Compression of Remotely Sensed Images using Self Organizing Feature Maps

Publisher Summary This chapter discusses the compression of remotely sensed images using self-organizing feature maps. Data compression is one tool that can be used to help overcome data transmission bandwidth limitations. However, for experimental remote sensing data, lossless data compression is required for any data that is to be actually fully analyzed by the researcher utilizing the data. Nonetheless, highly lossy data compression can be used by a researcher who just needs to browse through a large number of data sets, and moderately lossy data compression can be used for the final selection of data sets to be fully analyzed. As more familiarity is gained with particular data sets, lossy data compression algorithms could be designed that give significant compression while losing only non-essential information, essentially the noise, and retaining all the scientifically significant information. One way this could be accomplished would be by designing the data compression scheme as an integral part of the information extraction process, wherein the data compression is a form of conditioning of the data for analysis. Among lossy compression techniques, there are four important classes: (1) predictive coding techniques, (2) transform techniques, (3) hybrid coding, and (4) vector quantization.

[1]  S. P. Luttrell,et al.  Hierarchical vector quantisation , 1989 .

[2]  S.P. Luttrell.  Image compression using a neural network , 1988, International Geoscience and Remote Sensing Symposium, 'Remote Sensing: Moving Toward the 21st Century'..

[3]  Nasser M. Nasrabadi,et al.  Image coding using vector quantization: a review , 1988, IEEE Trans. Commun..

[4]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[5]  V. Cuperman,et al.  Vector quantization: A pattern-matching technique for speech coding , 1983, IEEE Communications Magazine.

[6]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[7]  R. Gray,et al.  Speech coding based upon vector quantization , 1980, ICASSP.

[8]  Robert M. Gray,et al.  High-resolution quantization theory and the vector quantizer advantage , 1989, IEEE Trans. Inf. Theory.

[9]  P. Murali,et al.  Fault-tolerance and learning performance of the back-propagation algorithm using massively parallel implementation , 1990, [1990 Proceedings] The Third Symposium on the Frontiers of Massively Parallel Computation.

[10]  C. E. SHANNON,et al.  A mathematical theory of communication , 1948, MOCO.

[11]  Stephen P. Luttrell.  Image compression using a multilayer neural network , 1989, Pattern Recognit. Lett..

[12]  William Equitz,et al.  A new vector quantization clustering algorithm , 1989, IEEE Trans. Acoust. Speech Signal Process..

[13]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[14]  Bhaskar Ramamurthi,et al.  Image coding using vector quantization , 1982, ICASSP.

[15]  P. A. Ramamoorthy,et al.  Bit-serial VLSI implementation of vector quantizer for real-time image coding , 1989 .

[16]  Leslie A. Tavenner.  AIAA/NASA International Symposium on Space Information Systems, 2nd, Pasadena, CA, Sept. 17-19, 1990, Proceedings. Vols. 1 & 2 , 1991 .

[17]  R. Gray,et al.  Vector quantization , 1984, IEEE ASSP Magazine.