沙果腐烂的高光谱图像检测

Detection of Rot in Malus asiatica Nakai Using Hyperspectral Imaging

采用高光谱成像技术对沙果的腐烂进行识别,通过高光谱成像系统采集了18个沙果腐烂样本的高光谱图像,利用主成分分析(PCA)对图像进行数据压缩,分别采用"Sobel"算子和区域生长算法"Region grow"并结合主成分图像对18个沙果腐烂样本进行识别。结果表明,采用高光谱图像技术可以实现对沙果腐烂的识别。该研究为沙果的在线检测提供了理论参考和依据。

Hyperspectral imaging technology is employed to detect rot of Malus asiatica Nakai. 18 RGB image of rot samples are acquired by hyperspectral imaging system. The images of PCA are employed to identify the location and area of defects feature through imaging processing. Using Sobel operator,Region growing algorithm and the images of PCA,the edge and defect feature of 18 Malus asiatica Nakai could be recognized. This investigation demonstrates that the rot defect of Malus asiatica Nakai could detect by hyperspectral imaging technology, which provides a theoretical reference for the on-line detection of Malus asiatica Nakai.