Shi Jiyong, Wang Yueying, Liu Chuanpeng, Li Zhihua, Huang Xiaowei, Guo Zhiming, Zhang Xinai, Zhang Di, Zou Xiaobo
Agricultural Product Processing and Storage Lab, School of Food and Biological Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China.
Food Chem X. 2021 Aug 21;11:100128. doi: 10.1016/j.fochx.2021.100128. eCollection 2021 Oct 30.
Foreign matter (FM) in mixed congee not only reduces the quality of the congee but may also harm consumers. However, the common computer vision methods with poor recognition ability for the homochromatic FM. This study used hyperspectral reflectance images with the pattern recognition model to detect homochromatic FM on the mixed congee surface. First, spectral features corresponding to homochromatic FM and background were extracted from hyperspectral images. Then, based on the optimal spectral preprocessing method, LDA, K-nearest neighbor, backpropagation artificial neural network, and support vector machine (SVM) were used to classify the spectral features. The results revealed that the SVM model input with raw spectra principal components exhibited optimal identification rates of 99.17%. Finally, most of the pixels for homochromatic FM were classified correctly by using the SVM model. To summarized, hyperspectral images combined with pattern recognition are an effective method for recognizing homochromatic FM in mixed congee.
混合粥中的异物（FM）不仅会降低粥的品质，还可能对消费者造成危害。然而，常见的计算机视觉方法对同色异物的识别能力较差。本研究使用高光谱反射图像和模式识别模型来检测混合粥表面的同色异物。首先，从高光谱图像中提取与同色异物和背景相对应的光谱特征。然后，基于最优光谱预处理方法，使用线性判别分析（LDA）、K近邻、反向传播人工神经网络和支持向量机（SVM）对光谱特征进行分类。结果表明，输入原始光谱主成分的支持向量机模型表现出最优的识别率，为99.17%。最后，使用支持向量机模型对大多数同色异物像素进行了正确分类。综上所述，高光谱图像结合模式识别是识别混合粥中同色异物的有效方法。
