Abstract
Compressed sensing (CS) theory enables the reconstruction of spectral images (SI) using a lower number of measurements than the traditional Shannon-Nyquist sampling approach, through compressive spectral imaging (CSI) systems. These CSI systems rely on a dispersive-based optical setup coupled to one or more coded-apertures to capture and compress a spectral scene simultaneously. Afterward, the reconstruction of the underlying scene is obtained through computational algorithms. Then, processing tasks like classification, object detection, or segmentation are performed over the reconstructed images. However, this reconstruction process is computationally expensive, which introduces a time overhead for these tasks. In this paper, spectral classification is directly performed over compressed measurements acquired through an optical architecture following the CS framework. An end-to-end method to optimize both coded-apertures and deep learning model parameters is proposed. This approach has been applied to the grading of Tahiti lime (Citrus latifolia), but can be used for different agricultural materials. In this specific case, the classification accuracy reached 99%. In addition, for the purpose of comparison, our experiments improved up to 7% in classification accuracy over a testing database when the coded-apertures were optimized.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Orange Export S.A.S. www.orange-export.com.
References
Nandhini, A., Hemalatha, S., Radha, R., et al.: Web enabled plant disease detection system for agricultural applications using WMSN. Wirel. Person. Commun. 102, 725–740 (2018)
Draganić, A., Orović, I., Stanković, S., Zhang, X., Wang, X.: Compressive sensing approach in the table grape cold chain logistics. In: 2017 6th Mediterranean Conference on Embedded Computing (MECO), pp. 1–4 (2017)
Yang, Y., Qin, X., Ruan, S., Tian, D.: A new compressed sensing model based on median filter with application to reconstruct brain MR images. In: 2018 IEEE 3rd International Conference on Signal and Image Processing (ICSIP), pp. 116–120 (2018)
Mirrashid, A., Beheshti, A.A.: Compressed remote sensing by using deep learning. In: 2018 9th International Symposium on Telecommunications (IST), pp. 549–552 (2018)
Zhang, Y., Orfeo, D., Huston, D., Xia, T.: Compressive sensing based software defined GPR for subsurface imaging. In: 2021 IEEE Radar Conference (RadarConf21), pp. 1–6 (2021)
TE-Cooled Fluorescence Spectrometer|Edmund Optics. https://www.edmundoptics.com/p/te-cooled-fluorescence-spectrometer/28866/
Donoho, D.L.: Compressed sensing. IEEE Trans. Inf. Theory 52(4), 1289–1306 (2006)
Duarte, M.F., et al.: Single-pixel imaging via compressive sampling. IEEE Signal Process. Mag. 25(2), 83–91 (2008)
Gehm, M.E., John, R., Brady, D.J., Willett, R.M., Schulz, T.J.: Single-shot compressive spectral imaging with a dual-disperser architecture. Opt. Exp. 15(21), 14013 (2007)
Wagadarikar, A., John, R., Willett, B., Brady, D.: Single disperser design for coded aperture snapshot spectral imaging. Appl. Opt. 47(10) (2008)
Lin, X., Liu, Y., Wu, J., Dai, Q.: Spatial-spectral encoded compressive hyperspectral imaging. ACM Trans. Graph. 33(6) (2014)
Wang, L., Xiong, Z., Shi, G., Wu, F., Zeng, W.: Adaptive nonlocal sparse representation for dual-camera compressive hyperspectral imaging. IEEE Trans. Pattern Anal. Mach. Intell. 39(10), 2104–2111 (2017)
Xingyi, C., Yujie, Z., Rui, O.: Block sparse signals recovery algorithm for distributed compressed sensing reconstruction. J. Inf. Process. Syst. 15(2), 410–421 (2019)
Figueiredo, M.A., Nowak, R.D., Wright, S.J.: Gradient projection for sparse reconstruction: application to compressed sensing and other inverse problems. IEEE J. Sel. Top. Signal Process. 1(4), 586–597 (2007)
Tropp, J.A., Gilbert, A.C.: Signal recovery from random measurements via orthogonal matching pursuit. IEEE Trans. Inf. Theory 53(12), 4655–4666 (2007)
