Image registration is a challenging NP-hard problem within the computer vision field. The differential evolutionary algorithm is a simple and efficient method to find the best among all the possible common parts of images. To improve the efficiency and accuracy of the registration, a knowledge-fusion-based differential evolution algorithm is proposed, which combines segmentation, gradient descent method, and hybrid selection strategy to enhance the exploration ability in the early stage and the exploitation ability in the later stage. The proposed algorithms have been implemented and tested with CEC2013 benchmark and real image data. The experimental results show that the proposed algorithm is superior to the existing algorithms in terms of solution quality, convergence speed, and solution success rate.

图像配准是计算机视觉领域内具有挑战性的NP难题。差分进化算法是一种简单有效的方法，可以在图像的所有可能的公共部分中找到最佳的。为了提高配准的效率和准确性，提出了一种基于知识融合的差分进化算法，该算法结合了分段，梯度下降法和混合选择策略，提高了早期的勘探能力和后期的开采能力。阶段。所提出的算法已通过CEC2013基准和真实图像数据实施和测试。实验结果表明，该算法在求解质量，收敛速度和求解成功率方面均优于现有算法。