Detecting chilling injury in Red Delicious apple using hyperspectral imaging and neural networks
Detecting chilling injury in Red Delicious apple using hyperspectral imaging and neural networks
复制标题
DOI：
10.1016/j.postharvbio.2008.11.008
复制
发表时间：
2009-04-01
影响因子：
7
通讯作者：
Vigneault, Clement
中科院分区：
文献类型：
--
作者：
ElMasry, Gamal;Wang, Ning;Vigneault, Clement
研究了高光谱成像（400-1000 nm）和人工神经网络（ANN）技术用于红美味苹果冷害检测的方法。建立了一套苹果高光谱成像系统，对苹果图像进行采集、预处理和光谱特征提取。建立了前向反向传播神经网络模型，用于选择最佳波长，对苹果进行分类，并检测由于冷害引起的硬度变化。人工神经网络筛选出5个最佳波长为717、751、875、960和980 nm。ANN模型进行了训练，测试和验证，使用不同的水果组，以评估模型的鲁棒性。在选定的五个最佳波长的光谱和空间响应，平均分类准确率达到98.4%，区分正常和受伤的水果。测量和预测的硬度值之间的相关系数分别为0.93，0.91和0.92的训练，测试和验证集，分别。这些结果表明，所提出的技术用于检测冷害和预测苹果硬度的潜力。(C)2008 Elsevier B. V.保留所有权利。
Hyperspectral imaging (400-1000 nm) and artificial neural network (ANN) techniques were investigated for the detection of chilling injury in Red Delicious apples. A hyperspectral imaging system was established to acquire and pre-process apple images, as well as to extract apple spectral properties. Feed-forward back-propagation ANN models were developed to select the optimal wavelength(s), classify the apples, and detect firmness changes due to chilling injury. The five optimal wavelengths selected by ANN were 717,751, 875, 960 and 980 nm. The ANN models were trained, tested,and validated using different groups of fruit in order to evaluate the robustness of the models. With the spectral and spatial responses at the selected five optimal wavelengths, an average classification accuracy of 98.4% was achieved for distinguishing between normal and injured fruit. The correlation coefficients between measured and predicted firmness values were 0.93, 0.91 and 0.92 for the training, testing, and validation sets, respectively. These results show the potential of the proposed techniques for detecting chilling injury and predicting apple firmness. (C) 2008 Elsevier B.V. All rights reserved.