Hiperspektral Görüntüler için Yüksek Boyutlu Model Gösterilimi Kullanarak Seyrek Kodlama Sözlüklerinin İyileştirilmesi

Abstract

Hiperspektral görüntüleme, zengin uzamsal ve izgesel detayları sayesinde uzaktan algılama, biyomedikal mühendisliği ve kalite kontrol gibi alanlarda yaygın olarak kullanılmaktadır. Ancak, hiperspektral görüntülerin yüksek boyutluluğu ve büyük veri hacmi, verimli işleme ve sınıflandırma açısından önemli zorluklar oluşturmaktadır. Bu zorlukları aşmak için seyrek kodlama tabanlı teknikler yaygın olarak kullanılmaktadır. Bu nedenle, seyrek kodlama tabanlı yöntemlerin etkinliğini artırmak için uygun bir sözlük oluşturulmalıdır. Bu çalışma, seyrek kodlama tabanlı sınıflandırmayı iyileştirmek amacıyla, Yüksek Boyutlu Model Gösterilimi adı verilen etkili bir gürültü giderme ve dekorelasyon tekniğini kullanan bir sözlük iyileştirme yöntemi önermektedir. Bu teknik, üç boyutlu hiperspektral veriyi yönetilebilir bileşenlere ayırarak gürültüyü ve korelasyonları etkili bir şekilde azaltmaktadır. Daha sonra, incelenen hiperspektral verinin rastgele spektral sinyalleri kullanılarak iyileştirilmiş bir sözlük oluşturulmaktadır. Seyrek kodlama tabanlı sınıflandırıcı, bu iyileştirilmiş sözlüğü kullanarak sınıflandırma doğruluğunu artırmaktadır. Yaygın olarak kullanılan hiperspektral veri kümeleri üzerinde gerçekleştirilen deneysel sonuçlar, önerilen yöntemin sınıflandırma doğruluğunu önemli ölçüde artırdığını göstermektedir. Bu yöntem, Yüksek Boyutlu Model Temsili yönteminin gürültü giderme ve ilintisizleştirme avantajlarından yararlanarak iyileştirilmiş bir sözlük üretmekte ve hiperspektral görüntü sınıflandırması için sağlam ve verimli bir çözüm sunmaktadır.

Keywords

• Sınıflandırma
• Sözlük İyileştirme
• Yüksek Boyutlu Model Gösterilimi
• Hiperspektral Görüntüleme
• Makine Öğrenmesi
• Optimizasyon
• Seyrek Kodlama

Refining Sparse Coding Dictionaries Using High Dimensional Model Representation for Hyperspectral Imagery

Abstract

Hyperspectral imaging, known for its rich spectral and spatial details, finds applications in remote sensing, biomedical engineering, and quality control. Nonetheless, the high dimensionality and large data volume of hyperspectral images create substantial challenges in efficient processing and classification. Sparse coding-based techniques are widely employed to tackle these challenges. Therefore, an appropriate dictionary should be constructed to improve the efficacy of the sparse coding-based methods. This study introduces a dictionary refinement method that enhances sparse coding-based classification by exploiting an efficient denoising and decorrelation technique named High Dimensional Model Representation. This technique decomposes the 3-D hyperspectral data into manageable components, effectively reducing noise and correlations. Then, a refined dictionary is acquired by using random spectral signals of the hyperspectral data under consideration. The sparse coding-based classifier adopting the refined dictionary is exploited to improve the classification accuracy. Experimental results on widely used HS datasets show that the proposed method significantly boosts classification accuracy. This method leverages the benefits of denoising and decorrelation of the High Dimensional Model Representation method to generate a refined dictionary and provide a robust and efficient solution for hyperspectral image classification.

