腐烂是发生在柑橘类水果中最普遍、 最严重的病害, 早期腐烂果的自动化检测有助于提高水果加工业的市场竞争力。 然而, 目前没有有效的自动化检测技术。 以脐橙为研究对象, 利用荧光高光谱成像检测早期腐烂果。 最佳指数OIF理论用于识别腐烂果的最优波段组合(498.6和591.4 nm)。 基于最优波长的比图像及双阈值分割算法, 识别率达到100%。 研究表明, 该方法能有效克服梗伤果及果梗在紫外线诱导下所产生的荧光效应对腐烂果识别的影响。 该研究为基于多光谱成像技术对早期腐烂果的在线检测系统的开发奠定了基础。

Rottenness is most prevalent and devastating disease that threats citrus fruit. Automatic detection of early rottenness can enhance the competitiveness and profitability of the citrus industry. However, there is no efficient automatic detection technology at this time that could detect this disease. The navel orange was selected as research objective. Hyperspectral fluorescence imaging was used to detect early rottenness in orange. Optimum index factor (OIF) method was applied to identify the optimal band combination. 100% detection rate was achieved based on the optimal bands ratio image and two threshold values. The research showed that the proposed method can effectively overcome the affect from florescence effect because stem damage area and stem also can produce florescence under ultraviolet light. This study will lay a foundation for developing multispectral detection system used in on-line detection of early rottenness fruit.