Adaptive Neural-Network-Based Lossless Image Coder with Preprocessed Input Data
Source abstract
Abstract
It is shown in this paper that the appropriate preprocessing of input data may result in an important reduction of Artificial Neural Network (ANN) training time and simplification of its structure, while improving its performance. The ANN is working as a data predictor in a lossless image coder. Its adaptation is done for each coded pixel separately; no initial training using learning image sets is necessary. This means that there is no extra off-line time needed for initial ANN training, and there are no problems with network overfitting. There are two concepts covered in this paper: Replacement of image pixels by their differences diminishes data variability and increases ANN convergence (Concept 1); Preceding ANN by advanced predictors reduces ANN complexity (Concept 2). The obtained codecs are much faster than one without modifications, while their data compaction properties are clearly better. It outperforms the JPEG-LS codec by approximately 10%.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Data Compression Techniques · Image and Signal Denoising Methods · Advanced Steganography and Watermarking Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Computer Science and Information Technology, West Pomeranian University of Technology, 71-210 Szczecin, Poland
Institute of Multimedia Telecommunications, Poznan University of Technology, 60-965 Poznan, Poland
Funding
Polish Ministry of Science and Higher Education
References (49)
Show source-provided references
1. The LOCO-I lossless image compression algorithm: Principles and standardization into JPEG-LS10.1109/83.855427 ↗
2. Marcellin, M., Gormish, M., Bilgin, A., and Boliek, M. (2000, January 28–30). An overview of JPEG-2000. Proceedings of the Proceedings DCC 2000. Data Compression Conference, Snowbird, UT, USA.
3. (2023, April 08). Codec WebP 1.3. Available online: https://storage.googleapis.com/downloads.webmproject.org/releases/webp/libwebp-1.3.0-windows-x64.zip.
4. Wu, X., and Memon, N. (1996, January 9). CALIC—A Context Based Adaptive Lossless Image Codec. Proceedings of the 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings, Atlanta, GA, USA.
5. Meyer, B., and Tischer, P. (2001, January 27–29). TMWLego—An Object Oriented Image Modeling Framework. Proceedings of the Data Compression Conference, Washington, DC, USA.
6. Ye, H., Deng, G., and Devlin, J. (2003, January 23–25). A weighted least squares method for adaptive prediction in lossless image compression. Proceedings of the Picture Coding Symposium PCS’03, Saint Malo, France.
7. Matsuda, I., Ozaki, N., Umezu, Y., and Itoh, S. (2005, January 4–8). Lossless coding using Variable Blok-Size adaptive prediction optimized for each image. Proceedings of the 13th European Signal Processing Conference EUSIPCO-05 CD, Antalya, Turkey.
8. Large Discriminative Structured Set Prediction Modeling with Max-Margin Markov Network for Lossless Image Coding10.1109/TIP.2013.2293429 ↗
9. Matsuda, I., Ozaki, N., Umezu, Y., and Itoh, S. (2018, January 3–7). A Lossless Image Coding Method Based on Probability Model Optimization. Proceedings of the 2018 26th European Signal Processing Conference (EUSIPCO), Rome, Italy.10.23919/EUSIPCO.2018.8553404 ↗
10. Unno, K., Kameda, Y., Matsuda, I., Itoh, S., and Naito, S. (2019, January 2–6). Lossless Image Coding Exploiting Local and Non-local Information via Probability Model Optimization. Proceedings of the 27th European Signal Processing Conference (EUSIPCO), A Coruna, Spain.10.23919/EUSIPCO.2019.8903128 ↗
11. Kojima, H., Kita, Y., Matsuda, I., Itoh, S., Kameda, Y., Unno, K., and Kawamura, K. (2022, January 4–6). Improved Probability Modeling for Lossless Image Coding Using Example Search and Adaptive Prediction. Proceedings of the International Workshop on Advanced Imaging Technology (IWAIT) 2022, Hong Kong, China.10.1117/12.2625972 ↗
12. Ulacha, G., Stasinski, R., and Wernik, C. (2020). Extended Multi WLS Method for Lossless Image Coding. Entropy, 22.10.3390/e22090919 ↗
13. Lossless image coding using adaptive, switching algorithm with automatic fuzzy context modelling10.1049/ip-vis:20045256 ↗
14. Marusic, S., and Deng, G. (1999, January 22–25). A neural network based adaptive non-linear lossless predictive coding technique. Proceedings of the ISSPA ’99. Proceedings of the Fifth International Symposium on Signal Processing and Its Applications (IEEE Cat. No.99EX359), Brisbane, QLD, Australia.
