Cigarette quality on-line detection device and detection method based on machine vision

Abstract

The invention provides a cigarette quality on-line detection device and a detection method based on machine vision. The detection device comprises a light path detecting unit, an image information processing unit, a control unit and an executing mechanism. The detection method comprises the steps as follows: a white LED light source emits illuminating beams through an optical component, the illuminating beams penetrates through a piece of shielding glass to irradiate on a cigarette advancing at a high speed, and a reflected light generated on the cigarette is focused on the target surface of a high-speed CCD (charge coupled device) line-scan camera through a reflecting mirror and a lens; image information is converted into digital signals through an A / D sampling module and transmitted to the image information processing unit so as to enable the quality of every cigarette to be judged; and the analysis result is transmitted to an upper controller and a PLC ( Programmable Logic Controller) through a CAN bus network, so that defective cigarettes are counted and tracked and then are removed. The cigarette quality online detection device and the detection method can remove unaccepted products on line accurately and deliver qualified products to downstream equipment, thereby greatly improving finished product qualification rate and production rate of a whole production line.

Description

technical field [0001] The invention relates to tobacco machinery, namely a machine vision-based online cigarette quality detection device and detection method. Background technique [0002] Machine vision refers to converting the involved targets into image signals through visual sensors, such as CCD, CMOS and photoelectric sensors, and sending them to a dedicated image processing system. The image processing system performs various operations on these image information to obtain target features, and finally A technique for on-site control based on the results of discrimination. [0003] In the production process of enterprises, due to the fast production speed, the detection tasks become complicated and urgent, and it is difficult to find and eliminate substandard products manually on the production line. At present, the detection method adopted by most factories is manual sampling inspection, which cannot realize online detection. As a result, it is difficult to find un...

AI Technical Summary

Problems solved by technology

[0003] In the production process of enterprises, due to the fast production speed, the detection task becomes complicated and urgent, and it is difficult to find and reject unqualified products on the production line manually.

At present, the detection method adopted by most factories is manual sampling inspection, which cannot realize online detection

As a result, it is difficult to find unqualified products in time during the production process and make timely adjustments, resulting in a large number of unqualified products

Images