Multisensor image fusion based on a fuzzy neural network

Multisensor image fusion has its effective utilization for surveillance. In this paper, we utilize a fuzzy neural network approach to merge images from different sensors, in order to enhance visualization for surveillance. With the help of Sugeno-type fuzzy if-then rules and membership functions designed for the image data set, the fuzzy neural network approach can model and combine the images. Subjective and objective image fusion performance measures are introduced to assess image fusion schemes. Experimental results show that the fuzzy neural network approach is effective to merge images from different sensors.