Weighted truncated nuclear norm regularization for low-rank quaternion matrix completion

In recent years, quaternion matrix completion (QMC) based on low-rank regularization has been gradually used in image processing. Unlike (LRMC) which handles RGB images by recovering each color channel separately, QMC models retain the connection of three channels and process them as a whole. Most existing quaternion-based methods formulate (LRQMC) nuclear norm (a convex relaxation rank) minimization problem. The main limitation these approaches is that they minimize singular values simultaneously such cannot approximate attributes efficiently. To achieve more accurate approximation, we introduce truncated (QTNN) for LRQMC utilize alternating direction method multipliers (ADMM) to get optimization this paper. Further, propose weights residual error during update accelerating convergence QTNN with admissible performance. weighted utilizes concise gradient descent strategy theoretical guarantee optimization. effectiveness our illustrated experiments real visual data sets. • A novel proposed An efficient developed solve method. add matrices optimization, guarantee.