Nondestructive Identification of Salmon Adulteration with Water Based on Hyperspectral Data
Nondestructive Identification of Salmon Adulteration with Water Based on Hyperspectral Data
复制标题
DOI：
10.1155/2018/1809297
复制
发表时间：
2018-12
影响因子：
3.3
通讯作者：
Zhang Tao;Biyao Wang;Peng Yan;Kunlun Wang;Xu Zhang;Huihui Wang;Yan Lv
中科院分区：
文献类型：
--
作者：
Zhang Tao;Biyao Wang;Peng Yan;Kunlun Wang;Xu Zhang;Huihui Wang;Yan Lv
针对注水三文鱼掺假鉴别，提出了一种基于高光谱图像的无损鉴别方法。使用系统获得了可见光和近红外范围（390-1050 nm）的鲑鱼片的高光谱图像。原始高光谱数据通过主成分分析（PCA）进行处理。根据图像质量和PCA参数，选择第二主成分(PC2)图像作为特征图像，提取特征图像权重系数局部极值对应的波长作为特征波长，分别为454.9、512.3和569.1 nm。在此基础上，分别独立设置颜色与特征波长光谱结合、纹理与特征波长光谱结合、颜色-纹理与特征波长光谱结合作为输入，进行基于自组织特征图（SOM）网络的鲑鱼掺假识别建模。分析模型相邻神经元之间的距离和特征权重，实现识别结果的可视化。结果表明，以纹理颜色结合特征波长光谱融合特征为输入的基于SOM的模型具有最佳性能，识别准确率高达96.7%。
For the identification of salmon adulteration with water injection, a nondestructive identification method based on hyperspectral images was proposed. The hyperspectral images of salmon fillets in visible and near-infrared ranges (390–1050 nm) were obtained with a system. The original hyperspectral data were processed through the principal-component analysis (PCA). According to the image quality and PCA parameters, a second principal-component (PC2) image was selected as the feature image, and the wavelengths corresponding to the local extremum values of feature image weighting coefficients were extracted as feature wavelengths, which were 454.9, 512.3, and 569.1 nm. On this basis, the color combined with spectra at feature wavelengths, texture combined with spectra at feature wavelengths, and color-texture combined with spectra at feature wavelengths were independently set as the input, for the modeling of salmon adulteration identification based on the self-organizing feature map (SOM) network. The distances between neighboring neurons and feature weights of the models were analyzed to realize the visualization of identification results. The results showed that the SOM-based model, with texture-color combined with fusion features of spectra at feature wavelengths as the input, was evaluated to possess the best performance and identification accuracy is as high as 96.7%.