A method for coding pixels or voxels of a digital or digitalized two dimensional or three dimensional image, comprises the steps of: providing a digital image consisting in a two dimensional array of pixels or in a three dimensional array of voxels, each pixel or voxel being defined by at least one variable as its intensity in a grey scale image or the HSV (Hue, Saturation and Value) or the RGB values in a colour image; each pixel or voxel and for each target pixel or voxel a neighborhood being formed by a pixel or voxel windows comprising the said target pixel or voxel and a certain number of surrounding pixels or voxels for each target pixel or voxel generating a vector univocally associated to the said target pixel or voxel, the components of the said vectors being generated as a function of the values of the said target pixel or voxel and of each of the pixels or voxels of the said pixel or voxel window. The function of the values of the said target pixel or voxel and of each of the pixels or voxels of the said pixel or voxel window correspond to the characteristic parameters of the numerical matrix representing the pixels or voxels of the said window or of a transformation of the said numerical matrix. The invention relates also to an image processing method in which image data coded according to the above method are processed by means of a predictive algorithm as for example an artificial neural network.
展开▼
