论文部分内容阅读
为了实现不同品种苹果的快速无损鉴别,采用近红外光谱检测技术采集不同品种苹果的漫反射光谱,利用主成分分析法降低苹果近红外光谱的维数,运行模糊C-均值聚类,K调和聚类,GK模糊聚类和GG模糊聚类,实现苹果品种的分类。研究结果表明,采用主成分分析结合聚类分析实现了红富士、花牛和加纳3种苹果的正确识别。该方法属于无监督学习算法,不需要对苹果样本进行学习就可实现苹果品种的鉴别,为实现苹果品种的鉴别提供了一种无监督的快速无损鉴别分析方法。
In order to achieve rapid and non-destructive identification of different varieties of apple, the diffuse reflectance spectra of different varieties of apple were collected by near infrared spectroscopy. The principal component analysis (PCA) method was used to reduce the dimensionality of near infrared spectra of apples. Fuzzy C-means clustering, K- Class, GK fuzzy clustering and GG fuzzy clustering to realize the classification of apple varieties. The results show that the principal component analysis combined with cluster analysis to achieve the correct identification of three kinds of apple red Fuji, Hualan and Ghana. The method belongs to the unsupervised learning algorithm, which can identify the apple varieties without learning the apple samples, and provides an unsupervised rapid non-destructive identification analysis method for the apple varieties identification.