15. Adaptive prediction for lossless image compression10.1016/S0923-5965(02)00006-1 ↗
16. Ulacha, G., and Stasiński, R. (2012, January 7–9). Improving Neural Network Approach to Lossless Image Coding. Proceedings of the 29th Picture Coding Symposium PCS’12, Krakow, Poland.
17. Lossless Image Compression by Joint Prediction of Pixel and Context Using Duplex Neural Networks10.1109/ACCESS.2021.3088936 ↗
18. Zhang, Z., Wang, H., Chen, Z., and Liu, S. (2024, January 16–22). Learned Lossless Image Compression Based on Bit Plane Slicing. Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR52733.2024.02604 ↗
19. Rhee, H., and Cho, N.I. (November, January 31). Resolution-Adaptive Lossless Image Compression Using Frequency Decomposition Network. Proceedings of the 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Taipei, Taiwan.10.1109/APSIPAASC58517.2023.10317322 ↗
20. Probability Prediction Network With Checkerboard Prior for Lossless Remote Sensing Image Compression10.1109/JSTARS.2024.3462948 ↗
21. Shen, Y., Wu, G., Swaminathan, V., Wang, H., Petrangeli, S., and Yu, T. (2023, January 11–13). GPU-accelerated Lossless Image Compression with Massive Parallelization. Proceedings of the 2023 IEEE International Symposium on Multimedia (ISM), Laguna Hills, CA, USA.10.1109/ISM59092.2023.00061 ↗
22. Said, A., Le, H., and Farhadzadeh, F. (2023, January 11–13). Bitstream Organization for Parallel Entropy Coding on Neural Network-based Video Codecs. Proceedings of the 2023 IEEE International Symposium on Multimedia (ISM), Laguna Hills, CA, USA.10.1109/ISM59092.2023.00007 ↗
23. Deep Lossy Plus Residual Coding for Lossless and Near-Lossless Image Compression10.1109/TPAMI.2023.3348486 ↗
24. Zhang, S., Zhang, C., Kang, N., and Li, Z. (2021, January 20–25). Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.00068 ↗
25. Deep Architectures for Image Compression: A Critical Review10.1016/j.sigpro.2021.108346 ↗
26. Near-lossless image compression by relaxation-labeled prediction10.1016/S0165-1684(02)00305-5 ↗
27. Golchin, F., and Paliwal, K.K. (1997, January 26–29). Classified adaptive prediction and entropy coding for lossless coding of images. Proceedings of the International Conference on Image Processing, Santa Barbara, CA, USA.
28. Meyer, B., and Tischer, P. (1997, January 10–12). TMW—A new method for lossless image compression. Proceedings of the International Picture Coding Symposium (PCS 97), Berlin, Germany.
29. Strutz, T. (2002, January 28–30). Context-based adaptive linear prediction for Lossless Image Coding. Proceedings of the 4th International ITG Conference on Source and Channel Coding, Berlin, Germany.
30. Context-Based Predictor Blending for Lossless Colour Image Compression10.1109/TCSVT.2015.2416611 ↗
31. Ulacha, G., and Stasiński, R. (2014, January 11–13). New Context-Based Adaptive Linear Prediction Algorithm for Lossless Image Coding. Proceedings of the 2014 International Conference on Signals and Electronic Systems (ICSES), Poznan, Poland.10.1109/ICSES.2014.6948714 ↗
32. Ulacha, G., and Stasinski, R. (2009, January 7–10). Context based lossless coder based on RLS predictor adaption scheme. Proceedings of the 2009 16th IEEE International Conference on Image Processing (ICIP), Cairo, Egypt.10.1109/ICIP.2009.5413680 ↗
33. Wu, X., Barthel, E., and Zhang, W. (1998, January 7). Piecewise 2D autoregression for predictive image coding. Proceedings of the Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269), Chicago, IL, USA.