Keywords

• Classification
• Dictionary Refinement
• High Dimensional Model Representation
• Hyperspectral Imagery
• Machine Learning
• Optimization
• Sparse Coding

References

1. [1] Bhargava, A., Sachdeva, A., Sharma, K., Alsharif, M. H., Uthansakul, P., & Uthansakul, M. 2024. Hyperspectral imaging and its applications: A review. Heliyon, 10(12).
2. [2] Sun, D. W., Pu, H., & Yu, J. 2024. Applications of hyperspectral imaging technology in the food industry. Nature Reviews Electrical Engineering, 1(4), pp. 251-263.
3. [3] Polak, A., Kelman, T., Murray, P., Marshall, S., Stothard, D. J., Eastaugh, N., & Eastaugh, F. 2017. Hyperspectral imaging combined with data classification techniques as an aid for artwork authentication. Journal of Cultural Heritage, 26, pp. 1-11.
4. [4] Wilczyński, S., Koprowski, R., Marmion, M., Duda, P., & Błońska-Fajfrowska, B. 2016. The use of hyperspectral imaging in the VNIR (400–1000 nm) and SWIR range (1000–2500 nm) for detecting counterfeit drugs with identical API composition. Talanta, 160, pp. 1-8.
5. [5] Karim, S., Qadir, A., Farooq, U., Shakir, M., & Laghari, A. A. 2023. Hyperspectral imaging: a review and trends towards medical imaging. Current Medical Imaging Reviews, 19(5), pp. 417-427.
6. [6] Qian, S. E. 2022. Overview of hyperspectral imaging remote sensing from satellites. Advances in Hyperspectral Image Processing Techniques, pp. 41-66.
7. [7] Rasti, B., Hong, D., Hang, R., Ghamisi, P., Kang, X., Chanussot, J., & Benediktsson, J. A. 2020. Feature extraction for hyperspectral imagery: The evolution from shallow to deep: Overview and toolbox. IEEE Geoscience and Remote Sensing Magazine, 8(4), pp. 60-88.
8. [8] Tarabalka, Y., Fauvel, M., Chanussot, J., & Benediktsson, J. A. 2010. SVM-and MRF-based method for accurate classification of hyperspectral images. IEEE Geoscience and Remote Sensing Letters, 7(4), pp. 736-740.

