Classification of BPG-Based Lossy Compressed Noisy Images

Authors

  • Galina Proskura Department of Information-communication technologies named after O.O. Zelensky, National Aerospace University, "Kharkiv Aviation Institute", Kharkiv, Ukraine. https://orcid.org/0000-0001-8960-0421
  • Victoria Naumenko Department of Information-communication technologies named after O.O. Zelensky, National Aerospace University, "Kharkiv Aviation Institute", Kharkiv, Ukraine. https://orcid.org/0000-0002-5291-6032
  • Volodymyr Lukin Department of Information-communication technologies named after O.O. Zelensky, National Aerospace University, "Kharkiv Aviation Institute", Kharkiv, Ukraine. https://orcid.org/0000-0002-1443-9685

DOI:

https://doi.org/10.36023/ujrs.2024.11.3.266

Keywords:

image lossy compression, optimal operation point, BPG encoder, classification transform

Abstract

Acquired remote sensing images can be noisy. This fact has to be taken into account in their lossy compression and classification. In particular, a specific noise filtering effect is usually observed due to lossy compression and this can be positive for classification. Classification can be also influenced by methodology of classifier learning. In this paper, we consider peculiarities of lossy compression of three-channel noisy images by better portable graphics (BPG) encoder and their further classification. It is demonstrated that improvement of data classification accuracy is not observed if a given image is compressed in the neighborhood of optimal operation point (OOP) and the classifier training is performed for the noisy image. Performance of neural network based classifier is studied. As demonstrated, its training for compressed remote sensing data is able to provide certain benefits compared to training for noisy (uncompressed) data. Examples for Sentinel data used in simulations are offered.

References

Abramova V., Abramov S., Abramov K., Vozel B. (2024). Blind Evaluation of Noise Characteristics in Multichannel Images. Studies in Systems, Decision and Control. Cham: Springer, 507, 209-229. DOI 10.1007/978-3-031-43579-9_4

Aiazzi B., Alparone L., Baronti S., Lastri C., Selva M. (2012). Spectral distortion in lossy compression of hyperspectral data. Journal of Electrical Computer Engineering, Article ID 850637, 8. DOI: https://doi.org/10.1155/2012/850637.

Albalawi U., Mohanty S. P. and Kougianos E. (2016). Energy-Efficient Design of the Secure Better Portable Graphics Compression Architecture for Trusted Image Communication in the IoT. 2016 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), 302-307. DOI: 10.1109/ISVLSI.2016.21.

Al-Shaykh O. K. and Mersereau R. M. (1998). Lossy compression of noisy images. In IEEE Transactions on Image Processing, 7(12), 1641-1652. DOI: 10.1109/83.730376.

Bondžulić B., Stojanović N., Petrović V., Pavlović B., Miličević Z. (2021). Efficient Prediction of the First Just Noticeable Difference Point for JPEG Compressed Images. Acta Polytechnica Hungarica,18(8), 201-220. DOI:10.12700/APH.18.8.2021.8.11

Chang S. G., Yu B. and Vetterli M. (1997). Image denoising via lossy compression and wavelet thresholding. Proceedings of International Conference on Image Processing,1, 604-607. DOI: 10.1109/ICIP.1997.647985.

Chatterjee P. and Milanfar P. (2010). Is Denoising Dead? In IEEE Transactions on Image Processing, 19(4), 895-911. DOI: 10.1109/TIP.2009.2037087.

Chi M., Plaza A., Benediktsson J. A., Sun Z., Shen J., and Zhu Y. (2016). Big data for remote sensing: Challenges and opportunities. Proceedings of the IEEE, 104(11), 2207-2219. DOI: 10.1109/JPROC.2016.2598228.

Christophe E. (2011). Hyperspectral Data Compression Tradeoff. In: Prasad S., Bruce L., Chanussot J. (eds) Optical Remote Sensing. Augmented Vision and Reality. DOI:10.1007/978-3-642-14212-3_2.

Doss S., Pal S., Akila D., Jeyalaksshmi S., Jabeen T. N., and Suseendran G. (2020). Satellite image remote sensing for identifying aircraft using SPIHT and NSCT. IEEE Signal processing magazine, 7(5), 631-634.

Hussain A. J., Al-Fayadh A., and Radi N. (2018). Image compression techniques: A survey in lossless and lossy algorithms. Neurocomputing, 300: 44-69. DOI: 10.1016/j.neucom.2018.02.094

Kovalenko B., Lukin V., Naumenko V. and Krivenko S. (2021). Analysis of noisy image lossy compression by BPG using visual quality metrics. 2021 IEEE 3rd International Conference on Advanced Trends in Information Theory (ATIT), 20-25. DOI: 10.1109/ATIT54053.2021.9678575.

