This research project delves into the examination and comparison of diverse computer vision methodologies to assess the precision in detecting and estimating the ripeness level of strawberries. The investigation encompasses the application of multiple techniques, such as Mask RCNN, pixel counting, KNN, and Yolo V5, each contributing unique perspectives to the overall analysis. One key aspect of our study involves evaluating the efficiency of these methodologies by considering the trade-off between the time required for analysis and the quality of results obtained. Through the integration of these methodologies, the aim is to enhance our understanding of how these computer vision approaches perform in terms of characterizing and gauging the maturity of strawberries while also considering the time efficiency of each method.

See the project on Github