Automated visual evaluation of an electrode with neural networks

Abstract: This project was done in cooperation with the company Scibase. Scibase producesa product called Nevisense, which is used to detect skin cancer in a noninvasiveway. The measurements are made with electrical impulses and the electrodethat is in contact with the patients’ skin is only used once. When these electrodesare produced, they must pass visual inspections for each step in their assembly.These visual inspections are done by operators using a traditional microscope.This inspection is both time-consuming and uncomfortable for the operators, e.g.,microscopes strain their eyes and the design of the microscopes are not ergonomic.This project is about the automation of these visual inspections to increase the productionof electrodes and to improve working conditions.To automate this, two parts were needed: images of the electrodes and a way toclassify them as pass or fail. The images were taken with a digital microscope andto be able to get several images at once, a programmable XY-table was used. Theimages were processed with OpenCV, a computer vision library. The classificationof the images was done using a neural network and the accuracy that was achievedwas 99.2%, which is a higher accuracy than the conformity that the operators have.