Non-destructive fruit quality assessment: a review on emerging trends in thermal imaging technology

Abstract

As a vital non-destructive technique for fruit quality assessment, thermal imaging makes use of temperature changes to identify defects, disease, and maturity. With a focus on fruit grading specifically, this overview of the literature highlights the most recent advancements and applications of thermal imaging in agriculture. Infrared thermography, hyperspectral imaging, and deep learning algorithm integration are just a few of the technologies and methodologies that are covered in this article. The review includes significant research that demonstrates the utility of thermal imaging in accurately identifying diseases, classifying fruitripeness, and detecting bruises early on. Thermal imaging has been successfully used, for instance, in the ripeness-based classification of apples, the discovery of early disease in olive trees, and the identification of internal fruit anomalies in citrus fruits. The application of machine learning and deep learning models such as CNNs and LSTMs, considerably enhances the accuracy and efficiency of thermal image analysis by enabling automated and real-time quality assessments. Regardless the significant advantages, difficulties like environmental influences, data processing needs, and exorbitant expenses persist. The analysis also looks into possible future paths, such as combining thermal imaging with IoT technology and creating affordable ways to increase its use in agriculture. Overall, this thorough analysis highlights how thermal imaging can revolutionize contemporary agricultural methods, especially when it comes to improving fruit grading procedures, guaranteeing food safety, and lowering post-harvest losses.