Separating Nonlinear Image Mixtures Using a Physical Model Trained with ICA
Almeida , L.
Separating Nonlinear Image Mixtures Using a Physical Model Trained with ICA, Proc IEEE International Workshop on Machine Learning for Signal Processing, Maynooth, Ireland, Vol. 1, pp. 65 - 70, September, 2006.
Digital Object Identifier:
Download Full text PDF ( 700 KBs)
This work addresses the separation of real-life nonlinear mixtures of images, which occur when a paper document is scanned and the image from the back page shows through. A physical model of the mixing process, based on the consideration of the halftoning process used to print grayscale images, is presented. The corresponding inverse model is then used to perform image separation. The parameters of the inverse model are optimized through the MISEP technique of nonlinear ICA, which uses an independence criterion based on minimal mutual information. The quality of the separated images is competitive with the one achieved by other techniques, namely by MISEP with a generic MLP-based separation network and by Denoising Source Separation. The separation results show that MISEP is an appropriate technique for training the parameters and that the model fits the mixing process well, although not perfectly. Prospects for improvement of the model are presented.