Papers
2
Total Citations
68
H-Index
2
About
Mingfang He is a leading researcher in computer vision and fine-grained object recognition, with a focus on agricultural and ecological applications. His work bridges deep learning and real-world environmental challenges, particularly in plant disease detection and insect classification. He is best known for developing BCTNet, a novel deep learning architecture that achieves precise apple leaf disease detection under unconstrained, complex field conditions—a paper that has garnered 53 citations since 2023, reflecting its significant impact on smart agriculture. Earlier, He pioneered a rapid fine-grained classification method for butterflies by fusing FCM-KM clustering with Mask R-CNN, enabling robotic vision systems to accurately locate and recognize butterfly species in natural habitats. This work, with 15 citations, addresses the critical need for automated biodiversity monitoring. He’s contributions are notable for their practical deployment in unconstrained environments, advancing both precision agriculture and ecological observation. His research continues to influence the development of robust, real-time visual recognition systems for challenging outdoor settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2