Milk Thistle Segmentation

Project overview

Agricultural field images containing milk thistle plants were annotated for a computer vision dataset focused on detecting and segmenting milk thistle vegetation. Precise polygon annotations were created around visible milk thistle plants to generate high-quality training data for an AI-based segmentation model.

Work performed

• Reviewed and organised the agricultural image dataset before annotation.
• Visible milk thistle plants were identified within field images.
• Precise polygon annotations were created along the boundaries of the plants.
• Labelling remained consistent throughout using the Milk Thistle class.
• Partially visible plants were annotated where applicable.
• Quality checks were performed, and inaccurate or incomplete polygons were corrected.
• Annotations were confirmed suitable for agricultural segmentation model training.

What made it hard

• Identifying milk thistle plants among crops, weeds and soil.
• Irregular plant shapes and dense vegetation complicated annotation.
• Partially visible or overlapping plants had to be handled carefully.
• Accurate polygon boundaries around leaves and plant structures were difficult to maintain.
• Varying lighting, camera angles and field conditions affected visibility.

Result

A high-quality milk thistle segmentation dataset was completed with precise polygon annotations. The dataset was prepared for training a computer vision model capable of automatically detecting and segmenting milk thistle plants in agricultural field images.

Final deliverable

Accurate polygon annotations for milk thistle plants were delivered with consistent labelling and annotation quality maintained throughout the dataset. The final output was prepared according to project requirements and was ready for AI model training and agricultural computer vision applications.