Image Processing Based Fruit Damage Recognition: Thermal Imaging, Color Measurement and 3D Reconstruction

Bruising and quality changes of fruits due to bumping and freezing during harvesting, packing and transportation have a direct impact on commodity value and shelf life. The aim of this study was to identify and quantify the damages caused by bumping and freezing on apples and apricots. This was achieved by examining pictures of different fruit varieties before and after bumping and freezing treatments using color measurement, thermal imaging and 3d reconstructon techniques. Experiments were conducted to evaluate the detection performance of the three methods. The results showed that thermal imaging is not suitable for detecting bump damage, but can detect frozen damage with just a small change in temperature. Frozen and bumped damage can be detected by colour measurement. And photogrammetry is suitable for the detection of volume changes after bumping. The comprehensive experimental results of this study provide a scientific basis for the selection of non-destructive testing for damage detection in practical applications, and improve the accuracy and efficiency of fruit quality control.