Abstract

Mango pests consist of various types and it requires classification for prevention and treatment after infection. But for large-scale agriculture or industry, it takes a long time and is more expensive to identify the type of mango pest. Fortunately, Computer Vision can automatically identify the type of mango pest by analyzing previously recognized mango pests. Therefore, this paper proposes various Convolutional Neural Network (CNN) models to identify 15 types of mango pests automatically. This paper also proposes data augmentation to overcome the low number of images in several classes (mango pests). CNN models such as AlexNet, GoogleNet, InceptionV3, ResNet18, ResNet50 can identify mango pests well. By combining the CNN model and data augmentation, this study achieves 99.72% highest accuracy, highest 99.67% sensitivity, and 99.98% highest specificity. These results are better than previous studies.

Original languageEnglish
Title of host publication2022 10th International Conference on Information and Communication Technology, ICoICT 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages88-92
Number of pages5
ISBN (Electronic)9781665481656
DOIs
Publication statusPublished - 2022
Event10th International Conference on Information and Communication Technology, ICoICT 2022 - Virtual, Online, Indonesia
Duration: 2 Aug 20223 Aug 2022

Publication series

Name2022 10th International Conference on Information and Communication Technology, ICoICT 2022

Conference

Conference10th International Conference on Information and Communication Technology, ICoICT 2022
Country/TerritoryIndonesia
CityVirtual, Online
Period2/08/223/08/22

Keywords

  • Classification
  • Convolutional Neural Network
  • Data augmentation
  • Mango pests

Fingerprint

Dive into the research topics of 'Mango Pests Identification Based-on Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this