Journal
JOURNAL OF THE SCIENCE OF FOOD AND AGRICULTURE
Volume 98, Issue 12, Pages 4659-4664Publisher
WILEY
DOI: 10.1002/jsfa.8996
Keywords
tea plants; hyperspectral imaging; N fertilizer; classification model; SVM
Funding
- National Key Research and Development Plan [2016YFD0200900]
- Modern Agriculture (tea) Special System of China [CARS-19]
Ask authors/readers for more resources
BACKGROUND: Nitrogen (N) fertilizer plays an important role in tea plantation management, with significant impacts on the photosynthetic capacity, productivity and nutrition status of tea plants. The present study aimed to establish a method for the discrimination of N fertilizer levels using hyperspectral imaging technique. RESULTS: Spectral data were extracted from the region of interest, followed by the first derivative to reduce background noise. Five optimal wavelengths were selected by principal component analysis. Texture features were extracted from the images at optimal wavelengths by gray-level gradient co-occurrence matrix. Support vector machine (SVM) and extreme learning machine were used to build classification models based on spectral data, optimal wavelengths, texture features and data fusion, respectively. The SVM model using fused data gave the best performance with highest correct classification rate of 100% for prediction set. CONCLUSION: The overall results indicated that visible and near-infrared hyperspectral imaging combined with SVM were effective in discriminating N fertilizer levels of tea plants. (C) 2018 Society of Chemical Industry
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available