基于Shearlet变换域改进的IR与灰度VIS图像融合算法

针对多尺度变换域内红外(IR)与灰度可见光(VIS)图像融合后图像清晰度差、纹理信息不丰富等问题,提出一种基于剪切波变换(ST)域改进的IR与灰度VIS图像融合算法.首先,采用形态学顶帽变换(MTH)增强IR与VIS图像;然后,对增强后的IR与VIS图像采用ST变换,将其分解成高、低频图像,针对高频图像提出局部标准差(LSTD)与系数绝对值的融合策略;针对低频图像提出一种改进的权值融合策略;最后,通过逆剪切波变换(IST)获得最终融合图像.仿真实验结果表明,所推荐的方法具有优越的性能.

Improved infrared and gray visible light image fusion algorithm based on Shearlet transform

For the problems of definition difference and poor texture information of image after infrared (IR) and visible (VIS) light image fusion within multiscale transform domain, an improved fusion algorithm for IR and VIS images based on shearlet transform(ST) is proposed. Firstly, Morphology-Hat transform is used for an IR and a VIS light image separately. Then the enhanced IR and VIS light image are decomposed into high-frequency and low-frequency images by shearlet transform(ST). For the high frequency image, the fusion strategy of a local variance and the absolute value of the coefficient is proposed. For the low frequency image, a new weighted fusion strategy is proposed. Finally, the fused image is obtained by using the inverse shearlet transform(IST). The simulation experimental results show that the proposed method has superior performance.