Blumensath, T., Davies, M.E.: Iterative hard thresholding for compressed sensing. Appl. Comput. Harmon. Anal. 27(3), 265–274 (2009)
Zhao, C., Zhang, J., Wang, R., Gao, W.: Cream: CNN-regularized ADMM framework for compressive-sensed image reconstruction. IEEE Access 6, 76 838–76 853 (2018)
Davenport, M.A., Boufounos, P.T., Wakin, M.B., Baraniuk, R.G.: Signal processing with compressive measurements. IEEE J. Sel. Top. Signal Process. 4(2), 445–460 (2010)
Kulkarni, K., Lohit, S., Turaga, P., Kerviche, R., Ashok, A.: ReconNet: Non-iterative reconstruction of images from compressively sensed measurements. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, pp. 449–458 (2016)
LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010). http://yann.lecun.com/exdb/mnist/
Bacca, J., Galvis, L., Arguello, H.: Coupled deep learning coded aperture design for compressive image classification. Opt. Express 28(6), 8528–8540. http://www.opticsexpress.org/abstract.cfm?URI=oe-28-6-8528
Krizhevsky, A., Nair, V., Hinton, G.: Cifar-10 (Canadian Institute for Advanced Research). [Online]. http://www.cs.toronto.edu/~kriz/cifar.html
Galvis, L., Mojica, E., Arguello, H., Arce, G.R.: Shifting colored coded aperture design for spectral imaging. Appl. Opt. 58(7), B28–B38 (2019). http://www.osapublishing.org/ao/abstract.cfm?URI=ao-58-7-B28
Sobral, A., Vacavant, A.: A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos. Comput. Vis. Image Underst. 122, 4–21 (2014). https://www.sciencedirect.com/science/article/pii/S1077314213002361
Neubert, P., Protzel, P.: Compact watershed and preemptive SLIC: on improving trade-offs of superpixel segmentation algorithms. In: 2014 22nd International Conference on Pattern Recognition, pp. 996–1001 (2014)
Higham, C.F., Murray-Smith, R., Padgett, M.J., Edgar, M.P.: Deep learning for real-time single-pixel video. Sci. Rep. 8(1), 2369 (2018). https://doi.org/10.1038/s41598-018-20521-y
Buda, M., Maki, A., Mazurowski, M.A.: A systematic study of the class imbalance problem in convolutional neural networks. Neural Netw. 106, 249–259 (2018). https://www.sciencedirect.com/science/article/pii/S0893608018302107
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 8024–8035. Curran Associates Inc. (2019), http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J., Bottou, C.L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25. Curran Associates Inc. (2012). https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf
He, K., Zhang, K., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR, abs/1512.03385 (2015) http://arxiv.org/abs/1512.03385
Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. CoRR, abs/1708.07747 (2017). http://arxiv.org/abs/1708.07747
Acknowledgment
The authors acknowledge the support by the Sistema general de regalías de CTeI - Colombia (BPIN 2020000100415, “Desarrollo de un sistema óptico - computacional para estimar el contenido de carbono orgánico de suelos agrícolas a través de imágenes espectrales e inteligencia artificial en cultivos cítricos de Santander." with UIS code 8933). Laura Galvis was supported by the postdoctoral program of the VIE-UIS.
We also acknowledge Orange Export S.A.S. for supplying the classified lime samples studied in this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Silva-Maldonado, M., Galvis, L., Arguello, H. (2022). End-to-End Compressive Spectral Classification: A Deep Learning Approach Applied to the Grading of Tahiti Lime. In: Narváez, F.R., Proaño, J., Morillo, P., Vallejo, D., González Montoya, D., Díaz, G.M. (eds) Smart Technologies, Systems and Applications. SmartTech-IC 2021. Communications in Computer and Information Science, vol 1532. Springer, Cham. https://doi.org/10.1007/978-3-030-99170-8_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-99170-8_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-99169-2
Online ISBN: 978-3-030-99170-8
eBook Packages: Computer ScienceComputer Science (R0)