基于监督学习的Takagi Sugeno Kang模糊系统图像融合方法研究

A Novel Image Fusion Method Using the Takagi Sugeno Kang Fuzzy System Based on Supervised Learning

该文针对图像融合领域内难于对先验知识加以利用的问题提出一种新的有监督学习的Takagi Sugeno Kang(TSK)模糊系统图像融合方法。该方法通过引入TSK模糊系统构建标准图像融合图像库进行学习,将学习准则记录下来形成融合模型,并指导新的图像融合过程。不同于传统方法,该方法可以有效地避免模型参数择优的难题,在融合图像质量和适用范围方面表现出一定的优势。从单一类型图像融合和多种类型图像融合两个角度进行了实验研究,实验结果说明该方法的有效性。

A novel image fusion method based on supervised intelligent learning is proposed in order to overcome the difficulty in the use of priori knowledge in image fusion. In this study, the images database for supervised learning is first constructed,then the model parameters trained with the available training datasets are used for the Takagi Sugeno Kang （TSK） fuzzy system model. Different from the classical method that needs to manage the different parameters setting manually, the proposed method can effectively preclude the problem in the optimal parameters setting. Meanwhile, some advantages are displayed in the fusion image quality and adaptation. The experimental studies on different types of images, both single and multi, also show the effectiveness of the method.