The RaspGrade Dataset: Towards Automatic Raspberry Ripeness Grading with Deep Learning
It addresses the need for rapid, non-invasive food quality assessment for the agricultural industry, but is incremental as it applies existing deep learning methods to a new dataset.
This research tackled the problem of real-time raspberry ripeness grading into five classes using computer vision in an industrial setting, resulting in the creation of the RaspGrade dataset with instance segmentation experiments showing challenges in classification due to color similarities and occlusion.
This research investigates the application of computer vision for rapid, accurate, and non-invasive food quality assessment, focusing on the novel challenge of real-time raspberry grading into five distinct classes within an industrial environment as the fruits move along a conveyor belt. To address this, a dedicated dataset of raspberries, namely RaspGrade, was acquired and meticulously annotated. Instance segmentation experiments revealed that accurate fruit-level masks can be obtained; however, the classification of certain raspberry grades presents challenges due to color similarities and occlusion, while others are more readily distinguishable based on color. The acquired and annotated RaspGrade dataset is accessible on Hugging Face at: https://huggingface.co/datasets/FBK-TeV/RaspGrade.