1830 (2016).
N. L Eun, D. Kang, E. J. Son, et al., “Texture analysis with 3.0-T MRI for association of response to neoadjuvant chemotherapy in breast cancer,” Radiology 294 (1), 31–41 (2020).
A. Manickam, E. Devarasan, G. Manogaran, et al., “Score level based latent fingerprint enhancement and matching using SIFT feature,” Multimedia Tools Appl. 78 (3), 3065–3085 (2019).
M. Safdari, P. Moallem, and M. Satari, “SIFT detector boosted by adaptive contrast threshold to improve matching robustness of remote sensing panchromatic images,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 12 (02), 675–684 (2019).
Q. Guo, M. M. He, and A. Li, “High-resolution remote-sensing image registration based on angle matching of edge point features,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 11 (8), 2881–2895 (2018).
J. J. Yin, G. J. Cheng, N. Liu, et al., “Rock core thin section image stitching based on SIFT features,” Adv. Mater. Res. 1049, 398–401 (2014).
M. González-Hidalgo, S. Massanet, A. Mir, et al., “Improving salt and pepper noise removal using a fuzzy mathematical morphology-based filter,” Appl. Soft Comput. 63, 167–180 (2018).
F. Qiu, J. Berglund, J. R. Jensen, et al., “Speckle noise reduction in SAR imagery using a local adaptive median filter,” GISci. Remote Sens. 41 (3), 244–266 (2004).
M. Matsumoto, “Self-quotient ε-filter for feature extraction from noise corrupted image,” IEICE Trans. Inf. Syst. 93 (11), 3066–3075 (2010).
K. Mikolajczyk and C. Schmid, “A performance evaluation of local descriptors,” in 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE, New York, 2003), pp. 1–33.
K. Mikolajczyk and C. Schmid, “An affine invariant interest point detector,” in 7th European Conference on Computer Vision (Springer-Verlag, Berlin, 2002), pp. 128–142.
C. Harris, “A combined corner and edge detector,” in 4th Alvey Vision Conference (Plessey Co., Manchester, 1988), pp. 147–151.
S. M. Smith and J. M. Brady, “SUSAN—A new approach to low level image processing,” Int. J. Comput. Vision 23 (2), 45–78 (1997).
E. Rosten, R. Porter, and T. Drummond, “Faster and better: A machine learning approach to corner detection,” Comput. Sci. 32 (1), 105–119 (2008).
C. Jian, X. Xiang, and M. Zhang, “Mobile terminal gesture recognition based on improved FAST corner detection,” IET Image Process. 13 (6), 991–997 (2019).
P. Singh, “A review on role of mathematical morphology in face detection,” Int. J. Eng. Manage. Res. 6 (2), 539–543 (2016).
R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th ed. (Pearson, 2018), pp. 662–664.
A. Banharnsakun, “Feature point matching based on ABC-NCC algorithm,” Evol. Syst. 9 (1), 71–80 (2018).
M. A. Fischler and R. C. Bolles, “Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography,” Graphics Image Process. 24 (6), 381–395 (1981).
ACKNOWLEDGMENTS
Bin Zhang of ZZU helped the authors with experiments in this paper, and Wei Li of TU Darmstadt assisted us with submission and revision of the manuscript.
Funding
The authors acknowledge findings and scholarships supported by School of Physics and Engineering, Zhengzhou University.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
COMPLIANCE WITH ETHICAL STANDARDS
This article does not contain any studies involving animals or human participants performed by any of the authors.
CONFLICT OF INTERESTS
The authors declare that they have no conflicts of interest.
Additional information
Jinda Liu, 1993, graduated from Zhengzhou University with Master Degree in July 2019, and Liu is a research assistant in Zhengzhou University now. The areas of research include image processing and machine vision.
Hongxing Pei, 1975, was awarded PhD by Beijing Institute of Technology in Jan. 2009. Now, Li is associate professor in the School of Physics and Engineering in Zhengzhou University, and also is the Deputy Dean in Henan Academy of Big Data. The fields of research are machine vision, artificial intelligence and big data, and several publications were published on Information Technology Journal, Journal of Networks, etc.
Rights and permissions
About this article
Cite this article
Liu, J., Pei, H. An Improved Corner Detector Based on the Skeleton for Texture Image. Pattern Recognit. Image Anal. 31, 221–227 (2021). https://doi.org/10.1134/S1054661821020115
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661821020115