Foreign Particle Inspection for Infusion Fluids via Robust Dictionary Learning

Complicated sequential images acquired from the automatic particle inspection machine are used to extract tiny objects within bottled medical liquid on pharmaceutical production line. We propose a learning-based inspection method based on the theory of sparse representation and dictionary learning, which converts the inspection problem into background modeling. As discussed in the paper, the way of learning the dictionary is critical to the success of background modeling in our method. To build a correct background model when training samples contain foreign particles, illumination variation and outliers, we propose a robust dictionary learning algorithm and use online dictionary update method. It automatically prunes foreign particle pixels out at the learning stage. Experiments in both qualitative and quantitative comparisons with competing methods demonstrate the obtained robustness against background changes and better performance in foreign particle inspection.