Meta-baseline based on deep neuro-fuzzy network for few-shot plant leaf fungal diseases recognition

ABSTRACT

The emergence and spread of plant diseases can reduce yield. These diseases mainly result from fungi, viruses, and bacteria, of which fungi are the cause of most plant diseases. Deep learning is widely used to identify plant leaf fungal diseases but fails to process fuzzy information alone. A deep neuro-fuzzy network introduces fuzzy sets and fuzzy reasoning rules into deep learning for handling this information. However, since the deep neuro-fuzzy network has limitations, relying on the sufficient training set and requiring retraining when a new task appears, it isn't suitable for few-shot task. While the meta-baseline with the deep neuro-fuzzy network as backbone is an excellent choice, as it combines a deep neuro-fuzzy network and meta-learning to learn from a very few samples and generalize to numerous new samples. Experimental results demonstrate the advantages of the model. This model is an effective method for recognizing few-shot plant leaf fungal diseases.

KEYWORDS:

• Plant fungal leaf diseases
• the deep neuro-fuzzy network
• meta-baseline
• few-shot learning

Disclosure statement

No potential conflict of interest was reported by the author(s).

Informed consent

Informed consent was obtained from all individual participants included in the study.

Additional information

Notes on contributors

Xiangyan Meng

Xiangyan Meng received the B.Sc. degree in computational mathematics and applied software from the Harbin Institute of Technology University, China, in 1997, and the M.Sc. degree in ecological mathematics and the Ph.D. degree in agricultural water and soil engineering from Northeast Agricultural University, China, in 2008 and 2014, respectively. She is currently an Associated Professor with the College of Arts and Sciences, Northeast Agricultural University. Her research interests include agricultural water and soil engineering, and agricultural data analysis.

Xiaole Tian

Xiaole Tian was born in Hebei, China, in 1997. She is currently pursuing the master's degree in management science and engineering with Northeast Agricultural University, China. Her research interest includes machine learning and d intelligent agriculture.

Qiufeng Wu

Qiufeng Wu received the Ph.D. degree in computer application technology from the Harbin Institute of Technology, China, in 2014. He is currently working as an Associated Professor with the College of Arts and Sciences, Northeast Agricultural University. His research interests include machine learning, computer vision, and smart agriculture. He is a CCF member.

Yiping Chen

Yiping Chen received the master's degree in Northeast Agricultural University, Harbin, China, where she is currently pursuing the doctor degree in Dalian University of Technology. Her current research interests focus on machine learning, computer vision, and intelligent agriculture.

Jinchao Pan

Jinchao Pan was born in Heilongjiang, China, in 1997. She is currently pursuing the master's degree in management science and engineering with Northeast Agricultural University, China. Her research interest includes machine learning and intelligent agriculture.

Yan Hang

Yan Hang was born in Sichuan, China, in 1998. She is currently pursuing the master's degree in management science and engineering with Northeast Agricultural University, China. Her research interest includes machine learning and intelligent agriculture.