Deep indicator for fine-grained classification of banana’s ripening stages

Abstract

Determining banana’s ripening stages is becoming an essential requirement for standardizing the quality of commercial bananas. In this paper, we propose a novel convolutional neural network architecture which is designed specifically for the fine-grained classification of banana’s ripening stages. It learns a set of fine-grained image features based on a data-driven mechanism and offers a deep indicator of banana’s ripening stage. The resulted indicator can help to differentiate the subtle differences among subordinate classes of bananas in ripening state. Experimental results from 17,312 images of bananas in different ripening stages show that our deep indicator achieves an accuracy superior significantly to state-of-the-art computer vision-based systems both in rough- and fine-grained classification of ripening stages no matter the bananas bear or not severe defects.