Unsupervised Tomato Split Anomaly Detection Using Hyperspectral Imaging and Variational Autoencoders

Abstract

Tomato anomalies/damages pose a significant challenge in greenhouse farming. While this method of cultivation benefits from efficient resource utilization, anomalies can significantly degrade the quality of farm produce. A common anomaly associated with tomatoes is splitting, characterized by the development of cracks on the tomato skin, which degrades its quality. Detecting this type of anomaly is challenging due to dynamic variations in appearance and sizes, compounded by dataset scarcity. We address this problem in an unsupervised manner by utilizing a tailored variational autoencoder (VAE) with hyperspectral input. Preliminary analysis of the dataset enabled us to select the optimal range of wavelengths for detecting this anomaly. Our findings indicate that the 530 nm–550 nm range is suitable for identifying tomato dry splits. The proposed VAE model achieved a 97% detection accuracy for tomato split anomalies in the test data. The analysis on reconstruction loss allows us to not only detect the anomalies but also to some degree estimate the anomalous regions.