Abstract
Multi-feature fusion is a useful way to improve the classification of hyperspectral image (HSI). But the multi-feature fusion is usually at the decision level of classifier, which causes less link between features or poor extensibility of feature. In this paper, we propose a multi-feature fusion based deep forest method for HSI classification, named mfdForest. In mfdForest, the morphological features, saliency features, and edge features are extracted, then the three deep multi-grained scanning branches in dgcForest (one of improved deep forest) are used to extract and fuse the extracted features deeply, and the fused features are sent into cascade forest in dgcForest for classification. Experimental results indicate that the proposed framework consumes less training time and has better performance on two HSI data sets.
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
Tang, Y., et al.: Apple bruise grading using piecewise nonlinear curve fitting for hyperspectral imaging data. IEEE Access 8, 147494–147506 (2020)
Shimoni, M., Haelterman, R., Perneel, C.: Hypersectral imaging for military and security applications: combining myriad processing and sensing techniques. IEEE Geosci. Remote Sens. Mag. 7(2), 101–117 (2019)
Pike, R., Lu, G., Wang, D., Chen, Z.G., Fei, B.: A Minimum spanning forest-based method for noninvasive cancer detection with hyperspectral imaging. IEEE Trans. Biomed. Eng. 63(3), 653–663 (2016)
Zhang, L., Zhang, L., Du, B.: Deep learning for remote sensing data: a technical tutorial on the state of the art. IEEE Geosci. Remote Sens. 4(2), 22–40 (2016)
Yang, C., Li, Y., Peng, B., Cheng Y., Tong, L.: Road material information extraction based on multi-feature fusion of remote sensing image. In: 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). pp. 3943–3946, IEEE (2019)
Lu, J., Ma, C., Zhou, Y., Luo, M., Zhang, K.: Multi-feature fusion for enhancing image similarity learning. IEEE Access 7, 167547–167556 (2019)
Zhao, S., Nie, W., Zhang, B.: Multi-feature fusion using collaborative residual for hyperspectral palmprint recognition. In: 2018 IEEE 4th International Conference on Computer and Communications (ICCC), Chengdu, China, pp. 1402–1406, IEEE (2018)
He, M., Li, B., Chen, H.: Multi-scale 3D deep convolutional neural network for hyperspectral image classification. In: 2017 IEEE International Conference on Image Processing (ICIP). pp. 3904–3908. IEEE (2018)
Gu, Y., Liu, T., Jia, X., et al.: Nonlinear multiple kernel learning with multiple-structure-element extended morphological profiles for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 54(6), 3235–3247 (2016)
Jia, S., Lin, Z., Deng, B., et al.: Cascade superpixel regularized gabor feature fusion for hyperspectral image classification. IEEE Trans. Neural Netw. Learn. Syst. 31(5), 1638–1652 (2019)
Jia, S., Deng, B., Zhu, J., et al.: Local binary pattern-based hyperspectral image classification with superpixel guidance. IEEE Trans. Geosci. Remote Sens. 56(2), 749–759 (2017)
He, Z., Li, J., Liu, K., et al.: Kernel low-rank multitask learning in variational mode decomposition domain for multi-hyperspectral classification. IEEE Trans. Geosci. Remote Sens. 56(7), 4193–4208 (2018)
Li, F., Wang, J., Lan, R., et al.: Hyperspectral image classification using multi-feature fusion. Opt. Laser Technol. 110, 176–183 (2019)
Zhang, C., Han, M., Xu, M.: Multi-feature classification of hyperspectral image via probabilistic SVM and guided filter. In: 2018 International Joint Conference on Neural Networks (IJCNN). pp. 1–7. IEEE (2018)
Liu, X., Yin, X., Cai, Y., et al.: Visual saliency-based extended morphological profiles for unsupervised feature learning of hyperspectral images. IEEE Geosci. Remote Sens. Lett. 17(11), 1963–1967 (2019)
Zhou, Z., Feng, J.: Deep forest: towards an alternative to deep neural networks. In: 2017 International Joint Conference on Artificial Intelligence Organization (IGCAI). pp. 3553–3559
Yin, X., Wang, R. et al.: Deep forest-based classification of hyperspectral images. In: Chinese Control Conference, pp. 10367–10372, IEEE (2018)
Liu, X., Wang, R., Cai, Z., et al.: Deep multigrained cascade forest for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 57(10), 8169–8183 (2019). https://doi.org/10.1109/TGRS.2019.2918587
Luo, H., Tang, Y.Y., Yang, X., et al.: Autoencoder with extended morphological profile for hyperspectral image classification. In: 2017 IEEE International Conference on Cybernetics (CYBCONF). pp. 293–296. IEEE (2017)
Zhang, J., Sclaroff, S.: Saliency detection: a Boolean map approach. In: 2013 IEEE International Conference on Computer Vision (ICCV). pp. 153–160. IEEE (2013)
Guo, G., Neagu, D., Huang, X., Bi, Y.: An effective combination of multiple classifiers for toxicity prediction. In: Wang, L., Jiao, L., Shi, G., Li, X., Liu, J. (eds.) Fuzzy Systems and Knowledge Discovery, pp. 481–490. Springer Berlin Heidelberg, Berlin, Heidelberg (2006). https://doi.org/10.1007/11881599_56
Zhu, L., Chen, Y., Ghamisi, P., Benediktsson, J.A.: Generative adversarial networks for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 56(9), 5046–5063 (2018)
Zhong, Z., Li, J., Luo, Z., Chapman, M.: Spectral-spatial residual network for hyperspectral image classification: A 3-D deep learning framework. IEEE Trans. Geosci. Remote Sens. 56(2), 847–858 (2018)
Acknowledgement
This work was supported by National Nature Science Foundation of China (Grant Nos. 61973285, 62076226, 61873249).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, X., Mohammad, M.Z., Zhang, C., Gong, X., Cai, Z. (2022). Multi-feature Fusion Based Deep Forest for Hyperspectral Image Classification. In: Pan, L., Cui, Z., Cai, J., Li, L. (eds) Bio-Inspired Computing: Theories and Applications. BIC-TA 2021. Communications in Computer and Information Science, vol 1566. Springer, Singapore. https://doi.org/10.1007/978-981-19-1253-5_22
Download citation
DOI: https://doi.org/10.1007/978-981-19-1253-5_22
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-1252-8
Online ISBN: 978-981-19-1253-5
eBook Packages: Computer ScienceComputer Science (R0)