A Discrete Wavelet Transform - Singular Value Decomposition system for image coding

 

H. de Jesús Ochoa-Domínguez, K. R. Rao

 

Abstract

A system that combines techniques of wavelet transform (DWT) and singular value decomposition (SVD) to encode images is presented. The image is divided into tiles or blocks of 64x64 pixels. The decision criterion as to which transform to use is based on the standard deviation of the 8x8 pixel subblocks of the tile to encode. A successive approximation quantizer is used to encode the subbands and vector quantization/scalar quantization is used to encode the SVD eigenvectors/eigenvalues, respectively. For coding color images, the RGB components are transformed into YCbCr before encoding in 4:2:0 format. Results show that the proposed system outperforms the JPEG and approaches the JPEG2000.

Keywords: Wavelet Transform, Singular Value Decomposition, HC-RIOT, SPIHT, Scalar Quantization, Vector Quantization, Image Coding, HDCTSVD.

 

Resumen

Se presenta un nuevo sistema que combina técnicas de transformada wavelet (DWT) y descomposición en valores singulares (SVD) para codificar imágenes. Las imágenes se dividen en cuadros de 64x64 pixeles. Para decidir qué transformada utilizar, se utiliza un criterio basado en la desviación estándar de subbloques de 8x8 pixeles del bloque a codificar. Las subbandas, resultadas de aplicar la DWT, se codifican utilizando un cuantizador de aproximaciones sucesivas. Los eigenvectores y eigenvalores, resultados de la aplicación SVD, se codifican utilizando cuantización vectorial y escalar, respectivamente. Antes de codificar imágenes a color, las componentes RGB se transforman a YCbCr en formato 4:2:0. Los resultados muestran que con el sistema propuesto se logra mucho mayor compresión que JPEG y se aproxima bastante al nuevo estándar de compresión JPEG2000.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

9. REFERENCES

[1] Dapena and S. Ahalt, "A hybrid DCT-SVD image-coding algorithm," IEEE Trans. CSVT, vol. 12, pp.114-121, Feb. 2002.         [ Links ]

[2] H. C. Andrews, Computer Techniques in Images Processing. NY and London: Academic Press, 1970.         [ Links ]

[3] A. Said and W.A. Pearlman, "A new fast and efficient coder based on set partitioning in hierarchical trees," IEEE Trans. CSVT, vol. 6, pp.243-250, June 1996.         [ Links ]

[4] Y. F. Syed, A low bit rate wavelet-based image coder for transmission over hybrid networks. Doctoral Dissertation, University of Texas at Arlington, 1999.         [ Links ]

[5] K.R. Rao and J.J. Hwang, Techniques and Standards for Image, Video and Audio Coding. Upper Saddle River, New Jersey: Prentice Hall, 1996.         [ Links ]

[6] ISO/IEC FDIS 15444-1, JPEG 2000 Part I Final Draft International Standard, Aug. 2000.         [ Links ]

[7] A.K. Jain, Fundamentals of Digital Image Processing. Englewood Cliffs, NJ: Prentice-Hall, 1989.         [ Links ]

[8] A I. Daubechies, Ten Lectures on Wavelets. Rutgers University and AT & T Bell Laboratories, SIAM, 1992.         [ Links ]

[9] I. Daubechies and W. Sweldens, "Factoring wavelet transforms into lifting steps," J. Fourier Anal. Appl., vol. 4, pp. 247-269, 1998.         [ Links ]

[10] M. Smith and S. Eddins, "Analysis/Synthesis techniques for subband image coding," IEEE Trans. ASSP, vol. 38, pp. 1446-1456, Aug. 1990.         [ Links ]

[11] http://sipi.usc.edu/services/database/

[12] Y. Linde, A. Buzo, and R. M. Gray, "An algorithm for vector quantizer design," IEEE Trans. Communications, vol. 28, pp. 84-95, Jan. 1980.         [ Links ]

[13] H. Ochoa and K.R. Rao, "A New HDWTSVD Coding System for Monochromatic Images," WSEAS Transaction on Signal Processing, vol. 1, pp. 419-424, Dec. 2005.         [ Links ]

[14] H. Ochoa and K.R. Rao, "A New Modified Hybrid HDWTSVD Coding System for Color Images," WSEAS Transaction on Circuits and Systems, vol. 4, pp. 1246-1253, Oct. 2005.         [ Links ]