Method for recognizing foreign matters in bottle-packed oral liquid

Abstract

The invention discloses a method for recognizing foreign matters in bottle-packed oral liquid, and the method comprises the steps: carrying out the binarization processing of a preprocessed image; dividing the oral liquid into an upper region and a lower region, and setting threshold values for the imaging areas S, perimeters and minimum bounding matrix length-width ratios of the upper and lower regions; and judging whether the upper and lower regions have the visible foreign matters or not according to the relation of the parameters and threshold values. The method is high in precision, is good in stability, and solves a problem of recognition errors caused by the recognition of the foreign matters based on a single parameter. The distinguishing detection can achieve the effective detection of plant fibers, residuals and hairs, and also can achieve the accurate detection of the small foreign matters with a certain mass in irregular motion, and can effectively eliminate the interference caused by the bubbles. The method provided by the invention is low in equipment cost, is simple and efficient in processing algorithm, can detect various types of foreign matters, and can meet the requirements of the online production.

Description

technical field [0001] The invention belongs to the technical field of image processing and automation, and in particular relates to a method for identifying visible foreign matter in bottled oral liquid. Background technique [0002] In recent years, the output and sales volume of oral liquid of traditional Chinese medicine in my country is growing at an astonishing rate. Various brands of oral liquid are emerging in an endless stream, and the competition among manufacturers is becoming more and more intense. However, as the types and quantities of oral liquids continue to increase, the quality requirements for oral liquids also continue to increase, because impurities such as glass chips, plant fibers, residues, hair, and white spots are inevitably mixed in during the extraction process. . In order to ensure that such oral liquids do not harm human health, strict production process requirements and industry quality inspection standards have always been imposed on their qu...

AI Technical Summary

Problems solved by technology

[0005] (1) There are many kinds of visible foreign matter particles that may exist in oral liquid bottles, such as glass chips, plant fibers, residues, hair, soil, etc. Due to the difference in physical appearance and internal structure, different identification parameters need to be used. Current algorithms usually rely on a single parameter for identification, which is prone to missed and false detections

[0006] (2) There are scales and spots on the surface of the oral liquid bottle. The background of the image after imaging is complex and the noise is diverse. It is impossible to quickly judge genuine products and defective products, which often leads to detection errors and unsatisfactory results.

[0007] (3) Impurities with a certain quality, such as glass slag, always sink to the bottom during the rotation of the oral liquid bottle, and the generated air bubbles appear in the upper part of the bottle, which is easy to cause interference in the identification, resulting in false detection and missed detection. occur

Images