Drug identification system based on deep learning and implementation method thereof

Abstract

The invention discloses a drug identification system based on deep learning and an implementation method thereof, the drug identification system comprises a drug identification system body, and the drug identification system body comprises: a picture acquisition module used for collecting drug picture information; a detection segmentation module used for calculating the accurate position of each medicine and segmenting the medicines one by one; a controller used for receiving the feedback information, receiving the comparison information, receiving the medicine list information and sending a control instruction; an identification module used for identifying characters, texts and picture information of the medicine box and accurately identifying the types of the medicines and the number ofeach type; and a comparison module used for comparing the medicine information with the medicine list of the patient. According to the drug identification system based on deep learning and the implementation method thereof, the types and the number of drugs can be automatically and accurately identified, and the drug placing speed of a pharmacy is increased; and meanwhile, the manual operation process is replaced, and the probability of errors caused by manual drug dispensing is reduced while the labor cost is reduced.

Description

technical field [0001] The invention relates to the technical field of drug identification, in particular to a drug identification system based on deep learning and its implementation method. Background technique [0002] With the rapid development of the pharmaceutical industry, there are a wide variety of drugs on the market. Most hospitals have thousands of drugs, and the same drug has different specifications and dosages in many forms. [0003] In hospitals where medicines are still manually selected and dispensed, at the hospital’s medicine collection window, a staff member is required to confirm whether the types and quantities of medicines are correct before finally giving the medicines to patients. Misreading of prescriptions transmitted by (HIS) and similar drug packaging or confusing drug additions increase the workload of pharmacists and the probability of drug delivery errors. [0004] To this end, we propose a drug recognition system and its implementation meth...

AI Technical Summary

Problems solved by technology

[0003] In hospitals where medicines are still manually selected and dispensed, at the hospital’s medicine collection window, a staff member is required to confirm whether the types and quantities of medicines are correct before finally giving the medicines to patients. (HIS) transmission of misreading of prescriptions and similar drug packaging or confusing drug additions, etc., which increases the workload of pharmacists and the probability of drug delivery errors

Images