Detection of Bacterial Spot Disease in Bell Pepper Plant Using YOLOv3

Abstract

In countries like India, diseases in plants are a major concern in the agricultural sector. Crop loss due to diseases led to reduction in the quality and quantity of agricultural products. This also leads to economic losses. Hence, timely monitoring of plants is necessary. But monitoring diseases in large fields is a difficult task. To overcome this problem, effective management strategies should be taken to control diseases in plants. It can be done by acquiring data for disease identification and automation of the recognition of diseases. Deep learning is of great use in this area using the principles of object detection. In this paper, we are using YOLOv3 (you only look once) to determine the diseases in plants, based on the symptoms seen on the leaves. The advantage of using YOLOv3 is that multiple diseases can be detected on the image of a single leaf. An important feature of YOLOv3 is that it can detect small disease spots seen on the leaves. Here, we are concentrating on the bacterial spot disease seen on the bell pepper plant. The identification results show a mean average precision of 90%.

Keywords:

• YOLOv3
• Computer vision
• Training data
• Testing data
• Plant leaf disease detection
• Image labeling

ACKNOWLEDGEMENTS

Author contributions: Second author prepared the dataset, both authors did the experiment, and analyzed the results and wrote the manuscript. Both authors approved the submitted version.

DISCLOSURE STATEMENT

The authors declare that there is no conflict of interest.

Additional information

Funding

This work is selected for funding (INR 10,000) under the student project scheme of KSCSTE (Kerala State Centre for Science Technology and Engineering) [grant number 00456/SPS 65/2021/KSCSTE].

Notes on contributors

Therese Yamuna Mahesh

Therese Yamuna Mahesh is working as associate professor in the Department of Electronics and Communication Engineering at Amal Jyothi College of Engineering, Koovappali, Kerala. She has an experience of 27 years and her research interests include artificial intelligence, image processing and outcome based education. Corresponding author. Email: [email protected], [email protected]

Midhun P. Mathew

Midhun P Mathew received his BTech in electronic and communication from St Joseph College of Engineering, Pala and MTech in communication engineering from Amal Jyothi college of Engineering, Kanjirapally, Kerala in the year 2021. He then worked as assistant professor in Department of Electronic & Communication Engineering, College of Engineering, Poonjar Kerala. His research fields include machine learning and deepnets. Currently, he is persuing research at Cochin University of Science and Technology, Kochi, Kerala. Email: [email protected]