Abstract
The term super-resolution (SR) refers to the applications of enhancing the resolution of an image from low-resolution (LR) to high-resolution (HR). However, for compression purposes, we can intentionally down-sample the image during encoding and then up-sample it with a super-resolution technique at the decoder. Integrating this processing in a compression scheme will allow us to perform improvements through: (1) reducing the loss of information by producing a controlled down-sampling, which preserves the relevant information; (2) increasing the information compensation via a super-resolution technique that enhances the high-frequency components of the reconstructed image. In this paper, we propose a lossy hyperspectral image compression scheme. It combines a 3D wavelet transform with a wavelet learned-based super-resolution technique. The 3D wavelet transform introduces a down-sampling on the hyperspectral image to generate low-resolution (LR) images. This LR sequence is then lossy compressed by the 3D SPIHT encoder at the selected bitrate and produces the bitstream to save or transmit. At the decoder, we do the reconstruction by inverting the 3D SPIHT, which provides us with the approximate coefficients (AC) and corresponding detail coefficients (DC) of the LR image across all sub-bands. Then, we develop a wavelet learning-based SR technique that learns the mapping between the wavelet coefficients using a convolutional neural network (CNN). We use this mapping to invert the down-sampling process and predict the missing detail coefficients. Finally, The LR image and the predicted details coefficients (DC) are used to generate the high-resolution image by applying the inverse 3D wavelet transform. Therefore, we have used the down-sampling and the super-resolution technique as a mechanism to control the compression ratio (CR) and optimize the overall quality of the reconstructed image. The performance of the proposed compression scheme has been evaluated on AVIRIS hyperspectral images and compared with the main existing algorithms. Experimental results show that the proposed algorithm provides a promising performance and can generate high-quality images.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abd El-Samie FE, Hadhoud MM, El-Khamy SE (2019) Image super-resolution and applications. CRC Press, USA
Aggarwal CC (2018) Neural networks and deep learning. Springer, USA
Agrawal N, Verma K (2020) Dimensionality reduction on hyperspectral data set. In: First international conference on power, control and computing technologies, Raipur, Chhatisgarh, India, 2020
Barreto D, Alvarez LD, Molina R et al (2007) Region-based super-resolution for compression. Multidim Syst Sign Process 18:59–81. https://doi.org/10.1007/s11045-007-0019-y
Báscones D, González C, Mozos D (2018) Hyperspectral image compression using vector quantization, PCA and JPEG2000. Remote Sens 10(6):907. https://doi.org/10.3390/rs10060907
Bull DR (2014) Filter banks and wavelet compression. In: Bull DR (ed) Communicating pictures: A course in image and video coding. Academic Press, USA
Cao S, Wu C, Krähenbühl P (2020) Lossless image compression through super-resolution. arXiv:2004.02872
Cherifi M, Lahdir M, Ameur S (2019) Meteosat image sequence coding in the Radon field. Optik Int J Light Elect Opt 182:1228–1243. https://doi.org/10.1016/j.ijleo.2019.02.015
Dong C, Loy CC, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution. In: European conference on computer vision, Zurich, Switzerland, p 2014
Du Q, Fowler JE (2007) Hyperspectral image compression using JPEG2000 and principal component analysis. IEEE Geosci Remote Sens Lett 4:201–205. https://doi.org/10.1109/LGRS.2006.888109
Dua Y, Kumar V, Singh RS (2020) Comprehensive review of hyperspectral image compression algorithms. Opt Eng 59(9). https://doi.org/10.1117/1.OE.59.9.090902
Egho C, Vladimirova T (2014) Adaptive hyperspectral image compression using the KLT and integer KLT algorithms. NASA/ESA Conf Adapt Hardw Sys (AHS), 112–119. https://doi.org/10.1109/AHS.2014.6880166
Fan Z, Hu X, Chen C et al (2020) Facial image super-resolution guided by adaptive geometric features. J Wireless Com Network, pp 149. https://doi.org/10.1186/s13638-020-01760-y
Glaister J, Chan C, Frankovich M, Tang A, Wang A (2011) Hybrid video compression using selective keyframe identification and Patch-Based Super-Resolution. IEEE Int Symp Multimedia, pp 105–110
Golian M et al (2020) Prediction of tunnelling impact on flow rates of adjacent extraction water wells. Q J Eng Geol Hydrogeol 53(2):236. https://doi.org/10.1144/qjegh2019-055
Hassaballah M, Awad AI (2020) Deep learning in computer vision: principles and applications. CRC Press, USA
Hore A, Ziou DJ (2010) Image quality metrics: PSNR vs. SSIM. In: 20Th international conference on pattern recognition, Istanbul, Turkey, p 2010
Howard AG et al (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861
