An adaptive spherical image transform for high-speed fruit defect detection

摘要

A novel adaptive spherical transform was developed and applied in a machine-vision apple defect sorting system. The image transformation compensates the reflectance intensity gradient on curved objects and provides flexibility in coping withfruit's natural variations in brightness and size. Test results demonstrate the effectiveness of the proposed method for high-speed defect detection on apples. This transform can be applied to other fruits or similar curved objects.