Wykorzystanie sieci neuronowych do bezstratnej kompresji obrazów cyfrowych

• Autorzy: Ulacha G.

Warianty tytułu

EN

Application of Neural Networks for lossless digital image compression

• Języki publikacji: PL

Abstrakty

PL

W artykule zaprezentowano metodę bezstratnej kompresji obrazów. Zastosowano w niej modelowanie z wykorzystujące nieliniową predykcję, która bazuje na sieciach neuronowych. Przedstawiono wyniki badań efektywności w zależności od liczby epok, wielkości okna uczącego oraz liczby neuronów w poszczególnych warstwach sieci. Ponadto dla tych parametrów dokonano też analizy czasu trwania procedury kodującej. Po dobraniu odpowiednich parametrów metodę uzupełniono o autorskie 3 kroki pozwalające zwiększyć efektywność proponowanej metody kompresji.

EN

In this paper, it is presented a method of lossless image compression that benefits from modeling with non-linear prediction based on neural networks. Effectiveness measures are provided with respect to the number of epochs, teaching window size and the neurons' number in each network layer. Moreover, for these parameters a time analysis of the encoding procedure is presented. After selecting the suitable parameters, the procedure has been extended by 3 steps resulting in effectiveness increase of the proposed compression method.

Słowa kluczowe

PL

bezstratna kompresja obrazu; adaptacyjne sieci neuronowe; nieliniowa predykcja; NLMS

EN

nieliniowa predykcja; NLMS; lossless image coding; adaptive neural networks; non-linear prediction

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2012
• Tom: R. 88, nr 8
• Strony: 155--160
• Opis fizyczny: Bibliogr. 27 poz., rys., tab., wykr.

Twórcy

autor

Ulacha G.

• Zachodniopomorski Uniwersytet Technologiczny, Wydział Informatyki, ul. Żołnierska 49, 71-210 Szczecin,

Bibliografia

• [1] Kassim A.A., Pingkun Yan, Wei Siong Lee, Sengupta K., Motion compensated lossy-to-lossless compression of 4-D medical images using integer wavelet transforms, IEEE Transactions on Information Technology in Biomedicine, (2005), n. 1, 132-138.
• [2] Sanchez V., Nasiopoulos P., Abugharbieh R., Efficient 4D motion compensated lossless compression of dynamic volumetric medical image data, IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2008, Las Vegas, Nevada, U.S.A., (2008), 549-552.
• [3] Strom J., Cosman P., Medical image compression with lossless regions of interest, Signal Processing, (1997), n. 2, 155-171.
• [4] Xiang Xie, GuoLin Li, ZhiHua Wang, A Near-Lossless Image Compression Algorithm Suitable for Hardware Design in Wireless Endoscopy System, EURASIP Journal on Advances in Signal Processing, (2007), 48-61.
• [5] Chen X. et al., Lossless Compression for Space Imagery in a Dynamically Reconfigurable Architecture, In Proc. of International Workshop on Applied Reconfigurable Computing (ARC2008), (2008), LNCS 4943, 336-341.
• [6] Lossless Data Compression. Recommendation for Space Data System Standards, CCSDS 120.1-G-1. Green Book. Issue 1. Washington, D.C.: CCSDS, (2007).
• [7] Sayood K., Introduction to Data Compression, 2nd edition, Morgan Kaufmann Publ., San Francisco, (2002).
• [8] Weinberger M. J., Seroussi G., Sapiro G., LOCO-I: Lossless Image Compression Algorithm: Principles and Standardization into JPEG-LS, IEEE Trans. on Image Processing, n. 8, (2000), 1309-1324.
• [9] Wu X., Memon N. D., CALIC – A Context Based Adaptive Lossless Image Coding Scheme, IEEE Trans. on Communications, (1996), 437-444.
• [10] Marcellin M., Gormish M., Bilgin A., Boliek M., An Overview of JPEG2000, Proceedings Data Compression Conference, Snowbird, Utah, (2000), 523-541.
• [11] Meyer B., Tischer P., GLICBAWLS - Grey Level Image Compression by Adaptive Weighted Least Squares, Proceedings of Data Compression Conference, (2001), 503.
• [12] Kau L.-J., Lin Y.-P., Lossless image coding using a switching predictor with run-length encodings, Proceedings of IEEE International Conference on Multimedia and Expo, (2004), 1155-1158.
• [13] Meyer B., Tischer P., TMWLego - An Object Oriented Image Modelling Framework, Proceedings of Data Compression Conference (2001), 504.
• [14] Matsuda I., Ozaki N., Umezu Y., Itoh S., Lossless coding using Variable Blok-Size adaptive prediction optimized for each image, Proceedings of 13th European Signal Processing Conference EUSIPCO-05 CD, (2005).
• [15] Ye H., A study on lossless compression of greyscale images, PhD thesis, Department of Electronic Engineering, La Trobe University, (2002).
• [16] Topal C., Gerek Ö. N., Pdf sharpening for multichannel predictive coders, Proceedings of 14th European Signal Processing Conference EUSIPCO-06 CD, (2006).
• [17] Dony R. D., Haykin S., Neural network approaches to image compresion, Proceedings of the IEEE, n. 2, (1995), 288-303.
• [18] Jiang J., Image compression with neural networks  a survey, Signal Processing: Image Communication, (1999), 737-760.
• [19] Hong G., Hall G., Terrell T., Prediction by back-propagation neural network for lossless image compression, 3rd International Conference on Signal Processing, (1996), 1026- 1030.
• [20] Rizvi S.A., Nasrabadi N.M., Lossless image compression using modular differential pulse code modulation, Proceedings of International Conference on Image Processing ICIP 1999, Kobe, Japan, (1999), 440-443.
• [21] Takizawa K., Takenouchi S., Aomori H., Otake T., Tanaka M., Matsuda I., Itoh S., Lossless image coding by cellular neural networks with minimum coding rate learning, Proceedings of 20th European Conference on Circuit Theory and Design (ECCTD), Linköping, Sweden, (2011), 33-36.
• [22] Kau L.-J., Lin Y.-P., Lin C.-T., Lossless image coding using adaptive, switching algorithm with automatic fuzzy context modelling, IEE Proceeding Vision, Image and Signal Processing, n. 5, (2006), 684-694.
• [23] Marusic S., Deng G., A neural network based adaptive nonlinear lossless predictive coding technique, The 5th Int. Symposium on Signal Processing and Its Applications ISSPA ‘99, Brisbane, Australia, (1999), 653-656.
• [24] Marusic S., Deng G., Adaptive prediction for lossless image compression, Signal Processing: Image Communications, (2002), 363-372.
• [25] Ulacha G., Stasiński R., Context based lossless coder based on RLS predictor adaptation scheme, Proceedings of International Conference on Image Processing ICIP 2009, Egypt, Cairo, (2009), 1917-1920.
• [26] Lee C.-H., Lai W.-Y., Chen C.-C., Lossless image coding via adaptive Takagi-Sugeno fuzzy neural network predictor, International Conference on Networking, Sensing and Control 2004, Taipei, Taiwan, (2004), 565-570.
• [27] Ye H., Deng G., Devlin J. C., Adaptive linear prediction for lossless coding of greyscale images, in Proc. IEEE Int. Conf. on Image Processing (CDROM), Vancouver, Canada, (2000).