9. [9] Huang, K., Li, S., Kang, X., & Fang, L. 2016. Spectral–spatial hyperspectral image classification based on KNN. Sensing and Imaging, 17, pp. 1-13.
10. [10] Zhang, Y., Cao, G., Li, X., & Wang, B. 2018. Cascaded random forest for hyperspectral image classification. IEEE journal of selected topics in applied earth observations and remote sensing, 11(4), pp. 1082-1094.
11. [11] Bera, S., Shrivastava, V. K., & Satapathy, S. C. 2022. Advances in Hyperspectral Image Classification Based on Convolutional Neural Networks: A Review. CMES-Computer Modeling in Engineering & Sciences, 133(2).
12. [12] Khan, A., Vibhute, A. D., Mali, S., & Patil, C. H. 2022. A systematic review on hyperspectral imaging technology with a machine and deep learning methodology for agricultural applications. Ecological Informatics, 69, 101678.
13. [13] Jaiswal, G., Sharma, A., & Yadav, S. K. 2021. Critical insights into modern hyperspectral image applications through deep learning. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 11(6), e1426.
14. [14] Peng, J., Sun, W., Li, H. C., Li, W., Meng, X., Ge, C., & Du, Q. 2021. Low-rank and sparse representation for hyperspectral image processing: A review. IEEE Geoscience and Remote Sensing Magazine, 10(1), pp. 10-43.
15. [15] Bodrito, T., Zouaoui, A., Chanussot, J., & Mairal, J. 2021. A trainable spectral-spatial sparse coding model for hyperspectral image restoration. Advances in Neural Information Processing Systems, 34, pp. 5430-5442.
16. [16] Wang, M., Hong, D., Han, Z., Li, J., Yao, J., Gao, L., Zhang, B. & Chanussot, J. 2023. Tensor decompositions for hyperspectral data processing in remote sensing: A comprehensive review. IEEE Geoscience and Remote Sensing Magazine, 11(1), pp. 26-72.
17. [17] Yang, L., Zhou, J., Jing, J., Wei, L., Li, Y., He, X., ... & Nie, B. 2022. Compression of hyperspectral images based on Tucker decomposition and CP decomposition. Journal of the Optical Society of America A, 39(10), pp. 1815-1822.
18. [18] Tuna, S., Korkmaz Özay, E., Tunga, B., Gürvit, E., & Tunga, M. A. 2022. An efficient feature extraction approach for hyperspectral images using Wavelet High Dimensional Model Representation. International Journal of Remote Sensing, 43(19-24), pp. 6899-6920.
19. [19] Şen, M. E., & Tuna, S. 2025. A new feature extraction scheme based on support optimization in Enhanced Multivariance Products Representation for Hyperspectral Imagery. Journal of the Franklin Institute, 362(2), 107464.
20. [20] Taşkın, G., Kaya, H., & Bruzzone, L. 2017. Feature selection based on high dimensional model representation for hyperspectral images. IEEE Transactions on Image Processing, 26(6), pp. 2918-2928.
21. [21] Tuna, S., Töreyin, B. U., Demiralp, M., Ren, J., Zhao, H., & Marshall, S. 2020. Iterative enhanced multivariance products representation for effective compression of hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 59(11), pp. 9569-9584.
22. [22] Xue, Zhaohui, et al. 2017. Discriminative sparse representation for hyperspectral image classification: A semi-supervised perspective. Remote Sensing 9(4), pp. 386.
23. [23] Huang, S., Zhang, H., & Pižurica, A. 2017. A robust sparse representation model for hyperspectral image classification. Sensors, 17(9), 2087.
24. [24] Tao, W., Liu, N., Chen, Y., Su, J., Xiao, H., & Li, X. 2023. Research on Denoising Methods for Hyperspectral Images Based on Low-Rank Theory and Sparse Representation. IEEE International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD), pp. 1-5
25. [25] Zhuang, L., Gao, L., Zhang, B., Fu, X., & Bioucas-Dias, J. M. 2020. Hyperspectral image denoising and anomaly detection based on low-rank and sparse representations. IEEE Transactions on Geoscience and Remote Sensing, 60, pp.1-17.
26. [26] Ülkü, İ., & Töreyin, B. U. 2015. Sparse representations for online-learning-based hyperspectral image compression. Applied optics, 54(29), pp. 8625-8631.
27. [27] Zhang, Z., Xu, Y., Yang, J., Li, X., & Zhang, D. 2015. A survey of sparse representation: algorithms and applications. IEEE Access, 3, pp. 490-530.
28. [28] Li, C., Ma, Y., Mei, X., Liu, C., & Ma, J. 2016. Hyperspectral image classification with robust sparse representation. IEEE Geoscience and Remote Sensing Letters, 13(5), pp. 641-645.
29. [29] Rabitz, H., & Aliş, Ö. F. 1999. General foundations of high‐dimensional model representations. Journal of Mathematical Chemistry, 25(2), pp. 197-233.
30. [30] Tuna, S., Tunga, B., Baykara, N. A., & Demiralp, M. 2009. Fluctuation free matrix representation based univariate integration in hybrid high dimensional model representation (HHDMR) over plain and factorized HDMR. WSEAS Transactions on Mathematics, 8(5), pp. 225-230.
31. [31] Arar, M. E., & Sedef, H. 2023. An efficient lung sound classification technique based on MFCC and HDMR. Signal, Image and Video Processing, 17(8), pp. 4385-4394.
32. [32] Wang, J., Kwon, S., & Shim, B. 2012. Generalized orthogonal matching pursuit. IEEE Transactions on signal processing, 60(12), pp. 6202-6216.
33. [33] Dai, W., & Milenkovic, O. 2009. Subspace pursuit for compressive sensing signal reconstruction. IEEE transactions on Information Theory, 55(5), pp. 2230-2249.
34. [34] Chen, Y., Nasrabadi, N. M., & Tran, T. D. 2011. Hyperspectral image classification using dictionary-based sparse representation. IEEE transactions on geoscience and remote sensing, 49(10), pp. 3973-3985.
35. [35] Davenport, M. A., & Wakin, M. B. 2010. Analysis of orthogonal matching pursuit using the restricted isometry property. IEEE Transactions on Information Theory, 56(9), pp. 4395-4401.