Closed-loop feedback registration for consecutive images of moving flexible targets

Advancement of imaging techniques enables consecutive image sequences to be acquired for quality monitoring manufacturing production lines. Registration these is essential in-line pattern inspection and metrology, e.g., in the printing process flexible electronics. However, conventional registration algorithms cannot produce accurate results when images contain duplicate deformable patterns process. Such a failure originates from fact that only use spatial pixel intensity information registration. Considering nature temporal continuity product images, this paper, we propose closed-loop feedback algorithm. The algorithm leverages relationships fast, accurate, robust point matching. experimental show our finds about 100% more matching pairs with lower root mean squared error reduces up 86.5% running time compared other state-of-the-art outlier removal algorithms.