【摘要】 基于视觉显著特征提出一种新的图像融合算法。首先对源图像进行小波分解,得到低频系数和高频系数;然后针对低频系数提出一种基于视觉显著性的融合规则,对高频系数采用绝对值取大的融合规则;最后对融合后的低频系数和高频系数进行小波逆变换得到最终融合图像。该方法能完好地将源图像的细节融合在一起。仿真实验表明,该算法在视觉效果上比传统及改进方法更好,同时互信息、平均结构相似性、信息熵等传统客观评价指标有所提高。更多还原

【Abstract】 A new approach for image fusion is proposed based on visual saliency in this paper. Sourse images are decomposed by wavelet to get coefficients of low and high frequency,then the part of low frequency is fused using salient method proposed and the part of high frequency is fused by selecting large absolute wavelet coefficients. Fused image is got by wavelet inverse transformation.Details of source images is fused beautifully using this method. It proves that method proposed outperforms the traditional and improved method in visual effect and some assessment criteria are advanced,such as mutual information,average structural similarity,entropy and so on.更多还原