Method for fast count and integrality detection of tablets under complex environment

Abstract

The invention discloses a method for fast count and integrality detection of tablets under a complex environment. The method comprises the steps of obtaining images of some whole tablets by an industrial camera, calculating the size and the Hu moment of each standard tablet, and taking the average area and the average Hu moment of the tablets as standard parameters of tablets of the same batch; collecting images of tablets to be detected by the industrial camera, performing local illumination compensation on the images through histogram equalization, determining a mean value template and a sharpening template according to the standard area size and performing convolution operation on the templates and the images in order to complete processing the images under the complex environment; performing threshold segmentation on the preprocessed images to obtain the area and the Hu moment of each outline; removing pseudo tablet data; and comparing the detected parameters of each tablet with the standard parameters and identifying damaged tablets and distorted tablets according to judgement to complete detection. The method is simple and convenient to operate, good in stability and suitablefor a production line of tablets with different shapes of the same batch.

Description

technical field [0001] The invention relates to the technical field of machine vision detection, in particular to a method for rapid counting and integrity detection of tablets in a complex environment. Background technique [0002] In the process of tablet production, it is an indispensable link to check the tablets. The traditional manual visual inspection process is complicated and inefficient, which can no longer meet the requirements of the modern pharmaceutical industry. Visual measurement technology has the remarkable characteristics of non-contact, strong flexibility, and high integration. It has broad application prospects in the modern pharmaceutical industry and has become a research hotspot. In recent years, researchers at home and abroad have done a lot of research work in the field of machine vision technology applied to the pharmaceutical industry, and developed some visual inspection systems related to drug quality inspection, such as the Seidenader XS syste...

AI Technical Summary

Problems solved by technology

[0003] However, the above-mentioned detection system has higher requirements on the application environment, and better application results can only be achieved in an environment with less interference from water mist, dust, etc., and basically uniform lighting conditions.

Images