|MO, CHANGYEUN - National Agriculture And Forestry Research Institute (NAFRI)|
|KIM, GIYOUNG - National Agriculture And Forestry Research Institute (NAFRI)|
|LEE, KANGJIN - National Agriculture And Forestry Research Institute (NAFRI)|
|CHO, BYOUNG-KWAN - Chungnam National University|
|LIM, JONGKUK - National Agriculture And Forestry Research Institute (NAFRI)|
|KANG, SUKWON - National Agriculture And Forestry Research Institute (NAFRI)|
Submitted to: Sensors
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/4/2013
Publication Date: 1/6/2014
Citation: Mo, C., Kim, G., Lee, K., Kim, M.S., Cho, B., Lim, J., Kang, S. 2014. Non-destructive quality evaluation of pepper (Capsicum annuum L.) seeds using LED-induced hyperspectral reflectance imaging. Sensors. 14:7489-7504.
Interpretive Summary: Quality and safety attributes of agricultural commodities can be assessed using nondestructive optical sensing technologies. In this study, we developed a viability evaluation method for pepper seeds that is based on hyperspectral reflectance imaging. A model based on multivariate analysis of spectral image data was developed to predict the seed germination viability. Results demonstrated that the method can predict viable and non-viable seeds with 96.7% and 99.4% accuracies, respectively. This research will benefit produce growers, as well as agricultural engineers working to develop rapid means to accurately assess produce seed germination quality.
Technical Abstract: In this study, we develop a viability evaluation method for pepper (Capsicum annuum L.) seed based on hyperspectral reflectance imaging. The reflectance spectra of pepper seeds in the 400–700 nm range are collected from hyperspectral reflectance images obtained using blue, green, and red LED illumination. A partial least squares–discriminant analysis (PLS-DA) model is developed to classify viable and non-viable seeds. Four spectral ranges, which were pretreated using various methods with four types of LEDs (blue, green, red, and RGB), are investigated to develop the classification models. The optimal PLS-DA model based on the standard normal variate for RGB LED illumination (400–700 nm) yields discrimination accuracies of 96.7% and 99.4% for viable seeds and nonviable seeds, respectively. The use of images based on the PLS-DA model with the first-order derivative of a 31.5-nm gap for red LED illumination (600–700 nm) yields 100% discrimination accuracy for both viable and nonviable seeds. The results indicate that a hyperspectral imaging technique based on LED light can be potentially applied to high-quality pepper seed sorting.