|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Environmental pollution by garbage is a biggest problem of most of the developing country, garbage waste processing management and recy-cling is significant for ecological and economic reasons. computer vision techniques are very advance in many application for object detection and classification, we did an extensive study on the use of artificial intelligence for garbage processing and management and it is lagging because of dataset availability which have the top view images of garbage. We create a new da-taset ‘KACHARA’ which have 4727 images of seven classes Cloths, Decom-posable, Glass, Metal, Paper, Plastic, and Woods. Classification is performed by the transfer learning by popular Deep learning mode MobileNetv3 large with fine tuning the top layers. And archive the classification accuracy of 94.37
Keyword
Deep learning, Object classification, Object detection, Transfer learning, Aerial Images.
PDF Download (click here)
|
|
|
|
|