This repository encompasses a research project that investigates and compares various computer vision methodologies to enhance the precision in detecting and estimating the ripeness level of strawberries. The primary focus is on evaluating the efficiency of these methodologies, considering the trade-off between the time required for analysis and the quality of results obtained.
The following computer vision techniques are employed in this study:
- Mask RCNN: Utilized for its capabilities in instance segmentation and object detection.
- Pixel Counting: A method focused on quantifying ripeness through pixel analysis.
- KNN (K-Nearest Neighbors): Employed for its classification abilities based on proximity to neighboring data points.
- Yolo V5: Utilized for its real-time object detection capabilities.
One key aspect of this research is the evaluation of the efficiency of each methodology. We aim to understand the trade-off between the complexity of the methodology and the quality of results obtained. This consideration is crucial in determining the practical applicability of these computer vision approaches in real-world scenarios.
This project is licensed under the MIT License.