Eresearch Office, DVC-Research and Innovation, University of the Western Cape, Private Bag X17, Bellville 7535, South Africa.
SARChI Postharvest Technology Research Laboratory, Faculty of AgrSciences, African Institute for Postharvest Technology, Stellenbosch University, Private Bag X1, Stellenbosch 7602, South Africa.
Sensors (Basel). 2021 Jul 22;21(15):4990. doi: 10.3390/s21154990.
Bruise damage is a very commonly occurring defect in apple fruit which facilitates disease occurrence and spread, leads to fruit deterioration and can greatly contribute to postharvest loss. The detection of bruises at their earliest stage of development can be advantageous for screening purposes. An experiment to induce soft bruises in Golden Delicious apples was conducted by applying impact energy at different levels, which allowed to investigate the detectability of bruises at their latent stage. The existence of bruises that were rather invisible to the naked eye and to a digital camera was proven by reconstruction of hyperspectral images of bruised apples, based on effective wavelengths and data dimensionality reduced hyperspectrograms. Machine learning classifiers, namely ensemble subspace discriminant (ESD), k-nearest neighbors (KNN), support vector machine (SVM) and linear discriminant analysis (LDA) were used to build models for detecting bruises at their latent stage, to study the influence of time after bruise occurrence on detection performance and to model quantitative aspects of bruises (severity), spanning from latent to visible bruises. Over all classifiers, detection models had a higher performance than quantitative ones. Given its highest speed in prediction and high classification performance, SVM was rated most recommendable for detection tasks. However, ESD models had the highest classification accuracy in quantitative (>85%) models and were found to be relatively better suited for such a multiple category classification problem than the rest.
瘀伤损伤是苹果果实中非常常见的缺陷，它有利于疾病的发生和传播，导致果实恶化，并大大促成采后损失。在其最早的发育阶段检测瘀伤对于筛选目的是有利的。通过在不同水平上施加冲击能，对金冠苹果进行了诱导软瘀伤的实验，从而可以在潜伏阶段检测瘀伤的可检测性。通过基于有效波长和降维高光谱图的擦伤苹果高光谱图像的重建，证明了肉眼和数码相机都无法看到的瘀伤的存在。使用集成子空间判别器（ESD）、k-最近邻（KNN）、支持向量机（SVM）和线性判别分析（LDA）等机器学习分类器来建立潜伏阶段检测瘀伤的模型，研究瘀伤发生后时间对检测性能的影响，并对瘀伤（严重程度）的定量方面进行建模，范围从潜伏性瘀伤到可见性瘀伤。在所有分类器中，检测模型的性能均高于定量模型。鉴于其在预测方面的最快速度和较高的分类性能，SVM 被评为最适合检测任务的分类器。然而，在定量模型（>85%）中，ESD 模型具有最高的分类准确性，并且被发现比其他模型更适合这种多类别分类问题。
