Image fusion of the feature level based on quantum-behaved particle swarm optimization algorithm

Abstract

A new image fusion algorithm of the feature level is proposed incorporating with quantum-behaved particle swarm optimization algorithm (QPSO) clustering in this paper. Wavelet decomposition is performed on the source images, clustering algorithm that incorporates the fuzzy C-means (FCM) into QPSO algorithm (QPSO-FCM) is developed to segment the image in the feature space formed by multi-channel Gabor filters, and then the weighting factors are constructed. Finally, the fused image is obtained by taking inverse wavelet transform. The QPSO has less parameters and higher convergent capability of the global optimization. So QPSO-FCM has a strong global searching capacity and avoids the local minimum problems of FCM. The performance of the image fusion method is evaluated using five criteria including root mean square error, peek-to-peek signal-to-noise ratio, entropy, cross entropy and mutual information. Owing to the improved the clustering effect, the evaluation results indicate that the proposed algorithm outperforms the image fusion algorithm based on FCM.