Closed-Loop Restoration Approach to Blurry Images Based on Machine Learning and Feedback Optimization

Blind image deconvolution (BID) aims to remove or reduce the degradations that have occurred during the acquisition or processing. It is a challenging ill-posed problem due to a lack of enough information in degraded image for unambiguous recovery of both point spread function (PSF) and clear image. Although recently many powerful algorithms appeared; however, it is still an active research area due to the diversity of degraded images as well as degradations. Closed-loop control systems are characterized with their powerful ability to stabilize the behavior response and overcome external disturbances by designing an effective feedback optimization. In this paper, we employed feedback control to enhance the stability of BID by driving the current estimation quality of PSF to the desired level without manually selecting restoration parameters and using an effective combination of machine learning with feedback optimization. The foremost challenge when designing a feedback structure is to construct or choose a suitable performance metric as a controlled index and a feedback information. Our proposed quality metric is based on the blur assessment of deconvolved patches to identify the best PSF and computing its relative quality. The Kalman filter-based extremum seeking approach is employed to find the optimum value of controlled variable. To find better restoration parameters, learning algorithms, such as multilayer perceptron and bagged decision trees, are used to estimate the generic PSF support size instead of trial and error methods. The problem is modeled as a combination of pattern classification and regression using multiple training features, including noise metrics, blur metrics, and low-level statistics. Multi-objective genetic algorithm is used to find key patches from multiple saliency maps which enhance performance and save extra computation by avoiding ineffectual regions of the image. The proposed scheme is shown to outperform corresponding open-loop sch- mes, which often fails or needs many assumptions regarding images and thus resulting in sub-optimal results.