Based on Local Mean and Variance of Adaptive Pulse Coupled Neural Network Image Fusion

Pulse coupled neural network: PCNN is an algorithm pattern imitating the visual mechanism of living beings, has been widely used in the fields of image processing. As image fusion is the main part of PCNN image processing, the study on how to improve the algorithm performance of image fusion becomes hot. We present adaptive PCNN image fusion method in accordance with PCNN parameter automatic adjustment of local mean and variance. The experimental results show that, in terms of visual quality and objective evaluation, the adaptive PCNN fusion images do better than those in pyramid algorithms of image fusion, principal component analysis fusion method and wavelet transform method, etc. It has also some value on broadening the theoretical study and practical application of PCNN.