A Method Based on Multi-Scale Wavelet Decomposition of Image Fusion Algorithm

In recent years, image fusion has become an important and valuable new technology of Image Understanding and Computer Vision Fields. In order to integrate image information which be obtained by different type sensors and improved the reliability and observability of the image by processing the redundant data among the images, some methods have been described. In this paper, we introduce some methods, and selective analysis the multi-scale image fusion method based on wavelet-domain. Different fusion rules are adopted in high-frequency detailed parts and low-frequency approximate parts. The fusion method of maximum operation factor was adopted for the sub-images with low-frequency band. In the corresponding high-frequency coefficient, use the basic sub-images fusion method. Lastly, the whole fused image could be obtained by inverse wavelet transform of the low-frequency and the high-frequency sub-images which were processed by the above proposed methods. Because different fusion rules are adopted in different frequencies, it could overcome the disadvantages in image fusion which are easily disturbed by noise and subjected to loss of detailed information.