Image Fusion Based on Muti-directional Multiscale Analysis and Immune Optimization

Image fusion is a process by combining two or more source images from different modalities or instruments into a single image with more information. The successful fusion is of great importance in many applications, such as military, remote sensing, computer vision and medical imaging, et al. Image fusion can be performed at signal, pixel, feature and symbol levels depending on the representation format at which image information is processed. The pixel-level image fusion can provide the fine information by fusing the pixels of the source images and the fused images. In this chapter, we only consider the fusion technique on pixel-level. To the pixel-level fusion, some generic requirements can be imposed on the fused on the fusion results (Rockinger, O., 1996): a. The fused image should preserve all relevant information contained in the source images as closely as possible; b. The fused process should not introduce any artifacts or inconsistencies, which can distract or mislead the human observer, or any subsequent image processing steps; c. In the fused image, irrelevant features and noise should be suppressed to a maximum extent. The visible light sensor and the infrared sensor are in common use sensors acting on different bands. The infrared imaging sensor is sensitive to the radiation of object scene, but not to the brightness change of scene. The visible light imaging sensor is sensitive and decided by the reflectivity and the shadow of the object sensor and has the higher contrast degree, but independent to the heat contrast. The image features of the two kinds of sensors have the different gray values and have the complement information. The fusion of the infrared images and the low visible light images can be in favor of integrating the good object denote character of the infrared images and the clear scene information of the visible light images. Panchromatic (PAN) images of high spatial resolution can provide detailed geometric information, such as shapes features, and structures of objects of the earth’s surface. While multispectral(MS) images with usually lower resolution are used to obtain spectral information necessary for environmental applications. The different objects within images of high spectral resolution are easily identified. Data fusion methods aim to obtain the images with high spatial and spectral resolution, simultaneously. The PAN and MS remote sensing