Surface defect detection of plaster coating based on machine vision

As a kind of traditional Chinese Medicine, plaster has been favored by more and more patients because of its unique advantages in the treatment of diseases. For the coating of plaster, its quality is very important to the plaster. Therefore, coating surface defect detection is very necessary. The current mainstream detection method is manual inspection, there are many disadvantages in this, such as extremely low efficiency and bad for health. In light of this situation, a set of plaster coating quality automatic detection system based on machine vision has been proposed in this paper. Through a detailed analysis of the coating defects, a set of image detection algorithms have been given. It can be found from the experimental results that the algorithm can identify the type of defects and locate the position precisely. The error detection rate is low, and the robustness is good.

I. Introduction

Plaster is a traditional Chinese medicine which is for outward application only. It belongs to the transdermal drug delivery system (TDDS) and is popular because of its unique treatment methods [1]. The quality of the plaster coating will influence the adhesion and use of the drug, so the quality of the coating determines the quality of the plaster. The current detection means for plaster coating is mainly artificial detection, which makes the process of detection is very subjective, some relatively small defects is not easy to be detected, and the artificial detection makes the work efficiency very low, and the plant environment is generally poor, which is not conducive to the health of workers [2]–[4]. Therefore, it is necessary to design a set of automatic quality inspection system for plaster coating.