Whole surface image reconstruction for machine vision inspection of fruit

Abstract

Automated imaging systems offer the potential to inspect the quality and safety of fruits and vegetables consumed by the public. Current automated inspection systems allow fruits such as apples to be sorted for quality attributes such as weight, color, and size based on imaging a portion of the surface of each fruit. However, to ensure the inspected fruits are free of defects and contamination, the whole surface of each fruit must be imaged. The goal of this project was to develop an economical module capable of providing whole surface imaging of apples using mirrors and a single camera. Different configurations of flat and concave mirrors were examined and their ability to approach 100% of an apple's surface were characterized and compared. Specific configurations of two, four, or six parabolic concave mirrors were found capable of imaging an entire apple surface at desired image size for inspection without image distortion. This imaging module developed could be integrated into existing automated inspection systems to leverage the effectiveness of food safety inspection.