基于小波变换的多聚焦图像自适应融合

Multi-focus image fusion scheme based on wavelet transform

图像融合是对来自同一场景的不同源图像的信息进行互补和合成,从而获得更为准确、更为全面、更为可靠的图像。采用了一种基于小波变换的自适应图像融合方法,首先将配准好的图像进行小波分解,并提取出细节分量和近似分量。其次,针对不同的频率域选择不同的融合规则,对低频系数选取区域均匀度和变化率相结合的融合规则,对高频系数选用区域方向对比度和区域匹配度相结合的自适应融合规则。最后通过小波逆变换得到融合图像。将其它融合算法和文中所提算法进行主观和客观的对比,结果表明,该算法是一种有效可行的图像融合算法。

The image fusion is to combine information from different source images of the same scene to achieve a new image which can provide much more accurate and more comprehensive, more reliable information than the source images. Thus, an adaptive image fusion method based on wavelet transform to decompose the registration image is adopted. Firstly, it extracts the de- tail components and the approximate component. Then chooses different fusion rules in view of the different frequency domain, for low frequency coefficients, area uniformity and rate of combi- ning fusion rules are adopted, for high frequency coefficients, it chooses the regional direction and regional matching degree contrast with the combination of adaptive fusion rules. At last, the combination coefficients are transformed by wavelet inversely to obtain the fused image. Experimental analysis demonstrated that the proposed algorithm brings better vision effect and subjective evaluation to the fused image, and its fusion effect is satisfied.