Compression of Digital Mammograms Using Wavelets and Fuzzy Algorithms for Learning Vector Quantization
This chapter presents the development and evaluates the performance of an image compression system designed for digital mammograms using wavelet image decomposition and vector quantization. In digital mammograms, important diagnostic features such as the microcalcifications appear in small clusters of few pixels with relatively high intensity compared with their neighboring pixels. These image features can be preserved by a compression scheme employing a suitable image transform which can localize the signal characteristics in the original and the transform domain. Image compression is achieved by using wavelet filters to decompose digital mammograms into subbands carrying different frequencies. The resulting subbands are then encoded using vector quantization. Vector quantization is based on multiresolution codebooks designed by the Linde-Buzo-Gray (LBG) algorithm and a family of fuzzy algorithms for learning vector quantization (FALVQ). The experimental results confirm the potential of the compression system described in this chapter for use in digital mammography and also provide the basis for evaluating the effect of the main design components of such a system on image quality.
KeywordsCompression Ratio Filter Bank Wavelet Filter Learn Vector Quantization High Compression Ratio
Unable to display preview. Download preview PDF.
- 6.Crochiere, R. E., Webber, S. A., Flanagan, J. L. (1976). Digital coding of speech in subbands. Bell System Technical Journal, 55(8): 1069–1085.Google Scholar
- 10.Esteban, D., Galand, C. (1979). Applications of quadrature mirror filters to split band voice coding schemes. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Washington, DC, April 1979, pp. 191–195.Google Scholar
- 14.Karayiannis, N. B. (1995). Generalized fuzzy k-means algorithms and their application in image compression. S PIE Proceedings vol. 2493: Applications of Fuzzy Logic Technology II, Orlando, FL, April 17–21, 1995, pp. 206–217.Google Scholar
- 15.Karayiannis, N. B. (1996). Generalized fuzzy c-means algorithms. Proceedings of Fifth International Conference on Fuzzy Systems, New Orleans, LA, September 8–11, 1996, pp. 1036–1042.Google Scholar
- 16.Karayiannis, N. B. (1997). Entropy constrained learning vector quantization algorithms and their application in image compression. SPIE Proceedings vol. 3030: Applications of Artificial Neural Networks in Image Processing II, San Jose, CA, February 12–13, 1997, pp. 2–13.Google Scholar
- 17.Karayiannis, N. B. (1997). Learning vector quantization: A review. International Journal of Smart Engineering System Design, 1: 33–58.Google Scholar
- 18.Karayiannis, N. B. (1997). Fuzzy partition entropies and entropy constrained clustering algorithms. Journal of Intelligent & Fuzzy Systems, 5(2): 103–111.Google Scholar
- 20.Karayiannis, N. B. (1998). Ordered weighted learning vector quantization and clustering algorithms. Proceedings of 1998 International Conference on Fuzzy Systems, Anchorage, AK, May 4–9, 1998, pp. 1388–1393.Google Scholar
- 21.Karayiannis, N. B. (1998]. Soft learning vector quantization and clustering algorithms based in reformulation. Proceedings of 1998 International Conference on Fuzzy Systems, Anchorage, AK, May 4–9, 1998, pp. 1441–1446.Google Scholar
- 38.Smith, M. J. T., Barnwell III, T. P. (1986). Exact reconstruction for tree-structured subband coders. IEEE Transactions on Acoustics, Speech, and Signal Processing, 34(3): 431–441.Google Scholar
- 49.Wang, T. C, Karayiannis, N. B. (1997). Compression of digital mammograms using wavelets and learning vector quantization. SPIE Proceedings vol. 3030: Applications of Artificial Neural Networks in Image Processing II, San Jose, CA, February 12–13, 1997, pp. 44–55.Google Scholar