A Variable-Gain Fixed-Time Convergent and Robust ZNN Model for Image Fusion: Design, Analysis, and Verification

Image fusion can obtain the superior information and reduce the noise in the source image by designing a specific scheme. However, the noise in image fusion has been a difficult issue and hard to handle. In this article, a variable-gain fixed-time convergent and robust zeroing neural network (VFCR-ZNN) model is proposed to figure out the image fusion problem and the corresponding quadratic programming (QP) problem. In contrast to the original zeroing neural network model, the VFCR-ZNN model adopts a novel fixed-time activation function and a useful variable-gain parameter, which allows the VFCR-ZNN model to converge faster in fixed-time and realize noise immunity under external disturbance. The detailed theory is provided to support this point. Different numerical QP comparative examples are carried out to effectively corroborate the rightness of the theoretical analyses and the excellence of the VFCR-ZNN model. Additionally, the quality of fused images acquired by the VFCR-ZNN model is higher compared to existing state-of-the-art models for image fusion. Furthermore, the VFCR-ZNN model is successfully utilized in the repetitive motion of six-link robot manipulator to demonstrate its significant practical implications.