Conclusions
In this study, we developed a new image analysis system that can simultaneously evaluate multiple appearance characteristics of agricultural products. To evaluate the effectiveness of this system, we conducted quality evaluations and cultivar identification on the basis of statistical analyses of the appearance characteristics. The result of the cluster analysis revealed that strawberries could be classified on the basis of their appearance characteristics. This
result indicated that the appearance distances we defined in this study was able to represent the distance close to a human sense. By performing MDS, we were able to visualize the small differences in the appearance of the fruit based on multiple characteristics on a two-dimensional surface. Since we were able to quantitatively evaluate the distance on multiple fruit appearances, we plan to utilize our system for breeding purposes in the future study.
The results of the discriminant analysis revealed that the accuracy of strawberry cultivar classification using 14 cultivars was