Morphological filters and wavelet-based image fusion for concealed weapons detection

摘要: When viewing a scene for an object recognition task, one imaging sensor may not provide all the information needed recognition. One way to obtain more is use multiple sensors. These sensors should images that contain complementary about same scene. After preprocessing source images, we image fusion combine from difference The be fused have some details such as shadows, wrinkles, artifacts, etc., are in final image. application of morphological filters remove objects given size range Therefore, conjunction with wavelets improve performance after fusion. filtering, used construct multiresolution representations images. Once decomposed, combined form composite decomposed This method allows at different levels independently so important maintained We developing algorithms concealed weapon detection (CWD) applications. Fusion useful situations where types properties, e.g., IR and MMW Fusing these results which complete CWD applications weapons on person. In this paper present our most recent area.