34. Ye, H., Deng, G., and Devlin, J. (2000, January 10–13). Adaptive linear prediction for lossless coding of greyscale images. Proceedings of the Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101), Vancouver, BC, Canada.
35. Ye, H., Deng, G., and Devlin, J. (1999, January 22–25). Least squares approach for lossless image coding. Proceedings of the ISSPA ’99. Proceedings of the Fifth International Symposium on Signal Processing and Its Applications (IEEE Cat. No.99EX359), Brisbane, QLD, Australia.
36. Takizawa, K., Takenouchi, S., Aomori, H., Otake, T., Tanaka, M., Matsuda, I., and Itoh, S. (2011, January 10–15). Lossless image coding by cellular neural networks with minimum coding rate learning. Proceedings of the 2011 20th European Conference on Circuit Theory and Design (ECCTD), Brisbane, QLD, Australia.10.1109/ECCTD.2011.6043337 ↗
37. Lee, C.H., Kau, L.J., and Lin, Y.P. (2009, January 24–27). A fuzzy neural network based adaptive predictor with P-controller compensation for lossless compression of images. Proceedings of the 2009 IEEE International Symposium on Circuits and Systems (ISCAS), Taipei, Taiwan.10.1109/ISCAS.2009.5117828 ↗
38. Rahman, A., Hamada, M., and Rahman, A. (2022, January 25–28). A comparative analysis of the state-of-the-art lossless image compression techniques. Proceedings of the 4th ETLTC International Conference on ICT Integration in Technical Education (ETLTC2022), Aizuwakamatsu, Japan.
39. Mentzer, F., van Gool, L., and Tschannen, M. (2020, January 13–19). Learning Better Lossless Compression Using Lossy Compression. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00667 ↗
40. Rhee, H., Jang, Y.I., Kim, S., and Cho, N.I. (2022, January 18–24). Learned Lossless Image Compression with Frequency Decomposition Network. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00594 ↗
41. Hoogeboom, E., Peters, J.W., van den Berg, R., and Welling, M. (2019, January 8–14). Integer Discrete Flows and Lossless Compression. Proceedings of the International Conference on Neural Information Processing Systems (2019), Vancouver, BC, Canada.
42. Mentzer, F., Agustsson, E., Tschannen, M., Timofte, R., and Gool, L.V. (2019, January 15–20). Practical Full Resolution Learned Lossless Image Compression. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.01088 ↗
43. Cao, S., Wu, C.-Y., and Krähenbühl, P. (2020). Lossless Image Compression through Super-Resolution. arXiv.
44. Shim, J.H., Rhee, H., Jang, Y.I., Lee, G., Kim, S., and Cho, N.I. (2021, January 14–17). Lossless Image Compression Based on Image Decomposition and Progressive Prediction Using Convolutional Neural Networks. Proceedings of the 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Tokyo, Japan.
45. Gumus, S., and Kamisli, F. (2022). A Learned Pixel-by-Pixel Lossless Image Compression Method with 59K Parameters and Parallel Decoding. arXiv.10.1007/s11042-023-16270-4 ↗
46. Ulacha, G., and Stasiński, R. (2008, January 5–7). A Time-Effective Lossless Coder Based on Hierarchical Contexts and Adaptive Predictors. Proceedings of the 14th IEEE Mediterranean Electrotechnical Conference MELECON’08, Ajaccio, France.10.1109/MELCON.2008.4618538 ↗
47. Ulacha, G., and Łazoryszczak, M. (2023). Lossless Image Coding Using Non-MMSE Algorithms to Calculate Linear Prediction Coefficients. Entropy, 25.10.3390/e25010156 ↗
48. Liang, Y., Jia, T., Li, N., Liu, X., Jiang, J., and Lu, G. (2024, January 15–17). Review of Static Image Compression Algorithms. Proceedings of the 2024 IEEE 7th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chongqing, China.10.1109/IAEAC59436.2024.10503622 ↗
49. (2024, December 20). Test Images. Available online: https://kakit.zut.edu.pl/fileadmin/Test_Images.zip.