| Summary: | 碩士 === 國立中興大學 === 通訊工程研究所 === 106 === Phalaenopsis is a significant agricultural product with high economic value in Taiwan and more than 90% of Phalaenopsis is exported to all over the world. In recent reports, Fusarium wilt on Phalaenopsis is a disease that makes farmers suffer seriously. It causes Phalaenopsis leaves to turn yellow, dwindle, dehydrate and finally die. Although Phalaenopsis does not die immediately with Fusarium wilt, it seriously decreases the quality that buyers cannot accept. In recent years, the agricultural products and food inspections have been one of the most important issues all over the world. However, traditional food classification based on external features relies on manual processing, which is time consuming and subjective. Invasive detection depends on chemical analysis, and it is expensive, destructive, and experimental samples can never be eaten and used. Hyperspectral imaging is a popular remote sensing technology and widely used in various fields. It uses different materials with different reflection properties to detect different target. In this thesis, we introduce an emerging method to detect Fusarium wilt at the base of Phalaenopsis stems. The detection model divides Phalaenopsis samples into two categories, healthy and infected. The band selection (BS) processing technique based on band prioritization (BP) is applied to extract significant bands and eliminate redundant bands. The algorithms applied are: constrain energy minimization (CEM), spectral information divergence (SID) and SeQuential N-FINDR. These techniques could help detect Fusarium wilt, and we hope the research would help minimize the farmer’s losses.
|
|---|
