A method for processing components of an image for coding a sample of the image, the image being composed of a first type of component and a second type of component, wherein samples of the second type of component are predictable from samples of the first type of component using a prediction model, computing one parameter value for use in representing, in the prediction model, the link between the first type of component and the second type of component; detecting, whether or not, one type of error exists in one such computed parameter value of the prediction model and in the case where a first type of error is detected; adapting the computed parameter value to correct for the error detected; and predicting a sample of the second type from a sample of the first type using the prediction model and the adapted parameter value.