Author(s)

Tianze Zheng, Zhongxuan Zhang, Hekai Zhang

Corresponding Author

Tianze Zheng

ABSTRACT

In order to solve the problems of serious loss of detail and poor visual effect in the process of medical image fusion, a pulse coupled neural network medical image fusion algorithm based on non-subsampled contour transform and discrete wavelet transform is proposed in this paper. First of all, the medical source image is transformed by non-subsampling contour transform, and the corresponding low-frequency and high-frequency subbands are obtained, and the low-frequency subbands are transformed by discrete wavelet transform. Then, the pulse coupled neural network is used to fuse the low frequency subband, and the average gradient and the improved Laplace energy sum are taken as the input items of the pulse coupled neural network, and the fusion method of information entropy and matching degree is used for the high frequency subband. Finally, the fused low-frequency subband and high-frequency subband images are transformed by multi-scale inverse transform to get the fused image. The experimental results show that this method can effectively improve the contrast of the fused image and retain the details of the source image, and has excellent performance in both subjective and objective evaluation.

KEYWORDS

Image fusion, non-subsampled contour transform, discrete wavelet transform, pulse coupled neural network