Method for realizing automatic detection of medicine labels based on machine vision

Abstract

The invention discloses a method for realizing automatic detection of medicine labels based on machine vision, which comprises the steps of image acquisition, label positioning, label content identification and judgment. The label content identification and judgment step comprises identification and judgment of label colors, identification and judgment of label invariable contents and identification and judgment of label variable contents. The specific operation of identifying and judging the variable content of the label comprises manufacturing a prior template, carrying out binarization segmentation processing on a variable region image, carrying out character identification by adopting a neural network, outputting an identification result by using a softmax classifier, and judging and outputting a detection result according to whether the identification result is consistent with a comparison content which is manually input in advance. By adopting the method disclosed by the invention, automatic identification, detection and judgment of colors, appearance defects and text contents of the medicine labels can be realized, and the method has the advantages of high automation degree, high detection speed, high precision and the like.

Description

technical field [0001] The invention relates to a method for realizing automatic detection of drug labels based on machine vision, and belongs to the technical field of automatic visual detection. Background technique [0002] As an integral part of drug packaging, drug labels play a very important role in all aspects of drug quality requirements, especially in the process of use, usually including drug name, model specification, usage and dosage, production batch number, production date, expiration date, etc. Information has become an effective carrier for enterprises to track products, quality control and production management, and it is also an effective tool for consumers to understand drugs. [0003] Due to the influence of many uncertain factors such as production process, environment and equipment in the modern rapid printing production process of pharmaceutical labels, various printing defects and errors are unavoidable. If unqualified drug labels flow into the mark...

AI Technical Summary

Problems solved by technology

In the actual production process, the detection of drug labels not only includes the detection of label color and appearance defects, but also the detection of printing errors in text content, especially for the same drug label, although the drug name, model specification, usage The information such as dosage and production company is fixed, but the production batch number, production date, expiration date and other information will continue to change. If the single template matching method in the above-mentioned prior art is used for detection, the template needs to be replaced frequently. Not only will it lead to low detection efficiency and accuracy, but it will also lead to high detection costs. Therefore, this technology has not been widely used in actual production so far.

Images