Method for detecting, tracking and recognizing movement visible exogenous impurity in medicine liquid

Abstract

The invention discloses a detecting and recognition method of moveable and visible foreign matters and bubbles in liquid medicines, which is characterized in that the method comprises the following steps: (1) a continuous multi-frame image of a liquid medicine to be detected is obtained; (2) the image is preprocessed; (3) a moveable object is extracted, and a reinforced image is obtained; (4) the moveable object is partitioned as follows: an improved two-dimensional maximum entropy threshold partitioning algorithm is applied into the processing of the reinforced image and a two-dimensional histogram that is formed by grayscale and average neighborhood grayscale is adopted for choosing threshold, thus obtaining a partitioned image; (5) the movable object is traced; and (6) the image is identified and determined as follows: a movement trace of the object is obtained according to the tracing result, objects inducing foreign matters and bubbles are identified and distinguished by utilizing the continuity and the directivity of the object movement trace, and consequently whether the liquid medicine is qualified is finally determined. Under the condition of ensured algorithm precision, the detecting and recognition method of moveable and visible foreign matters and bubbles in liquid medicines adequately simplifies computation, improves the real-time property of the algorithm, greatly raises the accuracy of foreign matter and bubble identification in the liquid medicine, and lowers the false detection rate of the medicine.

Description

technical field [0001] The invention belongs to the technical field of image processing and automation, and relates to a method for detecting and identifying moving visible foreign matter and air bubbles in liquid medicine. Background technique [0002] At present, liquid medicines widely used in my country include injections, infusions, oral solutions, eye drops, etc., and are usually filled in the form of glass or plastic bottles. These medicines are poorly filtered and the containers are not cleaned during the production process. Visible foreign matter such as glass shavings, suspended solids, hair, etc. will exist in the drug liquid due to reasons such as good, collision during packaging, etc. In order to detect whether visible foreign matter is mixed in the filled liquid drug, it is necessary to carry out visible foreign matter detection on each bottle of drug. Since 1985, the Chinese Pharmacopoeia has stipulated that the detection of such drugs should be carried out by ...

AI Technical Summary

Problems solved by technology

Inevitable problems such as low efficiency, high missed detection rate, and low precision in manual detection, poor repeatability and consistency of detection results, and long-term detection work also bring harm to the health of light inspection personnel.

With the promotion of GMP certification, the automation and intelligence level of my country's pharmaceutical production equipment and testing equipment has been greatly improved. Semi-automatic light inspection machines and full-automatic light inspection machines for the detection of visible foreign matter in drugs have appeared, among which semi-automatic light inspection The machine adopts simple mechanical transmission and optical system to realize the semi-automation of manual light inspection. This detection device can reduce manual labor to a certain extent, but still through the analysis and judgment of light inspection workers, the detection accuracy and accuracy have not been improved.

Only a few companies in a few countries such as Germany, Japan, and Italy are capable of producing fully automatic light inspection machines. However, foreign automatic light inspection machines are still rarely used in my country. The reasons are as follows: the domestic pharmaceutical sector There are great differences in filtration, packaging materials, etc. in foreign countries, resulting in low quality of detection

[0004] 1. The size of the foreign matter is different, and the detection resolution must reach 50um. The foreign matter target has no information such as size, shape and texture, so traditional image processing methods cannot be applied;

[0005] 2. Due to the scale relief and spots on the surface of the bottle, the background of the image after imaging is complex and the noise is diverse;

[0006] 3. The signal-to-noise ratio in the image is low, and the foreign objects are often submerged in the background noise;

[0007] 4. The detection speed of the production line is high, which puts forward high requirements for the real-time performance of the recognition algorithm

Images