Abstract
The problem of image compression has been recently studied in a variety of different ways. Many approaches, however, are based either on transform coding techniques or on vector quantization; both of these methods essentially exploit the correlation which is generally present between close pixels in natural images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
H. M. Abbas and M. M. Fahmy, “Neural model for Karhunen-Loeve transform with application to adaptive image compression,”IEE Proceedings-I, vol. 140, pp. 135–143, Apr. 1993.
S. C. Ahalt, “Vector quantization using artificial neural networks models,” inProc. First COST #229 WG.2 Workshop, (Bayona, Spain), pp. 111–130, March 1991.
F. Arduini, S. Fioravanti, and D. D. Giusto, “Adaptive image coding using multilayer neural networks,” inProc. IEEE Int. Conf. Acoust, Speech, Signal Processing, (San Francisco), pp. II–381–II–384, March 1992.
P. Baldi and K. Hornik, “Neural networks and principal component analysis: learning from examples without local minima,”Neural Networks, vol. 2, pp. 53–58, 1989.
H. Bauer and K. R. Pawelzik, “Quantifying the neighborhood preservation of Self-Organizing Feature Maps,”IEEE Trans. on Neural Networks, vol. 3, pp. 570–578, July 1992.
M. E. Blain and T. R. Fisher, “A comparison of vector quantization techniques in transform and subband coding of imagery,”Signal Processing: Image Communication, vol. 3, pp. 91–105, 1991.
H. Bourlard and Y. Kamp, “Auto -association by multilayer perceptrons and singular value decomposition,”Biological Cybernetics, vol. 59, pp. 291–294, 1988.
E. Cammarota and G. Poggi, “Address predictive vector quantization of images,” inProc. AEI Symposium on Image Processing: Applications and Trends, (Genova, Italy), pp. 67–74, June 1991.
F. Campbell and J. Kulikowski, “Orientation selectivity of the human visual system,”J. Physiol., vol. 197, pp. 437–441, 1966.
S. Carrato, A. Premoli, and G. L. Sicuranza, “Linear and nonlinear neural networks for image compression,” inProc. 1991 International Conference on Digital Signal Processing, (Florence, Italy), pp. 526–531, Sept. 1991.
S. Carrato, G. Ramponi, A. Premoli, and G. L. Sicuranza, “Improved structures based on neural networks for image compression,” inProc. 1991 IEEE Workshop on Neural Networks for Signal Processing, (Princeton, New Jersey), pp. 493–502, Sept. 1991.
S Carrato, “Transform–based image compression optimized for some characteristics of the human visual system,” inSystems and Networks: Mathematical Theory and Applications, Proceedings of MTNS’93, (Berlin, Germany), pp. 635–640, Akademie Verlag GmbH, 1994
S Carrato, GL Sicuranza, and L Manzo, “Application of ordered codebooks to image coding,” inProc. 1993 IEEE-SP Workshop on Neural Networks for Signal Processing, (Linthicum Heights, MD, USA), pp. 291–300, Sept. 1993
P. Comon, “Independent component analysis,” inProc. International Signal Processing Workshop on Higher-Order Statistics, (Chamrousse, France), pp. 111–120, July 1991.
P. Comon, “Independent component analysis, a new concept?,”Signal Processing, vol. 36, pp. 287–314, 1994.
G. W. Cottrell, P. Munro, and D. Zipser, “Image compression by back propagation: an example of extensional programming,” inModels of cognition: a review of cognition science, ( N. E. Sharkey, ed.), NJ: Norwood, 1989.
D. DeMers and G. Cottrell, “Non-linear dimensionality reduction,” inAdvances in Neural Information Processing Systems 5, ( C. L. Giles, S. J. Hanson, and J. D. Cowan, eds.), San Mateo: Morgan Kaufmann, 1993.
K. I. Diamantaras and S. Y. Kung, “Compressing moving pictures using the APEX neural principal component extractor,” inProc. 1993 IEEE Workshop on Neural Networks for Signal Processing, (Linthicum Heights, MD), pp. 321–330, Sept. 1993.
N. Farvardin, “A study of vector quantization for noisy channels,”IEEE Trans. Inform. Theory, vol. 36, pp. 799–809, July 1990.
