This item is available under a Creative Commons License for non-commercial use only
1.2 COMPUTER AND INFORMATION SCIENCE, Computer Sciences, Information Science
Effective spoilage detection of perishable food items like fruits and vegetables is essential for retailers who stock and sell large quantities of these items. This research is aimed at developing a non-destructive, rapid and accurate method which is based on Spectral Imaging (SI) used in tandem with Convolutional Neural Network (CNN) to predict whether the fruit is fresh or rotten. The study also aims to determine the number of days before which the fruit rots. This research employs a primary, quantitative and inductive methods to investigate the Deep Learning based approach to detect fruit spoilage. Raspberry fruit in particular has been chosen for the experiment. Baskets of raspberries from three different stores were bought and stored in the refrigerator at four-degree Celsius. Images of these baskets was captured on a daily basis using an RGB digital camera until all the baskets of fruits were rotten. The study employs a Supervised learning-based classification approach where-by the data is labelled based on the physical appearance of fruits in the basket. The results show that a Spectral imaging technique used along with a CNN yields a good accuracy of 86% with the F1 score of 0.82 to classify the fruits as Good or Bad but does not fare well in estimating the number of days before the fruit actually rots. The ability of CNN to process and identify patterns in a SI to detect spoilage in fruits would help fruit retail operators to optimize their business chain.
Prakash, K.K.J. (2018). Spoilage Detection in Raspberry Fruit Based on Spectral Imaging Using Convolutional Neural Networks. Dissertation M.Sc. in Computing (Data Analytics), August 2018.