Research progress on key technologies of pharmaceutical intelligent manufacturing production line

GE et al. modeled the moving target in the liquid medicine, combined with the acquired sequence frame images to achieve feature extraction of the foreign object, and finally proposed the online sequential extreme learning machine (OS-ELM) based on space. Thus the classification of foreign bodies in liquid medicine is realized. In addition, ZHANG et al. [22] proposed a particle tracking and classification algorithm based on the adaptive local weighted collaborative sparse model (ALW-CSM). An automatic liquid particle detection system for injection is designed, which has better performance than OS-ELM algorithm. Aiming at the interference of bubbles on the detection of visible foreign bodies, Wang Yuqing et al. [24] proposed to take the region of interest of image sequence as the object. Firstly, using frame difference method, the image most likely to contain foreign bodies in image sequence was found as the start frame image, and the moving object in the start frame image was found to establish the initial template. Then, ECO(efficiency convolution operators) algorithm is used to track the moving target, record its trajectory and analyze its motion characteristics, so as to identify whether the target is a foreign body.