S. Fioravanti and D. D. Giusto, “Exploitation of a neural structure for improving vector quantization performances,” inProc. COST 229 WG1+2 Workshop, (Bayona, Spain), pp. 237–244, June 1993.
P. Foldiak, “Adaptive network for optimal linear feature extraction,” in IJCNN, (Washington DC), pp. I–401–I–406, 1989.
J. E. Fowler and S. C. Ahalt, “Robust, variable bit–rate coding using entropy-biased codebooks,” inProc. IEEE Data Compression Conference, (Los Alamitos, CA), pp. 361–370, 1993.
B. Fritzke, “Vector quantization with a growing and splitting elastic net,” inProc. ICANN’93, ( Amsterdam, The Netherlands ), Sept. 1993.
J.J. Gerbrands, “On the relationships between SVD, KLT, and PCA,”Pattern Recognition, vol. 14, pp. 375–381, 1981.
ISO/IEC, “Coding of moving pictures and associated audio,” ISO/IEC JTC 1/SC 29 WG 11, MPEG 92/No 245, July 1992.
A. K. Jain,Fundamentals of digital image processing. Englewood Cliffs, NJ: Prentice -Hall International, Inc., 1989.
J. Joutsensalo and J. Karhunen, “Nonlinear multilayer principal component type subspace learning algorithms,” inProc. 1993 IEEE–SP Workshop on Neural Networks for Signal Processing, (Linthicum Heights, MD, USA), pp. 68–77, Sept. 1993.
C. Jutten and J. Herault, “Blind separation of sources, part I: an adaptive algorithm based on neuromimetic architecture,”Signal Processing, vol. 24, pp. 1–10, 1991.
C. Jutten and J. Herault, “Independent Components Analysis (INCA) versus Principal Component Analysis,” inSignal processing IV: Theories and Applications, (J. L. Lacoume, A. Chehikian, N. Martin, and J. Malbos, eds. ), Elsevier Science Publishers B. V., 1988.
T. Kohonen,Self -organization and associative memory. Berlin: Springer-Verlag, 1984.
A. K. Krishnamurthy, S. C. Ahalt, D. E. Melton, and P. Chen, “Neural network for vector quantization of speech and images,”IEEE Journal on Selected Areas in Communications, vol. 8, pp. 1449–1457, Oct. 1990.
S. Y. Kung and K. I. Diamantaras, “A neural network learning algorithm for adaptive principal component extraction (APEX),” inProc. Int. Conf. on Acoustics, Speech, and Signal Processing, (Albuquerque, NM), pp. 861–864, Apr. 1990.
Y. Linde, A. Buzo, and R. M. Gray, “An algorithm for vector quantizer design,”IEEE Trans. Commun., vol. COM-28, pp. 84–95, Jan. 1980.
R. P. Lippmann, “An introduction to computing with neural nets,”IEEE ASSP Magazine, pp. 4–21, Apr. 1987.
S. Marsi, G. Ramponi, and G. L. Sicuranza, “Improved neural structures for image compression,” inProc. IEEE Int. Conf. Acoust., Speech, Signal Processing, pp. 2821–2824, May 1991.
S. Marsi and G. L. Sicuranza, “Neural networks for compression of image sequences,” inProc. 4th International Workshop on Time-Varying Image Processing and Moving Object Recognition, (Florence, Italy), June 1993.
G. Martinelli, L. P. Ricotti, and G. Marcone, “Neural clustering for optimal KLT image compression,”IEEE Trans, on Signal Processing, vol. 41, pp. 1737–1739, Apr. 1993.
W. Meier and H. von Stein, “Infrared image enhancement with nonlinear spatio-temporal filtering,” inProc. EUSIPCO-92, (Brussels, Belgium), pp. 1397–1400, Aug. 1992.
M. Mougeot, R. Azencott, and B. Angeniol, “Image compression with back propagation: improvement of the visual restoration using different cost functions,”Neural Networks, vol. 4, pp. 467–476, 1991.
M. Mougeot and R. Barrow, “From static to dynamic image compression,” inProc. INNC 90, (Paris), pp. 59–62, July 1990.
H. Niemann and J. Wu, “Neural network adaptive image coding,”IEEE Trans, on Neural Networks, vol. 4, pp. 615–627, 1993.
E. Oja, “Data compression, feature extraction, and autoassociation in feedforward neural networks,” inArtificial Neural Networks, (T. Kohonen, K. Makisara, O. Simula, and J. Kangas, eds. ), Elsevier Science Publisher B.V. — North-Holland, 1991.