Khorram S., van der WieleFrank C. F., Koch F. H., Nelson S. A. C., Potts M.D. (2016). Future Trends in Remote Sensing. In: Principles of Applied Remote Sensing, 277–285.

Kryvenko S., Lukin V., Vozel B. (2024). Lossy Compression of Single-channel Noisy Images by Modern Coders. Remote Sensing, 16, 2093, 1-19. DOI: 10.3390/rs16122093

Li F., Krivenko S., and Lukin V. (2020). Adaptive two-step procedure of providing desired visual quality of compressed image. In Proceedings of the 2020 4th International Conference on Electronic Information Technology and Computer Engineering, 407-414. DOI: 10.1145/3443467.3443791.

Lukin V., Ponomarenko N., Zelensky A., Kurekin A., Lever K. (2008). Compression and classification of noisy multichannel remote sensing images. Proc. SPIE 7109, Image and Signal Processing for Remote Sensing XIV, 1-12. DOI: 10.1117/12.799497

Lukin V., Kovalenko B., Kryvenko S., Naumenko V., Vozel B. (2022). Prediction of Optimal Operation Point Existence and Its Parameters in BPG-Based Automatic Lossy Compression of Noisy Images. Current Overview on Science and Technology Research, 9, 1-36. DOI: 10.9734/bpi/costr/v9/4316A

Ma Y., Wu H., Wang L., Huang B., Ranjan R., Zomaya A., Jie W. (2015). Remote sensing big data computing: Challenges and opportunities. Future Generation Computer Systems, 51, 47-60. DOI: 10.1016/j.future.2014.10.029.

Makarichev V., Vasilyeva I., Lukin V., Vozel B., Shelestov A., Kussul N. (2021). Discrete Atomic Transform-Based Lossy Compression of Three-Channel Remote Sensing Images with Quality Control. Remote Sens, 14 (1), 125. DOI: 10.3390/rs14010125

Ponomarenko N., Lukin V., Astola J., and Egiazarian K. (2015). Analysis of HVS-metrics’ properties using color image database TID2013. In International Conference on Advanced Concepts for Intelligent Vision Systems, 613-624. DOI:10.1007/978-3-319-25903-1_53.

Proskura G., Vasilyeva I., Li F., Lukin V. (2020). Classification of Compressed Multichannel Images and Its Improvement. Proceedings of the 30th International Conference Radioelektronika, 62-67. DOI: 10.1109/radioelektronika49387.2020.9092371.

Sayood K. (2017) Introduction to data compression, San Francisco: Morgan Kaufmann, 768. ISBN: 978-0-12-415796-5

Selva E., Kountouris A. and Louet Y. (2021). K-Means Based Blind Noise Variance Estimation. 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), 1-7. DOI: 10.1109/VTC2021-Spring51267.2021.9449072.

Tao D., Di S., Liang X., Chen Z., and Cappello F. (2018). Fixed-PSNR Lossy Compression for Scientific Data. 2018 IEEE International Conference on Cluster Computing (CLUSTER), 314-318. DOI: 10.48550/arXiv.1805.07384.

Taubman D.S., Marcellin M.W. (2013). JPEG2000: image compression fundamentals, standards, and practice.

Vasilyeva I., Lukin V., Kharchenko V., Nereta A. (2023). Combined Processing of Satellite and UAV Data to Increase the Classification Reliability. Proceedings of the 4th International Workshop on Intelligent Information Technologies & Systems of Information Security. 539-552. https://ceur-ws.org/Vol-3373/paper37.pdf.

Yee D., Soltaninejad S., Hazarika D., Mbuyi G., Barnwal R. and Basu A. (2017). Medical image compression based on region of interest using better portable graphics (BPG). 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 216-221. DOI: 10.1109/SMC.2017.8122605.

Zemliachenko A., Abramov S., Lukin V., Vozel B., Chehdi K. (2015). Lossy Compression of Noisy Remote Sensing Images with Prediction of Optimal Operation Point Existence and Parameters. SPIE Journal on Advances in Remote Sensing, 9 (1), 26. DOI: 10.1117/1.JRS.9.095066.

Zhai G., Min X. (2020). Perceptual image quality assessment: a survey. Science China Information Sciences, 63 (11), 1-52. DOI: 10.1007/s11432-019-2757-1.

Downloads

Published

2024-09-30

Issue

Section

Techniques for Earth observation data acquisition, processing and interpretation