Computer Vision Control System for Food Industry

Abstract

Defects in production can appear as a result of material and human errors. A food product with a defect may be the cause of direct and indirect losses caused by product recalls, logistic problems, destruction of defective products, reputation issues, possible penalties, etc. The purpose of this work is to minimize the human intervention and substitute it to the maximum extent with an automatic inspection system based on the artificial vision technology that will carry out the inspection task. To do so, the main functions of the system had to be elaborated in a specification. Examples of the inspection functions are barcode reading, label verification, content level checking, etc. Each function is performed and tested independently. The tests carried out made it possible to record the conditions necessary for the execution of each inspection, which is an indispensable factor in achieving the appropriate physical design. These functions are grouped in a single application with three interfaces (login, inspection and configuration). It allows the user to inspect the products according to a configuration that he can define. This work was developed based on National Instrument platform, the software code was made with LabVIEW software, which resources and libraries are adequate for such a work.