TY - GEN
T1 - Classification of Capsicum Frutescens Health Condition Through Features Extraction from NDVI Values Using Image Processing
AU - Puteh, Suhaimi
AU - Rodzali, Nurul Fadhilah Mohamed
AU - P. P. Abdul Majeed, Anwar
AU - Khairuddin, Ismail Mohd
AU - Ibrahim, Zelina Zaiton
AU - Razman, Mohd Azraai Mohd
N1 - Funding Information:
Acknowledgement. The authors would like to acknowledge Universiti Malaysia Pahang for funding this study under the Research Grant (RDU200332).
Publisher Copyright:
© 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2021
Y1 - 2021
N2 - Normalised Difference Vegetation Index (NDVI) is one indicator to measure the health of the plant condition. There is no application to monitor the plant condition based on the NDVI system on a smaller scale and low-cost production. Thus, this research was conducted where three objectives are presented and discussed. The first and second objectives are developing NDVI images and identifying and extracting NDVI images features, respectively. The third objective is the evaluation performance of machine learning (ML) models on the classification of chilli plant’s health, which are Support Vector Machine (SVM), k-Nearest Neighbour (k-NN), and Random Forest (RF). The chilli plant images will be captured by using two types of camera, whereby the camera is distinguished by having an infrared (IR) filter or non-IR filtered. The classification accuracy of classifiers was conducted on the datasets using the extracted data. In conclusion, the RF model was found to provide the best classification accuracy with 97.6% and 94.4% on training and test datasets, respectively.
AB - Normalised Difference Vegetation Index (NDVI) is one indicator to measure the health of the plant condition. There is no application to monitor the plant condition based on the NDVI system on a smaller scale and low-cost production. Thus, this research was conducted where three objectives are presented and discussed. The first and second objectives are developing NDVI images and identifying and extracting NDVI images features, respectively. The third objective is the evaluation performance of machine learning (ML) models on the classification of chilli plant’s health, which are Support Vector Machine (SVM), k-Nearest Neighbour (k-NN), and Random Forest (RF). The chilli plant images will be captured by using two types of camera, whereby the camera is distinguished by having an infrared (IR) filter or non-IR filtered. The classification accuracy of classifiers was conducted on the datasets using the extracted data. In conclusion, the RF model was found to provide the best classification accuracy with 97.6% and 94.4% on training and test datasets, respectively.
KW - Chilli
KW - Features extraction
KW - Machine learning
KW - NDVI
UR - https://www.scopus.com/pages/publications/85113755416
U2 - 10.1007/978-981-16-4803-8_41
DO - 10.1007/978-981-16-4803-8_41
M3 - Conference Proceeding
AN - SCOPUS:85113755416
SN - 9789811648021
T3 - Lecture Notes in Mechanical Engineering
SP - 414
EP - 423
BT - RiTA 2020 - Proceedings of the 8th International Conference on Robot Intelligence Technology and Applications
A2 - Chew, Esyin
A2 - P. P. Abdul Majeed, Anwar
A2 - Liu, Pengcheng
A2 - Platts, Jon
A2 - Myung, Hyun
A2 - Kim, Junmo
A2 - Kim, Jong-Hwan
PB - Springer Science and Business Media Deutschland GmbH
T2 - 8th International Conference on Robot Intelligence Technology and Applications, RiTA 2020
Y2 - 11 December 2020 through 13 December 2020
ER -