Automatic plant recognition using convolutional neural network on malaysian medicinal herbs: the value of data augmentation

Noor Aini Mohd Roslan (School of Computing Sciences, College of Computing, Informatics and Media, Universiti Teknologi MARA)
Norizan Mat Diah (School of Computing Sciences, College of Computing, Informatics and Media, Universiti Teknologi MARA)
Zaidah Ibrahim (School of Computing Sciences, College of Computing, Informatics and Media, Universiti Teknologi MARA)
Yuda Munarko (Informatics Department, Universitas Muhammadiyah Malang)
Agus Eko Minarno (Informatics Department, Universitas Muhammadiyah Malang)

International Journal of Advances in Intelligent Informatics
Vol 9, No 1 (2023): March 2023

Herbs are an important nutritional source for humans since they provide a variety of nutrients. Indigenous people have employed herbs, in particular, as traditional medicines since ancient times. Malaysia has hundreds of plant species; herb detection may be difficult due to the variety of herb species and their shape and color similarities. Furthermore, there is a scarcity of support datasets for detecting these plants. The main objective of this paper is to investigate the performance of convolutional neural network (CNN) on Malaysian medicinal herbs datasets, real data and augmented data. Malaysian medical herbs data were obtained from Taman Herba Pulau Pinang, Malaysia, and ten kinds of native herbs were chosen. Both datasets were evaluated using the CNN model developed throughout the research. Overall, herbs real data obtained an average accuracy of 75%, whereas herbs augmented data achieved an average accuracy of 88%. Based on these findings, herbs augmented data surpassed herbs actual data in terms of accuracy after undergoing the augmentation technique.