The RaspGrade Dataset: Towards Automatic Raspberry Ripeness Grading with Deep Learning

TL;DR

This paper introduces the RaspGrade dataset and explores deep learning methods for real-time raspberry ripeness grading using computer vision in industrial settings.

Contribution

It provides a new annotated dataset for raspberry grading and evaluates instance segmentation for fruit detection and classification challenges.

Findings

Accurate fruit-level masks can be obtained with instance segmentation.

Color similarities and occlusion pose challenges for certain raspberry grades.

Some raspberry grades are more distinguishable based on color.

Abstract

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.