Open AccessHYBRID APPROACH OF GARBAGE CLASSIFICATION USING COMPUTER VISION AND DEEP LEARNING
Author(s) -
Anish Tatke,
Madhura Patil,
Anuj Khot,
Parul Jadhav,
Vishwanath Karad
Publication year - 2021
Publication title -
international journal of engineering applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-2143
DOI - 10.33564/ijeast.2021.v05i10.032
Subject(s) - computer science , artificial intelligence , segmentation , deep learning , process (computing) , machine learning , artificial neural network , contextual image classification , image segmentation , convolutional neural network , image (mathematics) , pattern recognition (psychology) , operating system
As waste segregation becomes animportant issue in our lives, with the use oftechnology like deep neural networks andcomputer vision, we can make the process efficientand robust by image segmentation andclassification. These systems on the rise needaccurate and efficient segmentation andrecognition mechanisms and this demand coincideswith the increase of computational capabilities ofmodern computer architectures and more effectivealgorithms for image recognition. This paper doesa comparative analysis of various differentapproaches and methods like Simple CNN,ResNet50, VGG16, etc in brief. The comparativeanalysis and study explains the performance ofevery approach, this paper concludes thatResNet50 gives excellent performance. VGG16network also provides good performance whichmeets the needs of daily use.