2021-Now
Artificial vision system for inspecting the quality of fruits
Fruit sorting is a critical process in the agricultural industry, ensuring that only high-quality goods reach the market. However, traditional sorting methods are labor-intensive, time-consuming, and often subjective. With regard to this problem, machine learning algorithms have been developed to automate the sorting process and enhance its efficiency. In this study, we focused on the African Plum, a fruit tree that grows in tropical regions of Central and West Africa and is widely cultivated in Cameroon. Our aim was to build a machine learning model using the YOLO algorithm to make precise predictions about the quality of the African Plum’s surfaces, both damaged and undamaged. The YOLO algorithm, a deep learning method that uses single neural networks, proved to be highly accurate and fast in detecting damaged surfaces of the African plum. This study highlights the potential of machine learning in improving agricultural processes and provides a valuable contribution to the field of computer vision and agriculture.
Deployed application
- Plum quality inpection
Thesis
- Intelligent Fruit Inspection System: Developing a YOLO-based Model for Identifying Defects on Plums Surface
- Computer Vision for Segmentation and Quantification of Damage Surfaces on African Plum Fruits
Deployed application
- Plum quality inpection
Thesis
- Intelligent Fruit Inspection System: Developing a YOLO-based Model for Identifying Defects on Plums Surface
- Computer Vision for Segmentation and Quantification of Damage Surfaces on African Plum Fruits