Maede Hatefi

About

Maede Hatefi is a researcher advancing the field of precision agriculture through computer vision and deep learning. Her work focuses on developing automated systems for crop monitoring and harvesting, with a particular emphasis on fruit ripeness detection and localization in complex greenhouse environments. In her most-cited paper, "Tomato Ripeness Evaluation and Localization Using Mask R-CNN and DBSCAN Clustering" (2023, 3 citations), Hatefi tackles the challenge of enabling robotic harvesting by integrating Mask R-CNN for instance segmentation with DBSCAN clustering to accurately identify and localize tomatoes at different ripeness stages. Notably, she achieved robust results despite training on a limited dataset of only 62 annotated images, demonstrating the potential of transfer learning in agricultural applications. This work addresses key bottlenecks in automated harvesting—occlusion, variable lighting, and overlapping fruit—and contributes to the broader goal of reducing labor costs and improving efficiency in food production. Hatefi’s research sits at the intersection of artificial intelligence and sustainable agriculture, offering scalable solutions for smart farming.

Research Focus

Key Achievements

Top Papers

1. 1
   Tomato Ripeness Evaluation and Localization Using Mask R-CNN and DBSCAN Clustering

   3 citations · 2023

Key Collaborators

Contact & Links