基于模糊算子的Tetrolet变换图像融合算法

Tetrolet Transform Images Fusion Algorithm Based on Fuzzy Operator

针对目前图像融合信息不完整,融合结果对比度不高的缺点,提出了一种基于模糊算子的Tetrolet变换图像融合算法。将源图像经过改进的Tetrolet变换,得到高频系数和低频系数;对于低通系数引入邻域能量及其接近度的融合规则,而对高频系数采用一种新的模糊融合算子,通过模糊推理确定各个源图像高频系数的权值,再对相应系数加权平均得到融合后的高频系数;对融合后的高频系数和低频系数,经Tetrolet反变换重构得到融合后的融合图像。通过实验证明了该算法的有效性。

Aiming at the problems that the fused image information is incomplete and the contrast degree in the fused image is low, this paper proposes an improved Tetrolet transform images fusion algorithm based on fuzzy operator. Firstly, the images are converted to the high frequency coefficients and low frequency coefficients by the improved Tetrolet transform. For the low frequency coefficients, the neighborhood energy and proximity are introduced to the fusion rule. For the high frequency coefficients, a new kind of fuzzy fusion operator is adopted. According to local area features of high frequency coefficients in source images, the weights of corresponding coefficients are obtained through fuzzy reasoning. Then these coefficients are averaged to obtain the fused high frequency coefficients by the weights. Finally, the fused low frequency coefficients and high frequency coefficients are reconstructed by the inverse Tetrolet transform. The experimental results testify the algorithm validity on the images fusion.