Open AccessArtificial vision system for object classification in real time using Raspberry Pi and a Web camera
Author(s) -
Tomás Serrano-Ramírez,
Ninfa del Carmen Lozano-Rincón,
Arturo Mandujano-Nava,
Yosafat Jetsemaní Sámano-Flores
Publication year - 2021
Publication title -
revista de tecnologías de la información y comunicaciones
Language(s) - English
Resource type - Journals
ISSN - 2531-2200
DOI - 10.35429/jitc.2021.13.5.20.25
Subject(s) - artificial intelligence , raspberry pi , computer science , computer vision , automation , software , machine vision , object detection , identification (biology) , haar like features , object (grammar) , pattern recognition (psychology) , engineering , embedded system , operating system , face detection , mechanical engineering , botany , facial recognition system , biology , internet of things
Computer vision systems are an essential part in industrial automation tasks such as: identification, selection, measurement, defect detection and quality control in parts and components. There are smart cameras used to perform tasks, however, their high acquisition and maintenance cost is restrictive. In this work, a novel low-cost artificial vision system is proposed for classifying objects in real time, using the Raspberry Pi 3B + embedded system, a Web camera and the Open CV artificial vision library. The suggested technique comprises the training of a supervised classification system of the Haar Cascade type, with image banks of the object to be recognized, subsequently generating a predictive model which is put to the test with real-time detection, as well as the calculation for the prediction error. This seeks to build a powerful vision system, affordable and also developed using free software.