In reverse analysis of integrated circuits

three components of a color IC line-net image are often needed to be fused to a gray one to reduce complexity. Due to the local similarity in IC images

fusion is only performed in an automatically selected local neighborhood to get the global optimal weights in this paper. A new line model is constructed to describe the feature of interest and the model based fusion is divided into feature extraction

feature enhancement and noise suppression. Experiments show the superiority of local line model based fusion algorithm over traditional methods in enhancing the feature of interest and the quality of the fused image.