High-quality compression of echographic images by neural networks and vector quantisation
- 43 Downloads
A compression method is presented for medical images based on neural networks and vector quantisation (VQ). The neural net is a perceptron and it is followed by some expressly designed VQ algorithms. The method devotes special attention to the quality of the reconstructed images and to the reduction of artefacts. The compression ratio obtained in the long run with echographic images is greater than 50∶1 with good quality.
KeywordsEcography Image compression Image quality Neural nets Vector quantisation
Unable to display preview. Download preview PDF.
- Abut, H. (1990): ‘Vector quantisation’ (IEEE Press)Google Scholar
- Capitanio, L., D’Alessio, T., Zanette, E. andSalustri, M. (1992): ‘Compressione delle immagini ecografiche: l’impatto sulla qualità’in Moltedo, L. (Ed.): ‘Conoscenza per immagini’, pp. 267–270Google Scholar
- CCITT (1991): ‘Digital compression of continuous tone still images’. Draft CCITT Rec. T.JPEG, GinevraGoogle Scholar
- Schweizer, L., Parladori, G., Sicuranza, G. L., andMarsi, S. (1991): ‘A fully neural approach to image compression’in Kohonen, T., Makisara, K., Simula, O. andKangas, J. (Eds.): ‘Artificial neural networks’ (Elsevier, Amsterdam) pp. 815–820.Google Scholar
- Sonehara, N., Kawato, M., Miyake andNakane, N. (1989): ‘Image data compression using neural network model’. Proc. First Joint Conf. on Neural Networks, Washington DC, pp. II.35–II.41Google Scholar