Fusion algorithm for multi-sensor images based on lifting wavelet transform and fractal theory

The same object visual and near infrared images are fused in some agriculture pick machine vision systems. A novel image fusion algorithm is proposed based on lifting wavelet transform and fractal dimension theory. Firstly, the registered original images are decomposed using lifting wavelet transform respectively. Then, the decomposition low frequency components are combined by fractal dimension. The decomposition high frequency components are merged by region cross-entropy and energy features. Finally, the composite image is obtained by using inverse lifting wavelet transform. Experimental results demonstrate that the fusion algorithm is more effective in the fused image quality than traditional image fusion method based on wavelet transform. The fused image is suitable to human vision characteristic and is more advantageous to be further analyzed, understood and recognized.