作者: Kwankamon Dittakan , Nawanol Theera-Ampornpunt , Waraphon Witthayarat , Sararat Hinnoy , Supawit Klaiwan
DOI: 10.1109/INCIT.2017.8257854
关键词:
摘要: This paper presents scale-invariant shape analysis with respect to banana cultivar detection. We consider three cultivars: Cavendish, Lady Finger, and Pisang Awak. present the appropriate image preprocessing methods compare different feature selection algorithms, numbers of features, as well various machine learning models classifier. found that best method is chi square, optimal number features 100. Differences between prediction accuracy are small, but overall, Bayesian network performs best, overall AUC 0.933 84%.