Machine Vision-Based Measurement Systems for Fruit and Vegetable Quality Control in Postharvest

Area of Science:

• Agricultural Engineering
• Food Science
• Computer Vision

Background:

• Agricultural commodities exhibit inherent variability in physical attributes (color, shape, size) and dynamic quality changes over time.
• Manual inspection of fruit and vegetable quality is time-consuming and subjective, hindering comprehensive quality control.
• Ensuring food standards necessitates objective, repeatable, and efficient quality assessment methods.

Purpose of the Study:

• To review the current state-of-the-art in machine vision-based systems for agricultural commodity inspection.
• To highlight the capabilities of optical technologies for non-destructive quality assessment and monitoring.
• To explore advancements in spectral image analysis for internal quality and contaminant detection.

Main Methods:

• Utilizing machine vision systems with advanced optical technologies (e.g., UV, NIR) for image acquisition.
• Developing algorithms for spectral image analysis to assess quality attributes.
• Implementing systems for non-destructive examination of fruits and vegetables.

Main Results:

• Machine vision enables rapid, objective, and repeatable inspection of agricultural products, surpassing manual methods.
• Optical technologies allow quality assessment beyond human visual perception, including spectral ranges like ultraviolet and near-infrared.
• Applications range from sorting by commercial grades to detecting contaminants and analyzing surface chemical compounds.

Conclusions:

• Machine vision-based systems are crucial for modern, efficient, and accurate quality control in the agricultural sector.
• Integrating diverse technologies, from image acquisition to spectral analysis, is key to developing sophisticated inspection tools.
• Future developments focus on enhanced internal quality assessment and contaminant detection using advanced spectral imaging techniques.