Vision-Based System to Detect Antistatic Gloves and Antistatic ESD Protection in Laboratory

Abstract

The usage of ESD safety equipment is a growing issue while manipulating sensitive electronic devices and equipment. We propose an ESD equipment detection model to monitor lab workers for the presence of ESD protective gear. The proposed approach is realized with the help of a camera and a CPU. Using computer vision and machine learning techniques, including feature identification and description using SIFT, we can identify the ESD protection safety measures. The feature vector is optimized with K-Means and principal component analysis. Decision Trees and SVM classifiers are used to achieve accurate classification with these refined feature vectors. The suggested approach is a highly effective way of determining whether or not laboratory staff take appropriate ESD safety measures.