Abstract
Aiming at low-contrast fundus images directly captured by fundus instrument, a fundus image registration method based on improved feature description was proposed to improve the accuracy and efficiency of registration. First, pixel-level feature points were detected, and the sub-pixel position was calculated by Zernike Matrix. Then, an improved multi-disk mask feature description technique based on the FREAK algorithm is introduced to describe the feature points. Finally, the Euclidean distance combined with random sampling consistency algorithm is used to purify the matching points and calculate the transformation matrix to carry out the final image registration. The experimental results show that the proposed registration method can be used in fundus screening image database, especially in low-contrast fundus images. Compared with SIFT (Scale-invariant Feature Transform), SURF (Speeded-Up Robust Features) and FREAK (Fast Retina Keypoint) algorithms, the new method has more advantages in registration effect, efficiency and speed.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Devadas, P., Kalaiarasi, G., Selvi, M.: Intensity based Image Registration on Brain MRI images. In: Second International Conference on Inventive Research in Computing Applications (ICIRCA), pp. 257–262 (2020)
Jalili, J., Hejazi, S.M., Riazi-Esfahani, M., et al.: Retinal image mosaicking using scale-invariant feature transformation feature descriptors and voronoi diagram. J. Med. Imag. 7(04), 044001 (2020)
Rutesic, P., Stosic, Z.: Image registration based on normalized cross correlation and discrete cosine transform. Int. J. Signal. Process. 3, 16–20 (2018)
Yang, Y., Li, J., Wen, Q., et al.: Improved particle swarm optimization image registration based on mutual information. In: 11th International Conference on Measuring Technology and Mechatronics Automation. IEEE Press, NJ (2019)
Saha, S., Rahaman, G.M.A., Islam, T., et al.: Retinal image registration using log-polar transform and robust description of bifurcation points. Biomed. Signal Process. Control 66(11), 189–201 (2021)
Adal, K.M., et al.: A hierarchical coarse-to-fine approach for fundus image registration. In: International Workshop on Biomedical Image Registration, pp. 93–102 (2014)
Xiaoyan, L., Haohao, W., Gang, S., et al.: Automatic registration of fluorescein fundus angiography image sequences based on mutual information. J. Electron. Inf. Technol. 40(08), 1919–1926 (2018)
Parekar, J., et al.: Automatic retinal image registration using fully connected vascular tree. In: International Conference on Signal and Information Processing (IConSIP), pp. 1–5 (2016)
Shu, Y., Feng, Y., Wu, G., Kang, J., Li, H.: An automatic evaluation method for retinal image registration based on similar vessel structure matching. Med. Biol. Eng. Compu. 58(1), 117–129 (2019). https://doi.org/10.1007/s11517-019-02080-0
Wen, L., Mei, Y., Yurong, G., et al.: Application of non-dilated fundus photography in screening diabetic retinopathy. Chinese Community Health Care 7, 133–134 (2018)
Wenxuan, X., Jianxia, L.: An improved U-NET method for retinal vascular segmentation. Elect. Des. Eng. 20, 165–168 (2021)
Peng, L., Dongning, L.: Improvement of sub-pixel edge detection method in medical image. Elect. Tech. Softw. Eng. 6, 214–216 (2020)
Wenxuan, X., Jianxia, L., Ran, L., et al.: An improved u-shaped network method for retinal segmentation. Acta Optica Sinica 12(40), 1–11 (2020)
Wenxian, Z., Yue, M., Ding, Y., et al.: An overview of semantic segmentation based on deep learning. Modern Computer 21, 115–122 (2021)
Xin, Z., Qingan, Y., Jianjin, Z., et al.: A Review of Image semantic segmentation methods based on full convolutional neural network. Comput. Eng. Appl. 58(08), 45–57 (2022)
Lin, Z., Zheng, Q., Liang, Y., et al.: Medical image segmentation method based on inner roll U-NET model. Computer Eng. (2021). https://doi.org/10.19678/j.issn.1000-3428.0062023.)
Qian, Z., Shenxin, T., Shun, H., et al.: An improved SURf-RANSAC image matching algorithm. Comput. Eng. Des. 42(10), 2902–2909 (2021)
Hernandez-Matas, C.: Retinal image registration under the assumption of a spherical eye. Comput. Med. Imaging Graph. 55, 95–105 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Hang, Y., Zhang, Q., Qiu, J. (2023). Fundus Image Registration Based on Improved Feature Description. In: You, P., Li, H., Chen, Z. (eds) Proceedings of International Conference on Image, Vision and Intelligent Systems 2022 (ICIVIS 2022). ICIVIS 2022. Lecture Notes in Electrical Engineering, vol 1019. Springer, Singapore. https://doi.org/10.1007/978-981-99-0923-0_8
Download citation
DOI: https://doi.org/10.1007/978-981-99-0923-0_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-0922-3
Online ISBN: 978-981-99-0923-0
eBook Packages: EngineeringEngineering (R0)