Improved RoI-based remote sensing image compression

• Autorzy: Feng L. , Jiaxiong P.
• Języki publikacji: EN

Abstrakty

EN

The paper proposes an improved version of Rol - based coding for compressing remote sensing images. A fully automatic background - clustering algorithm is used based on some features which have fully considered the characteristics of region of interest - based image compression scheme. The new model has three advantages: allowing near-lossless Rol segmentation; reducing the ambiguity of reconstructed Rol edge; enhancing intelligibility for Rol in reconstructed image. The paper also introduce Wold feature. The feature can capture random texture as well as structural texture, and hence is better than other purely stochastic texture features. Some results on remote sensing images arę presented.

Słowa kluczowe

EN

image compression; improved Rol-based; Wold features

PL

kompresja obrazu; cecha Wolda

• Wydawca: Instytut Telekomunikacji i Informatyki Uniwersytetu Technologiczno-Przyrodniczego w Bydgoszczy
• Czasopismo: Image Processing & Communications
• Rocznik: 2003
• Tom: Vol. 9, no 1-2
• Strony: 3--15
• Opis fizyczny: Bibliogr. 12 poz., fot., rys.

Twórcy

autor

Feng L.

autor

Jiaxiong P.

Bibliografia

• [1] J. Askelof. M.L. Carlander and C. Christopoulos, Region of interest coding in JPEG 2000, Signal Processing: Image Comm., 17: 105-111, 2002.
• [2] D. Nister and C. Christopoulos, Lossless region of interest coding, Signal Processing, 78: 1-17, 1999.
• [3] J. Stroem, P.C. Cosman, Medical Image Compression with Lossless Regions of Interest, Signal Processing, 59: 155-177, 1997.
• [4] C. Andras. Medical Image Compression Using Region of Interest Vector Quantization, Proc. 20th Annual Int. Conf. IEEE Engineering in Medicine Society, France: Dept. ITI, ENST de Bretagne, pp.12771280, 1998.
• [5] G.A. Maria and F. Marco, Adaptive Image Compression Based on Regions of Interest and a Modified Contrast Sensitivity Function, Proc. 3rd. IEEE Conf. on Pattern Recognition, Italy:Dipartimento di Inf.e Sis- temistica. Pavia Univ. pp.215-218, 2000.
• [6] D.A. Karras and S.A. Karkanis, Image Compression Using the Wavelet Transform on Textural Regions of Interest, Proc. f2th IEEE Conf. on Euromicro, pp.633 -639, 1998.
• [7] A.T. Duchowsky, Representing Multiple Regions of Interest with Wavelets, Proc. SPIE on Visual Communications and Image Procession, pp.975-986, 1998.
• [8] J.M. Francos, A.Z. Meiri and B. Porat, A unified texture model Based on a 2-D Wold-like Decomposition, IEEE Trans. Signal Proc. 41: 2665-2677, 1993.
• [9] F. Liu and R.W. Picard. Periodicity, directionality, and randomnessAVold features for image modeling and retrieval, IEEE Trans. PAMI. 18: 722-733. 1996.
• [10] B. Adred and U. Andreas, Selective Medical Image Compression Techique fo Telemedical and Archiving Applocatons, Computer In Biology And Medicine, 30: 153-169, 2000.
• [11] R.L. Kashyap and R. Chellappa, Estimation and choice of neighbors in spatial- interaction models of image, IEEE Trans, on Information Theory, 29: 60-72, 1983.
• [12] T.N. Pappas, An adaptive clustering algorithm for image segmentation, IEEE Trans.Signal Proc.. 40: 901-914. 1992.