基于小波变换的多聚焦图像融合方法

Multi-focus Image Fusion Method Based on Wavelet Transform

为了改善图像融合效率,针对当前图像融合方法存在的局限性,提出一种基于小波变换的多聚焦图像融合方法.首先确定最优的小波分解层数,采用小波变换对图像进行多次分解;然后考虑低频子带与高频子带各自的特点,选择局部平均梯度准则作为高频子带的融合规则,低频子带采用3个系数的平均值作为融合规则;最后通过仿真实验对图像融合的有效性进行测试.实验结果表明,该方法获得了更理想的图像融合结果,提高了融合后的图像质量,且融合效果明显优于对比图像融合方法.

In order to improve the efficiency of image fusion,aiming at the limitation of current image fusion methods,the author proposed a multi-focus image fusion method based on wavelet transform.Firstly,the optimal wavelet decomposition level was determined,and wavelet transform was used to decompose image. Secondly,considering the characteristics of low frequency sub-band and high-frequency sub-band,the local average gradient criterion was chosen as the fusion rule of highfrequency sub-band,and the average value of three coefficients was used as the fusion rule of lowfrequency sub-band.Finally,the validity of image fusion was tested by simulation experiment.Experimental results show that the proposed method achieves more ideal image fusion results,and improves the quality of fused image.The fusion effect is better than the contrast image fusion method.