Significance-Linked Connected Component Analysis

MCVL Homepage Department of Computer Engineering and Computer Science

Contact Information:

Xinhua Zhuang
Department of Computer Engineering and Computer Science
University of Missouri-Columbia
Columbia, MO 65211

Jozsef Vass
Department of Computer Engineering and Computer Science
University of Missouri-Columbia
Columbia, MO 65211


Table of Contents


Introduction

In recent years, we have seen an impressive advance in wavelet image coding. The success is mainly attributed to innovative strategies for data organization and representation of wavelet-transformed images which exploit the statistical properties in a wavelet pyramid one way or the other. In the Multimedia Communications and Visualization Lab, a very high performance image coding algorithm termed significance-linked connected component analysis (SLCCA) was developed by Bing-Bing Chai, Jozsef Vass, and Xinhua Zhuang. Extensive computer experiment demonstrate that SLCCA is among the best wavelet coding algorithms.


Wavelet Transform

There are two types of subband decomposition which are commonly used in image compression, i.e., uniform and pyramidal decomposition. Uniform decomposition divides an image into equal-sized subbands. By contrast, pyramidal decomposition represents an octave-band (dyadic) decomposition, offering a multiresolution representation of the image. Most of the subband image coders published recently are based on pyramidal (or dyadic) wavelet decomposition.


Data Organization and Representation

Data organization plays key role in the recent success of wavelet image coding algorithms. There have been three such high performance wavelet image coder developed, Shapiro's embedded zerotree wavelet coder (EZW) [1], Servetto et al. morphological representation of wavelet data (MRWD) [2], and Said and Pearlman's set partitioning in hierarchical trees (SPIHT) [3]. Both EZW and SPIHT exploit cross-subband dependency of insignificant wavelet coefficients while MRWD does within-subband clustering of significant wavelet coefficients.

Different from EZW and SPIHT, where insignificant wavelet coefficients are represented by a highly constrained tree or set partitioned tree structure, SLCCA follows the spirit of MRWD by directly clustering the significance field. Furthermore, SLCCA strengthens MRWD by exploiting the cross-scale dependency as well.


Performance Evaluation

The coding results show that SLCCA outperforms several top performance wavelet coder such as EZW, SPIHT, and MRWD. The coding performance is demonstrated on the following images (in GIF format):

Images for true performance comparison (in PGM format):

Original CR=16:1

CR=32:1 CR=64:1

Original CR=18:1


References

[1] J. Shapiro, "Embedded image coding using zerotrees of wavelet coefficients," IEEE Transactions on Signal Processing, vol. 41, no. 12, pp. 3445-3462, Dec. 1993.

[2] S. Servetto, K. Ramchandran, and M. Orchard, "Wavelet based image coding via morphological prediction of significance," Proceedings of IEEE ICIP-95, Oct. 1995, pp. 530-533.

[3] A. Said and W.A. Pearlman, "A new, fast, and efficient image codec based on set partitioning in hierarchical trees," IEEE Transactions on Circuits and Systems for Video Technology, vol. 6, no. 3, pp. 243-250, June 1996.


[Home] CECS Multimedia Communications and Visualization Laboratory