• Title of article

    A Framework for Dry Waste Detection Based on a Deep Convolutional Neural Network

  • Author/Authors

    Ataee, A. Department of Electrical Engineering - Babol Noshirvani University of Technology - Babol, Iran , Kazemitabar, J. Department of Electrical Engineering - Babol Noshirvani University of Technology - Babol, Iran , Najafi, M. Department of Electrical and Computer Engineering - Arak University of Technology - Arak, Iran

  • Pages
    5
  • From page
    248
  • To page
    252
  • Abstract
    Due to lack of proper regulations in many areas of the world, consumers are not mandated to waste sorting at the origin of the source. Moreover, human sorting often suffers from human errors and low accuracy. In the intelligent detection system, it is attempted to break down a variety of household wastes including plastic bottles, glass, metals, paper bags, compact plastics, paper and disposable containers. In this paper, a real waste image system is investigated using the deep convolutional neural network and a remarkable accuracy of 92.76% was achieved.
  • Farsi abstract
    به دليل فقدان مقررات مناسب در بسياري از مناطق جهان، مصرف كنندگان مجبور به مرتب سازي زباله در منبع نيستند. علاوه بر اين، مرتب سازي انسان اغلب از دقت كمي برخوردار است. در سيستم تشخيص هوشمند، سعي در تجزيه انواع زباله هاي خانگي از جمله بطري هاي پلاستيكي، شيشه، فلزات، كيسه هاي كاغذي، پلاستيك هاي فشرده، كاغذ و ظروف يكبار مصرف است. در اين مقاله، يك سيستم تصوير پسماند واقعي با استفاده از شبكه عصبي كانول وشن عميق به دقت قابل توجه 76 / 92 درصد محقق گرديده است.
  • Keywords
    Deep learning , Dry residue , Image processing , Sorting , Transfer learning
  • Journal title
    Iranian Journal of Energy and Environment
  • Serial Year
    2020
  • Record number

    2581027