Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Environmental Microbial & Food Safety Laboratory » Research » Publications at this Location » Publication #385328

Research Project: Sensing Technologies for the Detection and Characterization of Microbial, Chemical, and Biological Contaminants in Foods

Location: Environmental Microbial & Food Safety Laboratory

Title: Analysis of RGB plant images to identify root rot disease in Korean ginseng plants using deep learning

item KUMAR, PRAVEEN - Chungnam National University
item FAQEERZADA, MOHAMMAD - Chungnam National University
item PARK, EUNSOO - Chungnam National University
item KIM, YUN-SOO - Chungnam National University
item JOSHI, RAHUL - Chungnam National University
item AMANAH, HANIM - Chungnam National University
item SULTANA, TUNNY - Chungnam National University
item KIM, HANKI - (NCE, CECR)networks Of Centres Of Exellence Of Canada, Centres Of Excellence For Commercilization A
item NABWIRE, SHONA - Chungnam National University
item BAEK, INSUCK - Orise Fellow
item Kim, Moon
item CHO, BYOUNG-KWAN - Chungnam National University

Submitted to: Applied Sciences
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 2/23/2022
Publication Date: 2/27/2022
Citation: Kumar, P., Faqeerzada, M., Park, E., Kim, Y., Joshi, R., Amanah, H., Sultana, T., Kim, H., Nabwire, S., Baek, I., Kim, M.S., Cho, B. 2022. Analysis of RGB plant images to identify root rot disease in Korean ginseng plants using deep learning. Applied Sciences. 12:2489.

Interpretive Summary: The roots of the ginseng plant have highly valued medicinal properties, but a soil-borne fungal disease commonly called “root rot,” can cause severe damage to the plants and the quality of the roots. An easily implemented and non-destructive method to detect the disease in live plants is needed to help producers maintain crop quality and minimize losses. Computer vision and deep-learning techniques can be used to develop such detection methods. For this study, 136 healthy ginseng plants were grown in sterilized soil and 258 unhealthy plants were grown in soil contaminated with the fungal pathogen, grown from roots planted in pots and maintained under controlled growth chamber conditions. Weekly color images of the plants were taken and used to develop a new image-based deep-learning detection model, as well as to compare results from other deep-learning-based models, for predicting the presence of root rot. Results showed that the proposed new model achieved 93% accuracy in detecting diseased plants in the dataset used—exhibiting higher accuracy with a lower training time requirement compared to the other models. Although additional research is needed to test for detection at earlier stages of plant growth and with the simultaneous presence of other plant stressors in addition to the fungal disease, this work suggests that the method shows great promise for use with live plants that could help producers to minimize or prevent the incidence of root rot in their crops.

Technical Abstract: Ginseng is an important medicinal plant in Korea. The roots of the ginseng plant have medicinal properties; thus, it is very important to maintain the quality of ginseng roots. Root rot disease is a major disease that affects the quality of ginseng roots. It is important to predict this disease before it causes severe damage to the plants. Hence, there is a need for a non-destructive method to identify root rot disease in ginseng plants. In this paper, a method to identify the root rot disease by analyzing the RGB plant images using image processing and deep learning is proposed. Initially, plant segmentation is performed, and then the noise regions are removed in the plant images. These images are given as input to the proposed linear deep learning model to identify root rot disease in ginseng plants. Transfer learning models are also applied to these images. The performance of the proposed method is promising in identifying root rot disease.