Open AccessHerbal plant recognition using deep convolutional neural network
Author(s) -
Izwan Asraf Md Zin,
Zarina Bibi İbrahim,
Dino Isa,
Sharifah Aliman,
Nurbaity Sabri,
Nur Nabilah Abu Mangshor
Publication year - 2020
Publication title -
bulletin of electrical engineering and informatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.251
H-Index - 12
ISSN - 2302-9285
DOI - 10.11591/eei.v9i5.2250
Subject(s) - convolutional neural network , identification (biology) , deep learning , computer science , artificial intelligence , pattern recognition (psychology) , plant identification , machine learning , artificial neural network , botany , biology
This paper investigates the application of deep Convolutional Neural Network (CNN) for herbal plant recognition through leaf identification. Traditional plant identification is often time-consuming due to varieties as well as similarities possessed within the plant species. This study shows that a deep CNN model can be created and enhanced using multiple parameters to boost recognition accuracy performance. This study also shows the significant effects of the multi-layer model on small sample sizes to achieve reasonable performance. Furthermore, data augmentation provides more significant benefits on the overall performance. Simple augmentations such as resize, flip and rotate will increase accuracy significantly by creating invariance and preventing the model from learning irrelevant features. A new dataset of the leaves of various herbal plants found in Malaysia has been constructed and the experimental results achieved 99% accuracy