Javadinejad S et al (2018) Embankments. In: Bobrowsky P, Marker B (eds) Encyclopedia of engineering geology. Encyclopedia of earth sciences series. Springer, Cham
Jiwon K, Kwon Lee J, Mu Lee K (2016) Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA
Kappeler A, Yoo S, Dai Q, Katsaggelos AK (2016) Super-resolution of compressed videos using convolutional neural networks. In: 2016 IEEE international conference on image processing (ICIP). https://doi.org/10.1109/ICIP.2016.7532538, vol 2016, pp 1150–1154
Khan S, Rahmani H, Ali Shah SA, Bennamoun M, Medioni G, Dickinson S (2018) A guide to convolutional neural networks for computer vision. Morgan and Claypool, USA
Kuma N, Kumar Rai N, Sethi N (2012) Learning to predict super-resolution wavelet coefficients. In: Proceedings of the 21st international conference on pattern recognition, Tsukuba, Japan, p 2012
Li R, Pan Z, Wang Y (2019) The linear prediction vector quantization for hyperspectral image compression. Multimedia Tools Appl 78:11701–11718. https://doi.org/10.1007/s11042-018-6724-8
Müller MU, Ekhtiari N, Almeida RM, Rieke C (2020) Super-resolution of multispectral satellite images using convolutional neural networks. ISPRS, Ann Photogramm Remote Sens Spatial Inf Sci: 33–40. https://doi.org/10.5194/isprs-annals-V-1-2020-33-2020
Ouahioune M, Akrour L, Lahdir M, Ameur S (2012) Aviris hyperspectral images compression using 3D SPIHT algorithm. IOSR J Eng 2:31–36. https://doi.org/10.9790/3021-021023136
Pandey PR et al (2020) Hyperspectral remote sensing: theory and applications. Elsevier, USA
Pirnazar M, et al. (2018) The evaluation of the usage of the fuzzy algorithms in increasing the accuracy of the extracted land use maps. Int J Global Environ 17 (4):307–321. https://doi.org/10.1504/IJGENVI.2018.10013978
Pizzolante R, et al. (2011) Lossless compression of hyperspectral imagery. In: First international conference on data compression, communications and processing, Palinuro, Cilento Coast, Italy, p 2011
Pu R (2017) Hyperspectral remote sensing: fundamentals and practices. CRC Press, USA
Qiao W, Fang Z, Chang MF, Cong J (2019) An FPGA-based BWT accelerator for Bzip2 data compression. In: 2019 IEEE 27th annual international symposium on field-programmable custom computing machines (FCCM), San Diego, CA, USA, 2019
Salehi-Hafshejani et al (2019) Determination of the height of the vertical filter for heterogeneous earth dams with vertical clay core. Int J Hydrol Sci Technol 9 (3):221–235. https://doi.org/10.1504/IJHST.2019.102315
Shen H, Jiang Z, Pan WD (2018) Efficient lossless compression of multitemporal hyperspectral image data. J Imag 4(12):142. https://doi.org/10.3390/jimaging4120142
Sahito F, Zhiwen P, Ahmed J, Memon RA (2019) Wavelet-integrated deep networks for single image super-resolution. Electronics 8(5):553. https://doi.org/10.3390/electronics8050553
Tang X, Pearlman WA (2006) Three-dimensional wavelet-based compression of hyperspectral images. In: Motta G, Rizzo F, Storer A (eds) Hyperspectral data compression. Springer, USA
Xu K, Wan J, Wang L, He M, Nian Y (2016) Block-based KLT compression for multispectral images. International Journal of Wavelets. Multiresol Inf Process 14(4). https://doi.org/10.1142/S0219691316500296
Yadav RJ, Nagmode MS (2018) Compression of hyperspectral image using PCA–DCT technology. In: Saini H, Singh R, Reddy K (eds) Innovations in electronics and communication engineering. Lecture notes in networks and systems. Springer, USA
Yamashita K, Markov K (2020) Medical image enhancement using super resolution methods. In: Krzhizhanovskaya V et al. (eds) Computational science – ICCS 2020. ICCS 2020. Lecture Notes in Computer Science. Springer, Cham
Yan H, Lu H, Gao Q (2012) A BP-LZ77 compression algorithm based on BP network. In: Jin D, Lin S (eds) Advances in electronic engineering, communication and management. Lecture Notes in Electrical Engineering, vol 2. Springer, Berlin, p 2012
Yu H, Zhang H, Lei B, Wang C (2017) Hyperspectral image compressing using wavelet-based method. In: Proc. SPIE 10461, AOPC 2017: optical spectroscopy and imaging, Beijing, China, 2017
Zikiou N, Lahdir M, Helbert D (2019) Support vector regression-based 3D-wavelet texture learning for hyperspectral image compression. Vis Comput 36:1473–1490. https://doi.org/10.1007/s00371-019-01753-z
Zhao XJ, Jing YF (2013) The application of vector quantization algorithm in hyperspectral image compression. Adv Mater Res:1479–1483. https://doi.org/10.4028/www.scientific.net/AMR.756-759.1479
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest.
Additional information
Communicated by: H. Babaie
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ouahioune, M., Ameur, S. & Lahdir, M. Enhancing hyperspectral image compression using learning-based super-resolution technique. Earth Sci Inform 14, 1173–1183 (2021). https://doi.org/10.1007/s12145-021-00623-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-021-00623-4