Open AccessClean Our City: An Automatic Urban Garbage Classification Algorithm Using Computer Vision and Transfer Learning Technologies
Author(s) -
Yuke Chen,
Wendi Han,
Jizhi Jin,
Hao Wang,
Qiaochu Xing,
Yiwen Zhang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1994/1/012022
Subject(s) - garbage , computer science , set (abstract data type) , algorithm , field (mathematics) , data set , scale (ratio) , artificial intelligence , test set , data mining , statistical classification , transfer of learning , machine learning , image (mathematics) , database , mathematics , physics , quantum mechanics , pure mathematics , programming language
To improve the quality of human life in the city, the first thing to solve is the problem of urban garbage. So far, the best way to solve this problem is garbage classification. At present, many algorithms have been put forward one after another. Previous research proposed some computer vision systems to solve the problem of urban garbage classification. In recent years, with the development of computer hardware and large-scale data sets, the algorithm based on depth learning has shown superior performance in the field of image classification. Thus, the features designed by traditional methods are gradually replaced, which far exceed these traditional image classification algorithms in classification accuracy. This study proposes an algorithm based on InceptionV3 networks and test the algorithm on a large-scale garbage classification data-set. The data set was divided into 80% training sets, 10% validation set, and 10% test set and use the transfer learning approach. The model achieved an accuracy of 93.125%, which solved image garbage classification very well. What is more, the algorithm can play an important role in the medical area and help control the mechanical arm.