Some applications that make use of digital images do not allow that the last are compressed with loss of information. A solution for this problem can be the use of a selective compression method, where determined regions of the image where the loss of information is not tolerable (regions of interest - Rol) are compressed without losses and the remaining portion with losses, making possible to reach high compression ratios. This paper proposes a selective compression method of digital color images where the perfect reconstruction of the regions of interest is guaranteed. The method uses competitive neural networks, mathematical morphology, Huffman adaptive coding and wavelet transform.2 12071212Gonzales, R.C., Woods, R.E., (2000) Digital Image Processing, , Addison-WesleyWong, S., Zaremba, L., Gooden, D., Huang, H.K., Radiologie image compression - A review (1995) Proceeding of the IEEE, 83 (2), pp. 194-219Bruckmann, A., Uhl, A., Selective medical image compression technique for telemedical and archiving applications (2000) Computer in Biology and Medicine, 30, pp. 153-169Christopoulos, C., Skodras, A., Ebrahimi, T., The JPEG2000 still image coding system: An Overview (2000) IEEE Transactions on Consumer Electronics, 46 (4), pp. 1103-1127. , NovemberAlmeida Filho, W.T., Dória Neto, A.D., Brito Junior, A.M., A neural and morphological method for wavelet-based image compression (2002) Proc. of the International Joint Conference on Neural NetworksFliege, N.J., (1994) Multirate Digital Signal Processing, , WileyHuffman, D.A., A Method for construction of minimum redundancy codes (1952) Proc. of the Institute of Electronics and Radio Engineers, 40, pp. 1098-1101. , SeptemberHeijmans, H.J.A.M., (1994) Morphological Image Operators, , Academic PressBanon, G.J.F., Barrera, J., Minimal representations for translation-invariant ser mappings by mathematical morphology (1991) SIAM Jounal on Applied Mathematics, 51 (6), pp. 1782-1798Morales, E., Shih, F.Y., Wavelet coefficients clustering using morphological operations and pruned quadtrees (2000) Pattern Recognition, 33, pp. 1611-1620Rumelhart, D.E., Zipser, D., Feature discovery by competitive learning (1985) Cognitive Science, 9, pp. 75-112Haykin, S., (1999) Neural Networks, , Prentice-HellUSC-SIPI Image Database, , http://sipi.usc.edu/services/database/Database.html