E. Oja, “A simplified neuron model as a principal component analyzer,”J. Math Biology, vol. 15, pp. 267–273, 1982.
E. Oja and J. Karhunen, “On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix,”J. of Mathematical Analysis and Applications, vol. 106, pp. 69–84, 1985.
E. Oja, H. Ogawa, and J. Wangviwattana, “Learning in nonlinear constrained hebbian networks,” inArtificial Neural Networks, ( T. Kohonen, K. Makisara, O. Simula, and J. Kangas, eds.), Amsterdam: Elsevier Science Publishers B.V., 1991.
E. Oja, H. Ogawa, and J. Wangviwattana, “PCA in fully parallel neural networks,” inArtificial Neural Networks,2, (I. Aleksander and J. Taylor, eds. ), Elsevier Science Publisher B. V., 1992.
E. Oja, H. Ogawa, and J. Wangviwattana, “Principal component analysis by homogeneous neural networks, part II: analysis and extensions of the learning algorithms”IEICE Trans, on Information and Systems vol. E75-D, pp. 376–382, May 1992.
G. Poggi, “Address-predictive vector quantization of images by topology-preserving codebook ordering,”ETT, vol. 4, pp. 423–434, July-August 1993.
L. E. Russo, “An outer product neural network for extracting principal components from a time series,” inProc. 1991 IEEE Workshop on Neural Networks for Signal Processing, (Princeton, N.J., U.S.A.), pp. 161–170, Sept. 1991.
FM Salam, “An adaptive network for blind separation of indepentent signals,” inProc. ISCAS-93, pp. 431–434, 1993
T. D. Sanger, “An optimality principle for unsupervised learning,” inAdvances in Neural Information Processing Systems, I, (D. S. Touretzky, ed.).
G. Sartori, S. Carrato, and G. L. Sicuranza, “Linear neural networks with hierarchical structures for image compression,” inProc. 4th Italian Workshop on Parallel Architectures and Neural Networks, (Vietri sul Mare, Salerno, Italy), pp. 255–262, May 1991.
L Schweizer, G Parladori, and GL Sicuranza, “Globally trained neural network architecture for image compression,” inProc. 1992 IEEE Workshop on Neural Networks for Signal Processing, (Copenhagen), pp. 382–390, Aug. 1992
L. Schweizer, G. Parladori, G. L. Sicuranza, and S. Marsi, “A fully neural approach to image compression,” inProc. ICANN-91, (Espoo, Finland), pp. 815–820, June 1991.
G. L. Sicuranza, G. Ramponi, and S. Marsi, “Artificial neural network for image compression,”Electronics Letters, vol. 26, pp. 477–478, March 1990.
N. Sonehara, M. Kawato, S. Miyake, and K. Nakane, “Image data compression using a neural network model,” inProc. IJCNN, (Washington DC), pp. II–35–II–41, 1989.
L. Torres-Urgell and R. L. Kirlin, “Adaptive image compression using Karhunen-Loeve transform,”Signal Processing, vol. 21, pp. 303–313, Dec. 1990.
D. Tzovaras, M. G. Strintzis, and I. Pitas, “Image coding using nonlinear principal component analysis and vector quantization,” inProc. ISSSE-92, ( Paris ), Sept. 1992.
K. Zeger and A. Gersho, “Pseudo-Gray coding,”IEEE Trans. Commun., vol. 38, pp. 2147–2158, Dec. 1990.
K. Zeger, J. Vasey, and A. Gersho, “Globally optimal vector quantizer design by stochastic relaxation,”IEEE Trans. on Signal Processing, vol. 40, pp. 310–322, Feb. 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer-Verlag London Limited
About this chapter
Cite this chapter
Carrato, S., Marsi, S., Ramponi, G., Sicuranza, G.L. (1996). Image Coding Using Artificial Neural Networks. In: Figueiras-Vidal, A.R. (eds) Digital Signal Processing in Telecommunications. Springer, London. https://doi.org/10.1007/978-1-4471-1019-4_7
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1019-4_7
Publisher Name: Springer, London
Print ISBN: 978-3-540-76037-5
Online ISBN: 978-1-4471-1019-4
eBook Packages: Springer Book Archive