The Study and Simulation of the Fabric Defects Images Restoration
By using non-negativity and support constraints recursive inverse filtering ,blind image restoration can be realized. But it’s difficult to resolve the proplem of sensitive to noise,so there has been no practical application. In this paper,according to the characteristic of NAS-RIF algorithm and the question of fuzzy by fabric defects images moving at a high-speed line, methods have been introduced, firstly, Adopt boundary keep smoothing filter as the de-noising pretreatment was carried out for image signal; Secondly, in each iteration of restoration,add the low-pass filter link。Thus,the problem of NAS-RIF algorithm is solved well.The simulation results show that this method has a satisfactory outcome both in visual impression and quantitative analysis.
Helen Zhang and David Jin
L. H. Zhang and Y. B. Liang, "The Study and Simulation of the Fabric Defects Images Restoration", Advanced Materials Research, Vol. 382, pp. 88-91, 2012