Emerging non-destructive imaging techniques for fruit damage detection: Image processing and analysis

Fruits are vulnerable to mechanical damages and physiological disorders caused by the static and dynamic forces acting on them during transportation and abiotic stresses throughout their growth and development, respectively. Identifying these defects is central to quality monitoring in the fruit processing industry. Conventionally, industries employ manual separation to segregate damaged fruits in the processing line. However, manual sorting is laborious, time-consuming, skilled labor-intensive, and destructive. Besides, it is incapable of inspecting every fruit on a fast-moving conveyor belt. Therefore, industries are looking for rapid, non-destructive, and precise technologies for the online inspection of every fruit in the process line. Non-destructive techniques (NDTs) such as biospeckle, X-ray imaging, hyperspectral imaging (HSI), and thermal imaging (TI) involve noninvasive testing of sample surfaces. Earlier review articles have emphasized the applications of various NDTs in determining fruit quality and safety, but with limited focus on image processing and analysis. Therefore, this review focuses on the working principle of these NDTs in detecting fruit damages, their instrumentation, and the steps involved in image processing and analysis. The final sections highlight the limitations and future prospects pertaining to each technique. Biospeckle, HSI, and TI techniques can detect surface damages due to their limited light penetration depth. The HSI spectrum is useful in detecting the defects and fruit quality parameters. Active TI can detect even minor damages in the fruit, but it is not appropriate for industrial production lines. Conversely, X-ray imaging can detect fruit internal damages. The synergistic applications of these NDTs along with appropriate chemometric procedures are useful in identifying damaged fruits without human interference and evade their entry into the processing line.