Master Assignment
[B] Recognition of Crops Relevant for Food Security from Images – Dataset Compilation and Classification Framework Design
Type: Master EE/CS/HMI
Period: TBD
Student: (Unassigned)
If you are interested, please contact :
Project Background:
Ensuring global food security requires accurate identification and monitoring of key crops that support populations, especially in regions where agriculture is a primary source of livelihood. In collaboration with researchers from Uganda, this project focuses on leveraging machine learning and computer vision to create systems capable of recognizing crops from images. The aim is to build a dataset and design a classification framework that can identify crops essential for food security, such as rice, maize, and other staples, contributing to agricultural planning and sustainability.
Project Overview:
- Compile a dataset of images featuring food security crops across diverse regions and conditions.
- Develop a machine learning classification framework that accurately recognizes and classifies these crops at different growth stages.
- Address challenges related to image quality variation, regional crop diversity, and similar crop appearances.
Why Join?
- Gain valuable experience working on real-world datasets in collaboration with Ugandan researchers and apply your skills in machine learning and computer vision.
- Contribute to meaningful research that supports agriculture in regions facing significant food security challenges, with potential global impact.
Who Should Apply?
- Students with a background in machine learning and computer vision.
Those passionate about using AI to address global challenges like food security and sustainable agriculture.