Real Time Machine Vision System for Quality Assurance of Canned TunaJulio Martín-Herrero, José L. Alba-Castro,Signal Theory and Communications Department, University of Vigo AbstractWe describe a PC-based real time machine vision system for the quality assurance of canned tuna at a tin rate over 1,000 tins per minute, allowing the inspection of the tin and its contents, with two main purposes: preventing defective tins from damaging the closure equipment or from reaching the market with a defective closure, and deviating from the production line tins with low quality content: bruised or darkened areas, excessive percentage of crumb, presence of strange bodies, or partially filled tins, such that they may be fixed and reintroduced in the line without wasting any oil or sauce. The system comprises a iPentium PC with frame grabber, a greyscale line scan CCD camera, a fibre optic halogen lighting system, and a compressed air system for the deviation of the rejected tins, and has been entirely programmed in C++.Keywords:Machine vision, quality assurance, real time image analysis.1. INTRODUCTIONThe canned tuna production lines are usually completely automated except for the visual inspection for quality assurance (QA hereafter). This critical task is being performed by a person that keeps an eye on a production line carrying a tin flow of about 300 tins per minute while reaching from time to time for a defective tin and, at the same time, rearranging and/or refilling some rejected tins. It is obvious that the automation of this obsolete and subjective inspection task would increase the robustness and consistency of the quality control while reaching higher overall production performance. Two main restrictions affect the design of an automatic inspection system: the canned fish industry is, on one side, a very demanding environment for electronic equipment, due to highly saline moisture, vibration, and electrical and mechanical noise; on the other, it operates at very high production speed, so any automatic system should assure tin rates well over the typical lines with manual QA. We describe a PC-based real time machine vision system for the automatic inspection of canned tuna at a tin rate over 1,000 tins per minute. Section 2 is devoted to the description of the selected equipment, section 3 gives the details of the software that governs the visual inspection, and section 4 ends with some conclusions.
本文来源：https://www.2haoxitong.net/k/doc/12952f6b011ca300a6c390af.html
