Using multiple sensors in a vision system can significantly reduce both human and machine errors in detection and recognition of objects. A particular case of interest is where images from possibly different types of sensors are to be combined. Concealed weapon detection (CWD) is one interesting application. An image fusion scheme is proposed which combines aspects of feature-level fusion with the pixel-level fusion. Images are fused by combining their wavelet/pyramid transforms. The identification of important features in each image, such as edges and regions of interest, are used to guide the fusion process. New, intelligent processing is used to determine how to produce the fused images from the source images. Experiments substantiate that the algorithm of the proposed technology works well in many situations.