Intelligent visual detection system of foreign matters and bubbles in liquid based on deep learning algorithm

Abstract

An intelligent visual detection system of foreign matters and bubbles in a liquid based on a deep learning algorithm is disclosed. The system comprises a plurality of work stations, a plurality of light sources, a plurality of industrial cameras, an image acquisition module, an image preprocessing and screening module, a packet forwarding module, a two-stage classification module and a classification result statistics module. In the invention, a liquid bottle in motion after spinning is creatively and directly detected on an assembly line, and a step of sudden stop after rotation of an infusion bottle is removed so that a lamp inspection machine hardware circuit design can be simplified, and time losses are reduced and a detection speed is increased because sudden stop after rotation and photographing are not needed. A detection method after a bottle body is horizontally placed is created for the first time, a foreign matter detection probability is greatly improved, a good detection effect on a floating foreign matter is achieved, multiple cameras and multiple stations are used, internal and external all-around detection of the infusion bottle is achieved, in addition, one stationis independently used for detecting the foreign matter rapidly sinking to the bottom, and the detection effect can reach 100%.

Description

technical field [0001] The invention relates to the technical field of intelligent visual detection, in particular to an intelligent visual detection system for foreign matter and air bubbles in liquid based on deep learning algorithm. Background technique [0002] In recent years, the types and quantities of traditional Chinese medicine oral liquids on the market have grown rapidly. However, the visible foreign matter detection method currently studied is mainly the traditional static detection method of larger infusion bottles and ampoules. The body of the traditional Chinese medicine liquid bottle is small, and the equipment that continues to move on the assembly line after spinning has already been realized in manufacturing. However, the corresponding detection technology of impurities in the liquid liquid bottle in the linear motion on the assembly line has not kept up with the pace of research. [0003] At present, most of them are still in the stage of manual detecti...

AI Technical Summary

Problems solved by technology

[0010] (2) Lettering, dents, etc. on the bottle wall will occasionally block foreign objects, causing recognition errors;

[0011] (3) Due to the influence of machining accuracy, the bottle containing the liquid medicine will move during the imaging process, increasing the detection

Due to the requirements of detection speed, on the one hand, the number of acquired image frames is limited, and on the other hand, the application of advanced detection algorithms is also limited.