The general similarity metric method is difficult to calculate the similarity of images under different resolutions, occlusion, and deformation. Therefore, this paper proposes a structured deep coupled metric learning framework (SDCML), which provides a solution for image matching under the above special interference. For the input image pairs, the structured region segmentation is performed to derive global and local sub-region images. After that, a stacked sparse auto-encoder network is used to implement deep feature extraction on these derived images. Then, the features with different dimensions of derived image pairs are transformed to coupled space through multi-supervised coupled mapping, and the similarity metric of feature pairs is completed in this space. Finally, all calculated similarities of derived image pairs are fused to obtain the final matching result. The effectiveness of the proposed method is verified by image matching experiments under non-ideal conditions; the optimal recognition rate was 91.98% on Yale-B dataset and 72.80% on Market1501 dataset, respectively.
This is a preview of subscription content, access via your institution.
Buy single article
Instant access to the full article PDF.
Price excludes VAT (USA)
Tax calculation will be finalised during checkout.
Shen, Y., Yan, Y., Wang, H.: Recent advances on supervised distance metric learning algorithms. Acta Autom. Sin. 40(12), 2673–2686 (2014)
Xiang, S., Nie, F., Zhang, C.: Learning a Mahalanobis distance metric for data clustering and classification. Pattern Recognit. 41(12), 3600–3612 (2008)
Chen, J.-Y., He, H.-H.: Density-based clustering algorithm for numerical and categorical data with mixed distance measure methods. Control Theory Appl. 32(8), 993–1002 (2015)
Dong, C., Loy, C.C., He, K., et al.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2016)
Noh, Y., Zhang, B., Lee, D.D.: Generative local metric learning for nearest neighbor classification. IEEE Trans. Pattern Anal. Mach. Intell. 40(1), 106–118 (2018)
Zou, G., Zhang, Y., Wang, K., et al.: An improved metric learning approach for degraded face recognition. Math. Probl. Eng. 2014, 1–10 (2014)
Jiang, J., Hu, R., Wang, Z., et al.: CDMMA: coupled discriminant multi-manifold analysis for matching low-resolution face images. Signal Process. 124, 162–172 (2016)
Ben, X., Meng, W., Yan, R., et al.: Kernel coupled distance metric learning for gait recognition and face recognition. Neurocomputing 120, 577–589 (2013)
Ben, X., Gong, C., Zhang, P., et al.: Coupled patch alignment for matching cross-view gaits. IEEE Trans. Image Process. 2019, 1–16 (2019)
You, X., Li, Q., Tao, D., et al.: Local metric learning for exemplar-based object detection. IEEE Trans. Circuits Syst. Video Technol. 24(8), 1265–1276 (2014)
Liong, V.E., Lu, J., Tan, Y.-P., et al.: Deep coupled metric learning for cross-modal matching. IEEE Trans. Multimed. 19(6), 1234–1244 (2017)
Yu, H.X., Wu, A., Zheng, W.S.: Cross-view asymmetric metric learning for unsupervised person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 994–1002 (2017)
Huang, S., Lu, J., Zhou, J., et al.: Nonlinear local metric learning for person re-identification. Comput. Sci. 1–10 (2015). https://arxiv.org/abs/1511.05169
Li, B., Chang, H., Shan, S.: Coupled metric learning for face recognition with degraded images. In: Asian Conference on Machine Learning, pp. 220–233. Springer (2009)
Li, B., Chang, H., Shan, S., et al.: Low-resolution face recognition via coupled locality preserving mappings. IEEE Signal Process. Lett. 17(1), 20–23 (2010)
Wang, K., Yan, T.: Kernel coupled metric learning and its application to gait recognition. Pattern Recognit. Artif. Intell. 26(2), 169–175 (2013)
Zhang, P., Ben, X., Jiang, W., et al.: Coupled marginal discriminant mappings for low-resolution face recognition. Optik 126(23), 4352–4357 (2015)
Lu, J., Hu, J., Tan, Y.P.: Discriminative deep metric learning for face and kinship verification. IEEE Trans. Image Process. 26(9), 4269–4282 (2017)
Le, Q.V., Ngiam, J., Coates, A. et al.: On optimization methods for deep learning. In: Proceedings of the 28th International Conference on International Conference on Machine Learning, pp. 265–272. Omnipress (2011)
Ng, A., et al.: Sparse Autoencoder, CS294A Lecture Notes 72, pp. 1–19 (2011)
Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cogn. Neurosci. 3(1), 71–86 (1991)
He, X., Niyogi, P.: Locality preserving projections. Adv. Neural Inf. Process. Syst. 16(16), 153–160 (2004)
Schölkopf, B., Smola, A., Müller, K.-R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 10(5), 1299–1319 (1998)
Cai, D., He, X., Han, J.: Spectral regression for dimensionality reduction, Tech. rep. (2007)
Funding was provided by Integration Fund of Shandong University of Technology and Zhangdian District (Grant No. 118228) and The National Natural Science Foundation of China (Grant No. 61601266).
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Fu, G., Zou, G., Gao, M. et al. Image matching based on a structured deep coupled metric learning framework. SIViP 16, 1649–1657 (2022). https://doi.org/10.1007/s11760-021-02120-z
- Structured region segmentation
- Deep sparse auto-encoder network
- Multi-supervised coupled mapping
- Non-ideal image matching